release 2016.03.26

encode_dict functionality has been improved and moved directly into compat_urllib_parse_urlencode
All occurrences of compat_urllib_parse.urlencode throughout the codebase have been replaced by compat_urllib_parse_urlencode

Closes #8974

AUTHORS

@@ -161,3 +161,9 @@ Jens Wille
 Robin Houtevelts
 Patrick Griffis
 Aidan Rowe
+mutantmonkey
+Ben Congdon
+Kacper Michajłow
+José Joaquín Atria
+Viťas Strádal
+Kagami Hiiragi

CONTRIBUTING.md

@@ -85,7 +85,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make
+* make (both GNU make and BSD make are supported)
 * pandoc
 * zip
 * nosetests

Makefile

@@ -12,15 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
 PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
-ifeq ($(PREFIX),/usr)
-	SYSCONFDIR=/etc
-else
-	ifeq ($(PREFIX),/usr/local)
-		SYSCONFDIR=/etc
-	else
-		SYSCONFDIR=$(PREFIX)/etc
-	endif
-endif
+SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
 
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	install -d $(DESTDIR)$(BINDIR)

README.md

@@ -164,6 +164,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      (e.g. 50K or 4.2M)
     -R, --retries RETRIES            Number of retries (default is 10), or
                                      "infinite".
+    --fragment-retries RETRIES       Number of retries for a fragment (default
+                                     is 10), or "infinite" (DASH only)
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -181,7 +183,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      to play it)
     --external-downloader COMMAND    Use the specified external downloader.
                                      Currently supports
-                                     aria2c,axel,curl,httpie,wget
+                                     aria2c,avconv,axel,curl,ffmpeg,httpie,wget
     --external-downloader-args ARGS  Give these arguments to the external
                                      downloader
 
@@ -376,8 +378,8 @@ which means you can modify it, redistribute it or use it however you like.
     --no-post-overwrites             Do not overwrite post-processed files; the
                                      post-processed files are overwritten by
                                      default
-    --embed-subs                     Embed subtitles in the video (only for mkv
-                                     and mp4 videos)
+    --embed-subs                     Embed subtitles in the video (only for mp4,
+                                     webm and mkv videos)
     --embed-thumbnail                Embed thumbnail in the audio as cover art
     --add-metadata                   Write metadata to the video file
     --metadata-from-title FORMAT     Parse additional metadata like song title /
@@ -831,7 +833,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make
+* make (both GNU make and BSD make are supported)
 * pandoc
 * zip
 * nosetests

docs/supportedsites.md

@@ -54,6 +54,7 @@
  - **AtresPlayer**
  - **ATTTechChannel**
  - **AudiMedia**
+ - **AudioBoom**
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
@@ -73,6 +74,7 @@
  - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
+ - **BioBioChileTV**
  - **BleacherReport**
  - **BleacherReportCMS**
  - **blinkx**
@@ -80,6 +82,7 @@
  - **BokeCC**
  - **Bpb**: Bundeszentrale für politische Bildung
  - **BR**: Bayerischer Rundfunk Mediathek
+ - **BravoTV**
  - **Break**
  - **brightcove:legacy**
  - **brightcove:new**
@@ -98,6 +101,7 @@
  - **CBSNews**: CBS News
  - **CBSNewsLiveVideo**: CBS News Live Videos
  - **CBSSports**
+ - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
  - **Chaturbate**
@@ -167,6 +171,8 @@
  - **Dump**
  - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
+ - **dw**
+ - **dw:article**
  - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
@@ -190,7 +196,6 @@
  - **ExpoTV**
  - **ExtremeTube**
  - **facebook**
- - **facebook:post**
  - **faz.net**
  - **fc2**
  - **Fczenit**
@@ -241,6 +246,7 @@
  - **GPUTechConf**
  - **Groupon**
  - **Hark**
+ - **HBO**
  - **HearThisAt**
  - **Heise**
  - **HellPorno**
@@ -325,6 +331,7 @@
  - **m6**
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
+ - **MakersChannel**
  - **MakerTV**
  - **Malemotion**
  - **MatchTV**
@@ -335,10 +342,12 @@
  - **Mgoon**
  - **Minhateca**
  - **MinistryGrid**
+ - **Minoto**
  - **miomio.tv**
  - **MiTele**: mitele.es
  - **mixcloud**
  - **MLB**
+ - **Mnet**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **Mojvideo**
@@ -435,6 +444,7 @@
  - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
+ - **Openload**
  - **OraTV**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
@@ -495,6 +505,7 @@
  - **Restudy**
  - **ReverbNation**
  - **Revision3**
+ - **RICE**
  - **RingTV**
  - **RottenTomatoes**
  - **Roxwel**
@@ -519,6 +530,7 @@
  - **RUTV**: RUTV.RU
  - **Ruutu**
  - **safari**: safaribooksonline.com online video
+ - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **Sapo**: SAPO Vídeos
@@ -612,7 +624,9 @@
  - **TheOnion**
  - **ThePlatform**
  - **ThePlatformFeed**
+ - **TheScene**
  - **TheSixtyOne**
+ - **TheStar**
  - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
@@ -646,6 +660,7 @@
  - **tv.dfb.de**
  - **TV2**
  - **TV2Article**
+ - **TV3**
  - **TV4**: tv4.se and tv4play.se
  - **TVC**
  - **TVCArticle**
@@ -671,6 +686,7 @@
  - **UDNEmbed**: 聯合影音
  - **Unistra**
  - **Urort**: NRK P3 Urørt
+ - **USAToday**
  - **ustream**
  - **ustream:channel**
  - **Ustudio**
@@ -684,6 +700,7 @@
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
  - **Vice**
+ - **ViceShow**
  - **Viddler**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
@@ -711,6 +728,7 @@
  - **vimeo:channel**
  - **vimeo:group**
  - **vimeo:likes**: Vimeo user likes
+ - **vimeo:ondemand**
  - **vimeo:review**: Review pages on vimeo
  - **vimeo:user**
  - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
@@ -775,6 +793,7 @@
  - **youtube:channel**: YouTube.com channels
  - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
  - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
+ - **youtube:live**: YouTube.com live streams
  - **youtube:playlist**: YouTube.com playlists
  - **youtube:playlists**: YouTube.com user/channel playlists
  - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)

test/test_YoutubeDL.py

@@ -222,6 +222,11 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'dash-video-low')
 
+        ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-low')
+
         formats = [
             {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
         ]
@@ -502,6 +507,9 @@ class TestYoutubeDL(unittest.TestCase):
         assertRegexpMatches(self, ydl._format_note({
             'vbr': 10,
         }), '^\s*10k$')
+        assertRegexpMatches(self, ydl._format_note({
+            'fps': 30,
+        }), '^30fps$')
 
     def test_postprocessors(self):
         filename = 'post-processor-testfile.mp4'

test/test_compat.py

@@ -19,6 +19,7 @@ from youtube_dl.compat import (
     compat_str,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
+    compat_urllib_parse_urlencode,
 )
 
 
@@ -70,6 +71,12 @@ class TestCompat(unittest.TestCase):
         self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
         self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
 
+    def test_compat_urllib_parse_urlencode(self):
+        self.assertEqual(compat_urllib_parse_urlencode({'abc': 'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode({'abc': b'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode({b'abc': 'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode({b'abc': b'def'}), 'abc=def')
+
     def test_compat_shlex_split(self):
         self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
 

test/test_http.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# coding: utf-8
 from __future__ import unicode_literals
 
 # Allow direct execution
@@ -120,5 +121,14 @@ class TestProxy(unittest.TestCase):
         response = ydl.urlopen(req).read().decode('utf-8')
         self.assertEqual(response, 'cn: {0}'.format(url))
 
+    def test_proxy_with_idn(self):
+        ydl = YoutubeDL({
+            'proxy': 'localhost:{0}'.format(self.port),
+        })
+        url = 'http://中文.tw/'
+        response = ydl.urlopen(url).read().decode('utf-8')
+        # b'xn--fiq228c' is '中文'.encode('idna')
+        self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -28,6 +28,7 @@ from youtube_dl.utils import (
     encodeFilename,
     escape_rfc3986,
     escape_url,
+    extract_attributes,
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
@@ -41,6 +42,7 @@ from youtube_dl.utils import (
     orderedSet,
     parse_duration,
     parse_filesize,
+    parse_count,
     parse_iso8601,
     read_batch_urls,
     sanitize_filename,
@@ -76,6 +78,7 @@ from youtube_dl.utils import (
     cli_bool_option,
 )
 from youtube_dl.compat import (
+    compat_chr,
     compat_etree_fromstring,
     compat_urlparse,
     compat_parse_qs,
@@ -574,11 +577,11 @@ class TestUtil(unittest.TestCase):
         )
         self.assertEqual(
             escape_url('http://тест.рф/фрагмент'),
-            'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
+            'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
         )
         self.assertEqual(
             escape_url('http://тест.рф/абв?абв=абв#абв'),
-            'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
+            'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
         )
         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 
@@ -628,6 +631,44 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('{"abc": "def",}')
         self.assertEqual(json.loads(on), {'abc': 'def'})
 
+    def test_extract_attributes(self):
+        self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
+        self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
+        self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
+        self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'})  # XML
+        self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
+        self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'})  # HTML 3.2
+        self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'})  # HTML 4.0
+        self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
+        self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
+        self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
+        self.assertEqual(extract_attributes('<e x >'), {'x': None})
+        self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
+        self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
+        self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
+        self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
+        self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
+        self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'})  # Names lowercased
+        self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
+        self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
+        self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
+        self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
+        self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
+        # "Narrow" Python builds don't support unicode code points outside BMP.
+        try:
+            compat_chr(0x10000)
+            supports_outside_bmp = True
+        except ValueError:
+            supports_outside_bmp = False
+        if supports_outside_bmp:
+            self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
+
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
@@ -653,6 +694,17 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
         self.assertEqual(parse_filesize('1,24 KB'), 1240)
 
+    def test_parse_count(self):
+        self.assertEqual(parse_count(None), None)
+        self.assertEqual(parse_count(''), None)
+        self.assertEqual(parse_count('0'), 0)
+        self.assertEqual(parse_count('1000'), 1000)
+        self.assertEqual(parse_count('1.000'), 1000)
+        self.assertEqual(parse_count('1.1k'), 1100)
+        self.assertEqual(parse_count('1.1kk'), 1100000)
+        self.assertEqual(parse_count('1.1kk '), 1100000)
+        self.assertEqual(parse_count('1.1kk views'), 1100000)
+
     def test_version_tuple(self):
         self.assertEqual(version_tuple('1'), (1,))
         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))

tox.ini

@@ -8,6 +8,6 @@ deps =
 passenv = HOME
 defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
     --exclude test_subtitles.py --exclude test_write_annotations.py
-    --exclude test_youtube_lists.py
+    --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py
 commands = nosetests --verbose {posargs:{[testenv]defaultargs}}  # --with-coverage --cover-package=youtube_dl --cover-html
                                                # test.test_download:TestDownload.test_NowVideo

youtube_dl/YoutubeDL.py

@@ -905,7 +905,7 @@ class YoutubeDL(object):
                 '*=': lambda attr, value: value in attr,
             }
             str_operator_rex = re.compile(r'''(?x)
-                \s*(?P<key>ext|acodec|vcodec|container|protocol)
+                \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id)
                 \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
                 \s*(?P<value>[a-zA-Z0-9._-]+)
                 \s*$
@@ -1234,6 +1234,10 @@ class YoutubeDL(object):
                 if t.get('id') is None:
                     t['id'] = '%d' % i
 
+        if self.params.get('list_thumbnails'):
+            self.list_thumbnails(info_dict)
+            return
+
         if thumbnails and 'thumbnail' not in info_dict:
             info_dict['thumbnail'] = thumbnails[-1]['url']
 
@@ -1335,9 +1339,6 @@ class YoutubeDL(object):
         if self.params.get('listformats'):
             self.list_formats(info_dict)
             return
-        if self.params.get('list_thumbnails'):
-            self.list_thumbnails(info_dict)
-            return
 
         req_format = self.params.get('format')
         if req_format is None:
@@ -1835,7 +1836,7 @@ class YoutubeDL(object):
         if fdict.get('language'):
             if res:
                 res += ' '
-            res += '[%s]' % fdict['language']
+            res += '[%s] ' % fdict['language']
         if fdict.get('format_note') is not None:
             res += fdict['format_note'] + ' '
         if fdict.get('tbr') is not None:
@@ -1856,7 +1857,9 @@ class YoutubeDL(object):
         if fdict.get('vbr') is not None:
             res += '%4dk' % fdict['vbr']
         if fdict.get('fps') is not None:
-            res += ', %sfps' % fdict['fps']
+            if res:
+                res += ', '
+            res += '%sfps' % fdict['fps']
         if fdict.get('acodec') is not None:
             if res:
                 res += ', '
@@ -1899,13 +1902,8 @@ class YoutubeDL(object):
     def list_thumbnails(self, info_dict):
         thumbnails = info_dict.get('thumbnails')
         if not thumbnails:
-            tn_url = info_dict.get('thumbnail')
-            if tn_url:
-                thumbnails = [{'id': '0', 'url': tn_url}]
-            else:
-                self.to_screen(
-                    '[info] No thumbnails present for %s' % info_dict['id'])
-                return
+            self.to_screen('[info] No thumbnails present for %s' % info_dict['id'])
+            return
 
         self.to_screen(
             '[info] Thumbnails for %s:' % info_dict['id'])

youtube_dl/__init__.py

@@ -144,14 +144,20 @@ def _real_main(argv=None):
         if numeric_limit is None:
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit
-    if opts.retries is not None:
-        if opts.retries in ('inf', 'infinite'):
-            opts_retries = float('inf')
+
+    def parse_retries(retries):
+        if retries in ('inf', 'infinite'):
+            parsed_retries = float('inf')
         else:
             try:
-                opts_retries = int(opts.retries)
+                parsed_retries = int(retries)
             except (TypeError, ValueError):
                 parser.error('invalid retry count specified')
+        return parsed_retries
+    if opts.retries is not None:
+        opts.retries = parse_retries(opts.retries)
+    if opts.fragment_retries is not None:
+        opts.fragment_retries = parse_retries(opts.fragment_retries)
     if opts.buffersize is not None:
         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
         if numeric_buffersize is None:
@@ -299,7 +305,8 @@ def _real_main(argv=None):
         'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
-        'retries': opts_retries,
+        'retries': opts.retries,
+        'fragment_retries': opts.fragment_retries,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,

youtube_dl/compat.py

@@ -77,6 +77,11 @@ try:
 except ImportError:  # Python 2
     from urllib import urlretrieve as compat_urlretrieve
 
+try:
+    from html.parser import HTMLParser as compat_HTMLParser
+except ImportError:  # Python 2
+    from HTMLParser import HTMLParser as compat_HTMLParser
+
 
 try:
     from subprocess import DEVNULL
@@ -164,6 +169,31 @@ except ImportError:  # Python 2
         string = string.replace('+', ' ')
         return compat_urllib_parse_unquote(string, encoding, errors)
 
+try:
+    from urllib.parse import urlencode as compat_urllib_parse_urlencode
+except ImportError:  # Python 2
+    # Python 2 will choke in urlencode on mixture of byte and unicode strings.
+    # Possible solutions are to either port it from python 3 with all
+    # the friends or manually ensure input query contains only byte strings.
+    # We will stick with latter thus recursively encoding the whole query.
+    def compat_urllib_parse_urlencode(query, doseq=0, encoding='utf-8'):
+        def encode_elem(e):
+            if isinstance(e, dict):
+                e = encode_dict(e)
+            elif isinstance(e, (list, tuple,)):
+                e = encode_list(e)
+            elif isinstance(e, compat_str):
+                e = e.encode(encoding)
+            return e
+
+        def encode_dict(d):
+            return dict((encode_elem(k), encode_elem(v)) for k, v in d.items())
+
+        def encode_list(l):
+            return [encode_elem(e) for e in l]
+
+        return compat_urllib_parse.urlencode(encode_elem(query), doseq=doseq)
+
 try:
     from urllib.request import DataHandler as compat_urllib_request_DataHandler
 except ImportError:  # Python < 3.4
@@ -251,6 +281,16 @@ else:
                 el.text = el.text.decode('utf-8')
         return doc
 
+if sys.version_info < (2, 7):
+    # Here comes the crazy part: In 2.6, if the xpath is a unicode,
+    # .//node does not match if a node is a direct child of . !
+    def compat_xpath(xpath):
+        if isinstance(xpath, compat_str):
+            xpath = xpath.encode('ascii')
+        return xpath
+else:
+    compat_xpath = lambda xpath: xpath
+
 try:
     from urllib.parse import parse_qs as compat_parse_qs
 except ImportError:  # Python 2
@@ -543,6 +583,7 @@ else:
     from tokenize import generate_tokens as compat_tokenize_tokenize
 
 __all__ = [
+    'compat_HTMLParser',
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',
@@ -572,6 +613,7 @@ __all__ = [
     'compat_urllib_parse_unquote',
     'compat_urllib_parse_unquote_plus',
     'compat_urllib_parse_unquote_to_bytes',
+    'compat_urllib_parse_urlencode',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
     'compat_urllib_request_DataHandler',
@@ -579,6 +621,7 @@ __all__ = [
     'compat_urlparse',
     'compat_urlretrieve',
     'compat_xml_parse_error',
+    'compat_xpath',
     'shlex_quote',
     'subprocess_check_output',
     'workaround_optparse_bug9161',

youtube_dl/downloader/__init__.py

@@ -1,14 +1,16 @@
 from __future__ import unicode_literals
 
 from .common import FileDownloader
-from .external import get_external_downloader
 from .f4m import F4mFD
 from .hls import HlsFD
-from .hls import NativeHlsFD
 from .http import HttpFD
-from .rtsp import RtspFD
 from .rtmp import RtmpFD
 from .dash import DashSegmentsFD
+from .rtsp import RtspFD
+from .external import (
+    get_external_downloader,
+    FFmpegFD,
+)
 
 from ..utils import (
     determine_protocol,
@@ -16,8 +18,8 @@ from ..utils import (
 
 PROTOCOL_MAP = {
     'rtmp': RtmpFD,
-    'm3u8_native': NativeHlsFD,
-    'm3u8': HlsFD,
+    'm3u8_native': HlsFD,
+    'm3u8': FFmpegFD,
     'mms': RtspFD,
     'rtsp': RtspFD,
     'f4m': F4mFD,
@@ -30,14 +32,17 @@ def get_suitable_downloader(info_dict, params={}):
     protocol = determine_protocol(info_dict)
     info_dict['protocol'] = protocol
 
+    # if (info_dict.get('start_time') or info_dict.get('end_time')) and not info_dict.get('requested_formats') and FFmpegFD.can_download(info_dict):
+    #     return FFmpegFD
+
     external_downloader = params.get('external_downloader')
     if external_downloader is not None:
         ed = get_external_downloader(external_downloader)
-        if ed.supports(info_dict):
+        if ed.can_download(info_dict):
             return ed
 
     if protocol == 'm3u8' and params.get('hls_prefer_native'):
-        return NativeHlsFD
+        return HlsFD
 
     return PROTOCOL_MAP.get(protocol, HttpFD)
 

youtube_dl/downloader/common.py

@@ -115,6 +115,10 @@ class FileDownloader(object):
             return '%10s' % '---b/s'
         return '%10s' % ('%s/s' % format_bytes(speed))
 
+    @staticmethod
+    def format_retries(retries):
+        return 'inf' if retries == float('inf') else '%.0f' % retries
+
     @staticmethod
     def best_block_size(elapsed_time, bytes):
         new_min = max(bytes / 2.0, 1.0)
@@ -297,7 +301,9 @@ class FileDownloader(object):
 
     def report_retry(self, count, retries):
         """Report retry in case of HTTP error 5xx"""
-        self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %.0f)...' % (count, retries))
+        self.to_screen(
+            '[download] Got server HTTP error. Retrying (attempt %d of %s)...'
+            % (count, self.format_retries(retries)))
 
     def report_file_already_downloaded(self, file_name):
         """Report file has already been fully downloaded."""

youtube_dl/downloader/dash.py

@@ -4,6 +4,7 @@ import os
 import re
 
 from .fragment import FragmentFD
+from ..compat import compat_urllib_error
 from ..utils import (
     sanitize_open,
     encodeFilename,
@@ -36,20 +37,41 @@ class DashSegmentsFD(FragmentFD):
 
         segments_filenames = []
 
-        def append_url_to_file(target_url, target_filename):
-            success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
-            if not success:
+        fragment_retries = self.params.get('fragment_retries', 0)
+
+        def append_url_to_file(target_url, tmp_filename, segment_name):
+            target_filename = '%s-%s' % (tmp_filename, segment_name)
+            count = 0
+            while count <= fragment_retries:
+                try:
+                    success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
+                    if not success:
+                        return False
+                    down, target_sanitized = sanitize_open(target_filename, 'rb')
+                    ctx['dest_stream'].write(down.read())
+                    down.close()
+                    segments_filenames.append(target_sanitized)
+                    break
+                except (compat_urllib_error.HTTPError, ) as err:
+                    # YouTube may often return 404 HTTP error for a fragment causing the
+                    # whole download to fail. However if the same fragment is immediately
+                    # retried with the same request data this usually succeeds (1-2 attemps
+                    # is usually enough) thus allowing to download the whole file successfully.
+                    # So, we will retry all fragments that fail with 404 HTTP error for now.
+                    if err.code != 404:
+                        raise
+                    # Retry fragment
+                    count += 1
+                    if count <= fragment_retries:
+                        self.report_retry_fragment(segment_name, count, fragment_retries)
+            if count > fragment_retries:
+                self.report_error('giving up after %s fragment retries' % fragment_retries)
                 return False
-            down, target_sanitized = sanitize_open(target_filename, 'rb')
-            ctx['dest_stream'].write(down.read())
-            down.close()
-            segments_filenames.append(target_sanitized)
 
         if initialization_url:
-            append_url_to_file(initialization_url, ctx['tmpfilename'] + '-Init')
+            append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
         for i, segment_url in enumerate(segment_urls):
-            segment_filename = '%s-Seg%d' % (ctx['tmpfilename'], i)
-            append_url_to_file(segment_url, segment_filename)
+            append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
 
         self._finish_frag_download(ctx)
 

youtube_dl/downloader/external.py

@@ -2,8 +2,11 @@ from __future__ import unicode_literals
 
 import os.path
 import subprocess
+import sys
+import re
 
 from .common import FileDownloader
+from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
 from ..utils import (
     cli_option,
     cli_valueless_option,
@@ -11,6 +14,8 @@ from ..utils import (
     cli_configuration_args,
     encodeFilename,
     encodeArgument,
+    handle_youtubedl_headers,
+    check_executable,
 )
 
 
@@ -45,10 +50,18 @@ class ExternalFD(FileDownloader):
     def exe(self):
         return self.params.get('external_downloader')
 
+    @classmethod
+    def available(cls):
+        return check_executable(cls.get_basename(), [cls.AVAILABLE_OPT])
+
     @classmethod
     def supports(cls, info_dict):
         return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
 
+    @classmethod
+    def can_download(cls, info_dict):
+        return cls.available() and cls.supports(info_dict)
+
     def _option(self, command_option, param):
         return cli_option(self.params, command_option, param)
 
@@ -76,6 +89,8 @@ class ExternalFD(FileDownloader):
 
 
 class CurlFD(ExternalFD):
+    AVAILABLE_OPT = '-V'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '--location', '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
@@ -89,6 +104,8 @@ class CurlFD(ExternalFD):
 
 
 class AxelFD(ExternalFD):
+    AVAILABLE_OPT = '-V'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
@@ -99,6 +116,8 @@ class AxelFD(ExternalFD):
 
 
 class WgetFD(ExternalFD):
+    AVAILABLE_OPT = '--version'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
         for key, val in info_dict['http_headers'].items():
@@ -112,6 +131,8 @@ class WgetFD(ExternalFD):
 
 
 class Aria2cFD(ExternalFD):
+    AVAILABLE_OPT = '-v'
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-c']
         cmd += self._configuration_args([
@@ -130,12 +151,112 @@ class Aria2cFD(ExternalFD):
 
 
 class HttpieFD(ExternalFD):
+    @classmethod
+    def available(cls):
+        return check_executable('http', ['--version'])
+
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
         for key, val in info_dict['http_headers'].items():
             cmd += ['%s:%s' % (key, val)]
         return cmd
 
+
+class FFmpegFD(ExternalFD):
+    @classmethod
+    def supports(cls, info_dict):
+        return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
+
+    @classmethod
+    def available(cls):
+        return FFmpegPostProcessor().available
+
+    def _call_downloader(self, tmpfilename, info_dict):
+        url = info_dict['url']
+        ffpp = FFmpegPostProcessor(downloader=self)
+        if not ffpp.available:
+            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            return False
+        ffpp.check_version()
+
+        args = [ffpp.executable, '-y']
+
+        args += self._configuration_args()
+
+        # start_time = info_dict.get('start_time') or 0
+        # if start_time:
+        #     args += ['-ss', compat_str(start_time)]
+        # end_time = info_dict.get('end_time')
+        # if end_time:
+        #     args += ['-t', compat_str(end_time - start_time)]
+
+        if info_dict['http_headers'] and re.match(r'^https?://', url):
+            # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
+            # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
+            headers = handle_youtubedl_headers(info_dict['http_headers'])
+            args += [
+                '-headers',
+                ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
+
+        protocol = info_dict.get('protocol')
+
+        if protocol == 'rtmp':
+            player_url = info_dict.get('player_url')
+            page_url = info_dict.get('page_url')
+            app = info_dict.get('app')
+            play_path = info_dict.get('play_path')
+            tc_url = info_dict.get('tc_url')
+            flash_version = info_dict.get('flash_version')
+            live = info_dict.get('rtmp_live', False)
+            if player_url is not None:
+                args += ['-rtmp_swfverify', player_url]
+            if page_url is not None:
+                args += ['-rtmp_pageurl', page_url]
+            if app is not None:
+                args += ['-rtmp_app', app]
+            if play_path is not None:
+                args += ['-rtmp_playpath', play_path]
+            if tc_url is not None:
+                args += ['-rtmp_tcurl', tc_url]
+            if flash_version is not None:
+                args += ['-rtmp_flashver', flash_version]
+            if live:
+                args += ['-rtmp_live', 'live']
+
+        args += ['-i', url, '-c', 'copy']
+        if protocol == 'm3u8':
+            if self.params.get('hls_use_mpegts', False):
+                args += ['-f', 'mpegts']
+            else:
+                args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
+        elif protocol == 'rtmp':
+            args += ['-f', 'flv']
+        else:
+            args += ['-f', EXT_TO_OUT_FORMATS.get(info_dict['ext'], info_dict['ext'])]
+
+        args = [encodeArgument(opt) for opt in args]
+        args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
+
+        self._debug_cmd(args)
+
+        proc = subprocess.Popen(args, stdin=subprocess.PIPE)
+        try:
+            retval = proc.wait()
+        except KeyboardInterrupt:
+            # subprocces.run would send the SIGKILL signal to ffmpeg and the
+            # mp4 file couldn't be played, but if we ask ffmpeg to quit it
+            # produces a file that is playable (this is mostly useful for live
+            # streams). Note that Windows is not affected and produces playable
+            # files (see https://github.com/rg3/youtube-dl/issues/8300).
+            if sys.platform != 'win32':
+                proc.communicate(b'q')
+            raise
+        return retval
+
+
+class AVconvFD(FFmpegFD):
+    pass
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()

youtube_dl/downloader/fragment.py

@@ -19,8 +19,17 @@ class HttpQuietDownloader(HttpFD):
 class FragmentFD(FileDownloader):
     """
     A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests).
+
+    Available options:
+
+    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH only)
     """
 
+    def report_retry_fragment(self, fragment_name, count, retries):
+        self.to_screen(
+            '[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
+            % (fragment_name, count, self.format_retries(retries)))
+
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)
         self._start_frag_download(ctx)

youtube_dl/downloader/hls.py

@@ -1,87 +1,19 @@
 from __future__ import unicode_literals
 
-import os
+import os.path
 import re
-import subprocess
-import sys
 
-from .common import FileDownloader
 from .fragment import FragmentFD
 
 from ..compat import compat_urlparse
-from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..utils import (
-    encodeArgument,
     encodeFilename,
     sanitize_open,
-    handle_youtubedl_headers,
 )
 
 
-class HlsFD(FileDownloader):
-    def real_download(self, filename, info_dict):
-        url = info_dict['url']
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-
-        ffpp = FFmpegPostProcessor(downloader=self)
-        if not ffpp.available:
-            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
-            return False
-        ffpp.check_version()
-
-        args = [ffpp.executable, '-y']
-
-        if info_dict['http_headers'] and re.match(r'^https?://', url):
-            # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
-            # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
-            headers = handle_youtubedl_headers(info_dict['http_headers'])
-            args += [
-                '-headers',
-                ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
-
-        args += ['-i', url, '-c', 'copy']
-        if self.params.get('hls_use_mpegts', False):
-            args += ['-f', 'mpegts']
-        else:
-            args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
-
-        args = [encodeArgument(opt) for opt in args]
-        args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
-
-        self._debug_cmd(args)
-
-        proc = subprocess.Popen(args, stdin=subprocess.PIPE)
-        try:
-            retval = proc.wait()
-        except KeyboardInterrupt:
-            # subprocces.run would send the SIGKILL signal to ffmpeg and the
-            # mp4 file couldn't be played, but if we ask ffmpeg to quit it
-            # produces a file that is playable (this is mostly useful for live
-            # streams). Note that Windows is not affected and produces playable
-            # files (see https://github.com/rg3/youtube-dl/issues/8300).
-            if sys.platform != 'win32':
-                proc.communicate(b'q')
-            raise
-        if retval == 0:
-            fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
-            self.try_rename(tmpfilename, filename)
-            self._hook_progress({
-                'downloaded_bytes': fsize,
-                'total_bytes': fsize,
-                'filename': filename,
-                'status': 'finished',
-            })
-            return True
-        else:
-            self.to_stderr('\n')
-            self.report_error('%s exited with code %d' % (ffpp.basename, retval))
-            return False
-
-
-class NativeHlsFD(FragmentFD):
-    """ A more limited implementation that does not require ffmpeg """
+class HlsFD(FragmentFD):
+    """ A limited implementation that does not require ffmpeg """
 
     FD_NAME = 'hlsnative'
 

youtube_dl/extractor/__init__.py

@@ -54,6 +54,7 @@ from .arte import (
 from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audimedia import AudiMediaIE
+from .audioboom import AudioBoomIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE, AzubuLiveIE
 from .baidu import BaiduVideoIE
@@ -71,6 +72,7 @@ from .bet import BetIE
 from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
+from .biobiochiletv import BioBioChileTVIE
 from .bleacherreport import (
     BleacherReportIE,
     BleacherReportCMSIE,
@@ -80,6 +82,7 @@ from .bloomberg import BloombergIE
 from .bokecc import BokeCCIE
 from .bpb import BpbIE
 from .br import BRIE
+from .bravotv import BravoTVIE
 from .breakcom import BreakIE
 from .brightcove import (
     BrightcoveLegacyIE,
@@ -106,6 +109,7 @@ from .cbsnews import (
 )
 from .cbssports import CBSSportsIE
 from .ccc import CCCIE
+from .cda import CDAIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .chaturbate import ChaturbateIE
@@ -134,6 +138,7 @@ from .collegerama import CollegeRamaIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
+from .commonprotocols import RtmpIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .crackle import CrackleIE
@@ -188,6 +193,10 @@ from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .dropbox import DropboxIE
+from .dw import (
+    DWIE,
+    DWArticleIE,
+)
 from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
@@ -212,10 +221,7 @@ from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
-from .facebook import (
-    FacebookIE,
-    FacebookPostIE,
-)
+from .facebook import FacebookIE
 from .faz import FazIE
 from .fc2 import FC2IE
 from .fczenit import FczenitIE
@@ -280,6 +286,7 @@ from .goshgay import GoshgayIE
 from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hark import HarkIE
+from .hbo import HBOIE
 from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
 from .hellporno import HellPornoIE
@@ -387,6 +394,7 @@ from .lynda import (
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
+from .makerschannel import MakersChannelIE
 from .makertv import MakerTVIE
 from .malemotion import MalemotionIE
 from .matchtv import MatchTVIE
@@ -396,11 +404,13 @@ from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
+from .minoto import MinotoIE
 from .miomio import MioMioIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
 from .mlb import MLBIE
+from .mnet import MnetIE
 from .mpora import MporaIE
 from .moevideo import MoeVideoIE
 from .mofosex import MofosexIE
@@ -526,6 +536,7 @@ from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
 )
+from .openload import OpenloadIE
 from .ora import OraTVIE
 from .orf import (
     ORFTVthekIE,
@@ -594,6 +605,7 @@ from .regiotv import RegioTVIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
 from .revision3 import Revision3IE
+from .rice import RICEIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
@@ -620,6 +632,7 @@ from .ruutu import RuutuIE
 from .sandia import SandiaIE
 from .safari import (
     SafariIE,
+    SafariApiIE,
     SafariCourseIE,
 )
 from .sapo import SapoIE
@@ -731,7 +744,9 @@ from .theplatform import (
     ThePlatformIE,
     ThePlatformFeedIE,
 )
+from .thescene import TheSceneIE
 from .thesixtyone import TheSixtyOneIE
+from .thestar import TheStarIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
@@ -778,6 +793,7 @@ from .tv2 import (
     TV2IE,
     TV2ArticleIE,
 )
+from .tv3 import TV3IE
 from .tv4 import TV4IE
 from .tvc import (
     TVCIE,
@@ -817,6 +833,7 @@ from .udn import UDNEmbedIE
 from .digiteka import DigitekaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
+from .usatoday import USATodayIE
 from .ustream import UstreamIE, UstreamChannelIE
 from .ustudio import UstudioIE
 from .varzesh3 import Varzesh3IE
@@ -832,7 +849,10 @@ from .vgtv import (
     VGTVIE,
 )
 from .vh1 import VH1IE
-from .vice import ViceIE
+from .vice import (
+    ViceIE,
+    ViceShowIE,
+)
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
@@ -859,6 +879,7 @@ from .vimeo import (
     VimeoChannelIE,
     VimeoGroupsIE,
     VimeoLikesIE,
+    VimeoOndemandIE,
     VimeoReviewIE,
     VimeoUserIE,
     VimeoWatchLaterIE,
@@ -940,7 +961,9 @@ from .youtube import (
     YoutubeChannelIE,
     YoutubeFavouritesIE,
     YoutubeHistoryIE,
+    YoutubeLiveIE,
     YoutubePlaylistIE,
+    YoutubePlaylistsIE,
     YoutubeRecommendedIE,
     YoutubeSearchDateIE,
     YoutubeSearchIE,
@@ -950,7 +973,6 @@ from .youtube import (
     YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
     YoutubeUserIE,
-    YoutubePlaylistsIE,
     YoutubeWatchLaterIE,
 )
 from .zapiks import ZapiksIE

youtube_dl/extractor/abc.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+    _VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',

youtube_dl/extractor/addanime.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
     compat_str,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class AddAnimeIE(InfoExtractor):
-    _VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
+    _VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
     _TESTS = [{
         'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
         'md5': '72954ea10bc979ab5e2eb288b21425a0',
@@ -60,7 +60,7 @@ class AddAnimeIE(InfoExtractor):
             confirm_url = (
                 parsed_url.scheme + '://' + parsed_url.netloc +
                 action + '?' +
-                compat_urllib_parse.urlencode({
+                compat_urllib_parse_urlencode({
                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
             self._download_webpage(
                 confirm_url, video_id,

youtube_dl/extractor/aftonbladet.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
         'info_dict': {

youtube_dl/extractor/aljazeera.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
 
     _TEST = {
         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
@@ -13,24 +13,18 @@ class AlJazeeraIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'The Slum - Episode 1: Deliverance',
             'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
-            'uploader': 'Al Jazeera English',
+            'uploader_id': '665003303001',
+            'timestamp': 1411116829,
+            'upload_date': '20140919',
         },
-        'add_ie': ['BrightcoveLegacy'],
+        'add_ie': ['BrightcoveNew'],
         'skip': 'Not accessible from Travis CI server',
     }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
         program_name = self._match_id(url)
         webpage = self._download_webpage(url, program_name)
         brightcove_id = self._search_regex(
             r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
-
-        return {
-            '_type': 'url',
-            'url': (
-                'brightcove:'
-                'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
-                '&%40videoPlayer={0}'.format(brightcove_id)
-            ),
-            'ie_key': 'BrightcoveLegacy',
-        }
+        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

youtube_dl/extractor/animeondemand.py

@@ -3,10 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_urlparse,
+    compat_str,
+)
 from ..utils import (
     determine_ext,
-    encode_dict,
+    extract_attributes,
     ExtractorError,
     sanitized_Request,
     urlencode_postdata,
@@ -18,7 +21,7 @@ class AnimeOnDemandIE(InfoExtractor):
     _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
     _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
     _NETRC_MACHINE = 'animeondemand'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.anime-on-demand.de/anime/161',
         'info_dict': {
             'id': '161',
@@ -26,7 +29,19 @@ class AnimeOnDemandIE(InfoExtractor):
             'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
         },
         'playlist_mincount': 4,
-    }
+    }, {
+        # Film wording is used instead of Episode
+        'url': 'https://www.anime-on-demand.de/anime/39',
+        'only_matching': True,
+    }, {
+        # Episodes without titles
+        'url': 'https://www.anime-on-demand.de/anime/162',
+        'only_matching': True,
+    }, {
+        # ger/jap, Dub/OmU, account required
+        'url': 'https://www.anime-on-demand.de/anime/169',
+        'only_matching': True,
+    }]
 
     def _login(self):
         (username, password) = self._get_login_info()
@@ -36,6 +51,10 @@ class AnimeOnDemandIE(InfoExtractor):
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
+        if '>Our licensing terms allow the distribution of animes only to German-speaking countries of Europe' in login_page:
+            self.raise_geo_restricted(
+                '%s is only available in German-speaking countries of Europe' % self.IE_NAME)
+
         login_form = self._form_hidden_inputs('new_user', login_page)
 
         login_form.update({
@@ -51,7 +70,7 @@ class AnimeOnDemandIE(InfoExtractor):
             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
 
         request = sanitized_Request(
-            post_url, urlencode_postdata(encode_dict(login_form)))
+            post_url, urlencode_postdata(login_form))
         request.add_header('Referer', self._LOGIN_URL)
 
         response = self._download_webpage(
@@ -91,14 +110,22 @@ class AnimeOnDemandIE(InfoExtractor):
 
         entries = []
 
-        for episode_html in re.findall(r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage):
-            m = re.search(
-                r'class="episodebox-title"[^>]+title="Episode (?P<number>\d+) - (?P<title>.+?)"', episode_html)
-            if not m:
+        for num, episode_html in enumerate(re.findall(
+                r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage), 1):
+            episodebox_title = self._search_regex(
+                (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
+                 r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
+                episode_html, 'episodebox title', default=None, group='title')
+            if not episodebox_title:
                 continue
 
-            episode_number = int(m.group('number'))
-            episode_title = m.group('title')
+            episode_number = int(self._search_regex(
+                r'(?:Episode|Film)\s*(\d+)',
+                episodebox_title, 'episode number', default=num))
+            episode_title = self._search_regex(
+                r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
+                episodebox_title, 'episode title', default=None)
+
             video_id = 'episode-%d' % episode_number
 
             common_info = {
@@ -110,33 +137,86 @@ class AnimeOnDemandIE(InfoExtractor):
 
             formats = []
 
-            playlist_url = self._search_regex(
-                r'data-playlist=(["\'])(?P<url>.+?)\1',
-                episode_html, 'data playlist', default=None, group='url')
-            if playlist_url:
-                request = sanitized_Request(
-                    compat_urlparse.urljoin(url, playlist_url),
-                    headers={
-                        'X-Requested-With': 'XMLHttpRequest',
-                        'X-CSRF-Token': csrf_token,
-                        'Referer': url,
-                        'Accept': 'application/json, text/javascript, */*; q=0.01',
-                    })
+            for input_ in re.findall(
+                    r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', episode_html):
+                attributes = extract_attributes(input_)
+                playlist_urls = []
+                for playlist_key in ('data-playlist', 'data-otherplaylist'):
+                    playlist_url = attributes.get(playlist_key)
+                    if isinstance(playlist_url, compat_str) and re.match(
+                            r'/?[\da-zA-Z]+', playlist_url):
+                        playlist_urls.append(attributes[playlist_key])
+                if not playlist_urls:
+                    continue
 
-                playlist = self._download_json(
-                    request, video_id, 'Downloading playlist JSON', fatal=False)
-                if playlist:
-                    playlist = playlist['playlist'][0]
-                    title = playlist['title']
+                lang = attributes.get('data-lang')
+                lang_note = attributes.get('value')
+
+                for playlist_url in playlist_urls:
+                    kind = self._search_regex(
+                        r'videomaterialurl/\d+/([^/]+)/',
+                        playlist_url, 'media kind', default=None)
+                    format_id_list = []
+                    if lang:
+                        format_id_list.append(lang)
+                    if kind:
+                        format_id_list.append(kind)
+                    if not format_id_list:
+                        format_id_list.append(compat_str(num))
+                    format_id = '-'.join(format_id_list)
+                    format_note = ', '.join(filter(None, (kind, lang_note)))
+                    request = sanitized_Request(
+                        compat_urlparse.urljoin(url, playlist_url),
+                        headers={
+                            'X-Requested-With': 'XMLHttpRequest',
+                            'X-CSRF-Token': csrf_token,
+                            'Referer': url,
+                            'Accept': 'application/json, text/javascript, */*; q=0.01',
+                        })
+                    playlist = self._download_json(
+                        request, video_id, 'Downloading %s playlist JSON' % format_id,
+                        fatal=False)
+                    if not playlist:
+                        continue
+                    start_video = playlist.get('startvideo', 0)
+                    playlist = playlist.get('playlist')
+                    if not playlist or not isinstance(playlist, list):
+                        continue
+                    playlist = playlist[start_video]
+                    title = playlist.get('title')
+                    if not title:
+                        continue
                     description = playlist.get('description')
                     for source in playlist.get('sources', []):
                         file_ = source.get('file')
-                        if file_ and determine_ext(file_) == 'm3u8':
-                            formats = self._extract_m3u8_formats(
+                        if not file_:
+                            continue
+                        ext = determine_ext(file_)
+                        format_id_list = [lang, kind]
+                        if ext == 'm3u8':
+                            format_id_list.append('hls')
+                        elif source.get('type') == 'video/dash' or ext == 'mpd':
+                            format_id_list.append('dash')
+                        format_id = '-'.join(filter(None, format_id_list))
+                        if ext == 'm3u8':
+                            file_formats = self._extract_m3u8_formats(
                                 file_, video_id, 'mp4',
-                                entry_protocol='m3u8_native', m3u8_id='hls')
+                                entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)
+                        elif source.get('type') == 'video/dash' or ext == 'mpd':
+                            continue
+                            file_formats = self._extract_mpd_formats(
+                                file_, video_id, mpd_id=format_id, fatal=False)
+                        else:
+                            continue
+                        for f in file_formats:
+                            f.update({
+                                'language': lang,
+                                'format_note': format_note,
+                            })
+                        formats.extend(file_formats)
 
             if formats:
+                self._sort_formats(formats)
                 f = common_info.copy()
                 f.update({
                     'title': title,
@@ -145,16 +225,18 @@ class AnimeOnDemandIE(InfoExtractor):
                 })
                 entries.append(f)
 
-            m = re.search(
-                r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
-                episode_html)
-            if m:
-                f = common_info.copy()
-                f.update({
-                    'id': '%s-teaser' % f['id'],
-                    'title': m.group('title'),
-                    'url': compat_urlparse.urljoin(url, m.group('href')),
-                })
-                entries.append(f)
+            # Extract teaser only when full episode is not available
+            if not formats:
+                m = re.search(
+                    r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
+                    episode_html)
+                if m:
+                    f = common_info.copy()
+                    f.update({
+                        'id': '%s-teaser' % f['id'],
+                        'title': m.group('title'),
+                        'url': compat_urlparse.urljoin(url, m.group('href')),
+                    })
+                    entries.append(f)
 
         return self.playlist_result(entries, anime_id, anime_title, anime_description)

youtube_dl/extractor/aol.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 class AolIE(InfoExtractor):
     IE_NAME = 'on.aol.com'
-    _VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
+    _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
 
     _TESTS = [{
         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
@@ -25,7 +25,7 @@ class AolIE(InfoExtractor):
 
 class AolFeaturesIE(InfoExtractor):
     IE_NAME = 'features.aol.com'
-    _VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
 
     _TESTS = [{
         'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',

youtube_dl/extractor/arte.py

@@ -23,7 +23,7 @@ from ..utils import (
 
 
 class ArteTvIE(InfoExtractor):
-    _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
+    _VALID_URL = r'https?://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
     IE_NAME = 'arte.tv'
 
     def _real_extract(self, url):
@@ -121,15 +121,18 @@ class ArteTVPlus7IE(InfoExtractor):
                 json_url = compat_parse_qs(
                     compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
         if json_url:
-            return self._extract_from_json_url(json_url, video_id, lang)
-        # Differend kind of embed URL (e.g.
+            title = self._search_regex(
+                r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
+                webpage, 'title', default=None, group='title')
+            return self._extract_from_json_url(json_url, video_id, lang, title=title)
+        # Different kind of embed URL (e.g.
         # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
         embed_url = self._search_regex(
             r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1',
             webpage, 'embed url', group='url')
         return self.url_result(embed_url)
 
-    def _extract_from_json_url(self, json_url, video_id, lang):
+    def _extract_from_json_url(self, json_url, video_id, lang, title=None):
         info = self._download_json(json_url, video_id)
         player_info = info['videoJsonPlayer']
 
@@ -137,7 +140,7 @@ class ArteTVPlus7IE(InfoExtractor):
         if not upload_date_str:
             upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
 
-        title = player_info['VTI'].strip()
+        title = (player_info.get('VTI') or title or player_info['VID']).strip()
         subtitle = player_info.get('VSU', '').strip()
         if subtitle:
             title += ' - %s' % subtitle

youtube_dl/extractor/atresplayer.py

@@ -6,16 +6,14 @@ import hashlib
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_urllib_parse,
-)
+from ..compat import compat_str
 from ..utils import (
-    int_or_none,
-    float_or_none,
-    sanitized_Request,
-    xpath_text,
     ExtractorError,
+    float_or_none,
+    int_or_none,
+    sanitized_Request,
+    urlencode_postdata,
+    xpath_text,
 )
 
 
@@ -86,7 +84,7 @@ class AtresPlayerIE(InfoExtractor):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+            self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)

youtube_dl/extractor/audioboom.py

@@ -0,0 +1,66 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class AudioBoomIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
+        'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
+        'info_dict': {
+            'id': '4279833',
+            'ext': 'mp3',
+            'title': '3/09/2016 Czaban Hour 3',
+            'description': 'Guest:   Nate Davis - NFL free agency,   Guest:   Stan Gans',
+            'duration': 2245.72,
+            'uploader': 'Steve Czaban',
+            'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        clip = None
+
+        clip_store = self._parse_json(
+            self._search_regex(
+                r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
+                webpage, 'clip store', default='{}', group='json'),
+            video_id, fatal=False)
+        if clip_store:
+            clips = clip_store.get('clips')
+            if clips and isinstance(clips, list) and isinstance(clips[0], dict):
+                clip = clips[0]
+
+        def from_clip(field):
+            if clip:
+                clip.get(field)
+
+        audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
+            'audio', webpage, 'audio url')
+        title = from_clip('title') or self._og_search_title(webpage)
+        description = from_clip('description') or self._og_search_description(webpage)
+
+        duration = float_or_none(from_clip('duration') or self._html_search_meta(
+            'weibo:audio:duration', webpage))
+
+        uploader = from_clip('author') or self._og_search_property(
+            'audio:artist', webpage, 'uploader', fatal=False)
+        uploader_url = from_clip('author_url') or self._html_search_meta(
+            'audioboo:channel', webpage, 'uploader url')
+
+        return {
+            'id': video_id,
+            'url': audio_url,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_url': uploader_url,
+        }

youtube_dl/extractor/azubu.py

@@ -98,7 +98,7 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
 
     _TEST = {
         'url': 'http://www.azubu.tv/MarsTVMDLen',

youtube_dl/extractor/baidu.py

@@ -9,7 +9,7 @@ from ..utils import unescapeHTML
 
 class BaiduVideoIE(InfoExtractor):
     IE_DESC = '百度视频'
-    _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
+    _VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
     _TESTS = [{
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
         'info_dict': {

youtube_dl/extractor/bambuser.py

@@ -4,15 +4,13 @@ import re
 import itertools
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_str,
-)
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
-    int_or_none,
     float_or_none,
+    int_or_none,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
@@ -58,7 +56,7 @@ class BambuserIE(InfoExtractor):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+            self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Referer', self._LOGIN_URL)
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)

youtube_dl/extractor/bbc.py

@@ -10,7 +10,6 @@ from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
-    remove_end,
     unescapeHTML,
 )
 from ..compat import (
@@ -561,7 +560,7 @@ class BBCIE(BBCCoUkIE):
         'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
         'info_dict': {
             'id': '3662a707-0af9-3149-963f-47bea720b460',
-            'title': 'BBC Blogs - Adam Curtis - BUGGER',
+            'title': 'BUGGER',
         },
         'playlist_count': 18,
     }, {
@@ -670,9 +669,17 @@ class BBCIE(BBCCoUkIE):
         'url': 'http://www.bbc.com/sport/0/football/34475836',
         'info_dict': {
             'id': '34475836',
-            'title': 'What Liverpool can expect from Klopp',
+            'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
         },
         'playlist_count': 3,
+    }, {
+        # school report article with single video
+        'url': 'http://www.bbc.co.uk/schoolreport/35744779',
+        'info_dict': {
+            'id': '35744779',
+            'title': 'School which breaks down barriers in Jerusalem',
+        },
+        'playlist_count': 1,
     }, {
         # single video with playlist URL from weather section
         'url': 'http://www.bbc.com/weather/features/33601775',
@@ -735,8 +742,17 @@ class BBCIE(BBCCoUkIE):
 
         json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
         timestamp = json_ld_info.get('timestamp')
+
         playlist_title = json_ld_info.get('title')
-        playlist_description = json_ld_info.get('description')
+        if not playlist_title:
+            playlist_title = self._og_search_title(
+                webpage, default=None) or self._html_search_regex(
+                r'<title>(.+?)</title>', webpage, 'playlist title', default=None)
+            if playlist_title:
+                playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
+
+        playlist_description = json_ld_info.get(
+            'description') or self._og_search_description(webpage, default=None)
 
         if not timestamp:
             timestamp = parse_iso8601(self._search_regex(
@@ -797,8 +813,6 @@ class BBCIE(BBCCoUkIE):
                                 playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
 
         if entries:
-            playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News')
-            playlist_description = playlist_description or self._og_search_description(webpage, default=None)
             return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
@@ -829,10 +843,6 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
-        playlist_title = self._html_search_regex(
-            r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
-        playlist_description = self._og_search_description(webpage, default=None)
-
         def extract_all(pattern):
             return list(filter(None, map(
                 lambda s: self._parse_json(s, playlist_id, fatal=False),
@@ -932,7 +942,7 @@ class BBCIE(BBCCoUkIE):
 
 
 class BBCCoUkArticleIE(InfoExtractor):
-    _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'
 

youtube_dl/extractor/behindkink.py

@@ -8,7 +8,7 @@ from ..utils import url_basename
 
 
 class BehindKinkIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
+    _VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
     _TEST = {
         'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
         'md5': '507b57d8fdcd75a41a9a7bdb7989c762',

youtube_dl/extractor/bilibili.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
+    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',

youtube_dl/extractor/biobiochiletv.py

@@ -0,0 +1,86 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import remove_end
+
+
+class BioBioChileTVIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
+
+    _TESTS = [{
+        'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
+        'md5': '26f51f03cf580265defefb4518faec09',
+        'info_dict': {
+            'id': 'sobre-camaras-y-camarillas-parlamentarias',
+            'ext': 'mp4',
+            'title': 'Sobre Cámaras y camarillas parlamentarias',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Fernando Atria',
+        },
+    }, {
+        # different uploader layout
+        'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
+        'md5': 'edc2e6b58974c46d5b047dea3c539ff3',
+        'info_dict': {
+            'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
+            'ext': 'mp4',
+            'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Piangella Obrador',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.biobiochile.cl/notas/2015/10/21/exclusivo-hector-pinto-formador-de-chupete-revela-version-del-ex-delantero-albo.shtml',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
+
+        file_url = self._search_regex(
+            r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1',
+            webpage, 'file url', group='url')
+
+        base_url = self._search_regex(
+            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage,
+            'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/',
+            group='url')
+
+        formats = self._extract_m3u8_formats(
+            '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+        f = {
+            'url': '%s%s' % (base_url, file_url),
+            'format_id': 'http',
+            'protocol': 'http',
+            'preference': 1,
+        }
+        if formats:
+            f_copy = formats[-1].copy()
+            f_copy.update(f)
+            f = f_copy
+        formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        uploader = self._html_search_regex(
+            r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>',
+            webpage, 'uploader', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'formats': formats,
+        }

youtube_dl/extractor/bokecc.py

@@ -33,7 +33,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 class BokeCCIE(BokeCCBaseIE):
     _IE_DESC = 'CC视频'
-    _VALID_URL = r'http://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
+    _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{
         'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',

youtube_dl/extractor/bpb.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class BpbIE(InfoExtractor):
     IE_DESC = 'Bundeszentrale für politische Bildung'
-    _VALID_URL = r'http://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
 
     _TEST = {
         'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',

youtube_dl/extractor/bravotv.py

@@ -0,0 +1,28 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class BravoTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+videos/(?P<id>[^/?]+)'
+    _TEST = {
+        'url': 'http://www.bravotv.com/last-chance-kitchen/season-5/videos/lck-ep-12-fishy-finale',
+        'md5': 'd60cdf68904e854fac669bd26cccf801',
+        'info_dict': {
+            'id': 'LitrBdX64qLn',
+            'ext': 'mp4',
+            'title': 'Last Chance Kitchen Returns',
+            'description': 'S13: Last Chance Kitchen Returns for Top Chef Season 13',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        account_pid = self._search_regex(r'"account_pid"\s*:\s*"([^"]+)"', webpage, 'account pid')
+        release_pid = self._search_regex(r'"release_pid"\s*:\s*"([^"]+)"', webpage, 'release pid')
+        return self.url_result(smuggle_url(
+            'http://link.theplatform.com/s/%s/%s?mbr=true&switch=progressive' % (account_pid, release_pid),
+            {'force_smil_url': True}), 'ThePlatform', release_pid)

youtube_dl/extractor/breakcom.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
         'info_dict': {

youtube_dl/extractor/brightcove.py

@@ -9,10 +9,10 @@ from ..compat import (
     compat_etree_fromstring,
     compat_parse_qs,
     compat_str,
-    compat_urllib_parse,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_xml_parse_error,
+    compat_HTTPError,
 )
 from ..utils import (
     determine_ext,
@@ -23,16 +23,16 @@ from ..utils import (
     js_to_json,
     int_or_none,
     parse_iso8601,
-    sanitized_Request,
     unescapeHTML,
     unsmuggle_url,
+    update_url_query,
 )
 
 
 class BrightcoveLegacyIE(InfoExtractor):
     IE_NAME = 'brightcove:legacy'
     _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
-    _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
+    _FEDERATED_URL = 'http://c.brightcove.com/services/viewer/htmlFederated'
 
     _TESTS = [
         {
@@ -155,8 +155,8 @@ class BrightcoveLegacyIE(InfoExtractor):
         # Not all pages define this value
         if playerKey is not None:
             params['playerKey'] = playerKey
-        # The three fields hold the id of the video
-        videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID')
+        # These fields hold the id of the video
+        videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList')
         if videoPlayer is not None:
             params['@videoPlayer'] = videoPlayer
         linkBase = find_param('linkBaseURL')
@@ -184,8 +184,7 @@ class BrightcoveLegacyIE(InfoExtractor):
 
     @classmethod
     def _make_brightcove_url(cls, params):
-        data = compat_urllib_parse.urlencode(params)
-        return cls._FEDERATED_URL_TEMPLATE % data
+        return update_url_query(cls._FEDERATED_URL, params)
 
     @classmethod
     def _extract_brightcove_url(cls, webpage):
@@ -239,7 +238,7 @@ class BrightcoveLegacyIE(InfoExtractor):
             # We set the original url as the default 'Referer' header
             referer = smuggled_data.get('Referer', url)
             return self._get_video_info(
-                videoPlayer[0], query_str, query, referer=referer)
+                videoPlayer[0], query, referer=referer)
         elif 'playerKey' in query:
             player_key = query['playerKey']
             return self._get_playlist_info(player_key[0])
@@ -248,15 +247,14 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?',
                 expected=True)
 
-    def _get_video_info(self, video_id, query_str, query, referer=None):
-        request_url = self._FEDERATED_URL_TEMPLATE % query_str
-        req = sanitized_Request(request_url)
+    def _get_video_info(self, video_id, query, referer=None):
+        headers = {}
         linkBase = query.get('linkBaseURL')
         if linkBase is not None:
             referer = linkBase[0]
         if referer is not None:
-            req.add_header('Referer', referer)
-        webpage = self._download_webpage(req, video_id)
+            headers['Referer'] = referer
+        webpage = self._download_webpage(self._FEDERATED_URL, video_id, headers=headers, query=query)
 
         error_msg = self._html_search_regex(
             r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage,
@@ -355,7 +353,7 @@ class BrightcoveLegacyIE(InfoExtractor):
 
 class BrightcoveNewIE(InfoExtractor):
     IE_NAME = 'brightcove:new'
-    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)'
+    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)'
     _TESTS = [{
         'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
         'md5': 'c8100925723840d4b0d243f7025703be',
@@ -391,6 +389,10 @@ class BrightcoveNewIE(InfoExtractor):
         # ref: prefixed video id
         'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442',
         'only_matching': True,
+    }, {
+        # non numeric ref: prefixed video id
+        'url': 'http://players.brightcove.net/710858724001/default_default/index.html?videoId=ref:event-stream-356',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -410,8 +412,8 @@ class BrightcoveNewIE(InfoExtractor):
 
         # Look for iframe embeds [1]
         for _, url in re.findall(
-                r'<iframe[^>]+src=(["\'])((?:https?:)//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
-            entries.append(url)
+                r'<iframe[^>]+src=(["\'])((?:https?:)?//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
+            entries.append(url if url.startswith('http') else 'http:' + url)
 
         # Look for embed_in_page embeds [2]
         for video_id, account_id, player_id, embed in re.findall(
@@ -420,11 +422,11 @@ class BrightcoveNewIE(InfoExtractor):
                 # According to [4] data-video-id may be prefixed with ref:
                 r'''(?sx)
                     <video[^>]+
-                        data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*?
+                        data-video-id=["\'](\d+|ref:[^"\']+)["\'][^>]*>.*?
                     </video>.*?
                     <script[^>]+
                         src=["\'](?:https?:)?//players\.brightcove\.net/
-                        (\d+)/([\da-f-]+)_([^/]+)/index\.min\.js
+                        (\d+)/([\da-f-]+)_([^/]+)/index(?:\.min)?\.js
                 ''', webpage):
             entries.append(
                 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
@@ -454,24 +456,33 @@ class BrightcoveNewIE(InfoExtractor):
                 r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
                 webpage, 'policy key', group='pk')
 
-        req = sanitized_Request(
-            'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s'
-            % (account_id, video_id),
-            headers={'Accept': 'application/json;pk=%s' % policy_key})
-        json_data = self._download_json(req, video_id)
+        api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
+        try:
+            json_data = self._download_json(api_url, video_id, headers={
+                'Accept': 'application/json;pk=%s' % policy_key
+            })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                json_data = self._parse_json(e.cause.read().decode(), video_id)
+                raise ExtractorError(json_data[0]['message'], expected=True)
+            raise
 
         title = json_data['name']
 
         formats = []
         for source in json_data.get('sources', []):
+            container = source.get('container')
             source_type = source.get('type')
             src = source.get('src')
-            if source_type == 'application/x-mpegURL':
+            if source_type == 'application/x-mpegURL' or container == 'M2TS':
                 if not src:
                     continue
                 formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
+                    src, video_id, 'mp4', m3u8_id='hls', fatal=False))
+            elif source_type == 'application/dash+xml':
+                if not src:
+                    continue
+                formats.extend(self._extract_mpd_formats(src, video_id, 'dash', fatal=False))
             else:
                 streaming_src = source.get('streaming_src')
                 stream_name, app_name = source.get('stream_name'), source.get('app_name')
@@ -479,15 +490,23 @@ class BrightcoveNewIE(InfoExtractor):
                     continue
                 tbr = float_or_none(source.get('avg_bitrate'), 1000)
                 height = int_or_none(source.get('height'))
+                width = int_or_none(source.get('width'))
                 f = {
                     'tbr': tbr,
-                    'width': int_or_none(source.get('width')),
-                    'height': height,
                     'filesize': int_or_none(source.get('size')),
-                    'container': source.get('container'),
-                    'vcodec': source.get('codec'),
-                    'ext': source.get('container').lower(),
+                    'container': container,
+                    'ext': container.lower(),
                 }
+                if width == 0 and height == 0:
+                    f.update({
+                        'vcodec': 'none',
+                    })
+                else:
+                    f.update({
+                        'width': width,
+                        'height': height,
+                        'vcodec': source.get('codec'),
+                    })
 
                 def build_format_id(kind):
                     format_id = kind

youtube_dl/extractor/camdemy.py

@@ -6,7 +6,7 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class CamdemyIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
     _TESTS = [{
         # single file
         'url': 'http://www.camdemy.com/media/5181/',
@@ -104,7 +104,7 @@ class CamdemyIE(InfoExtractor):
 
 
 class CamdemyFolderIE(InfoExtractor):
-    _VALID_URL = r'http://www.camdemy.com/folder/(?P<id>\d+)'
+    _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
     _TESTS = [{
         # links with trailing slash
         'url': 'http://www.camdemy.com/folder/450',
@@ -139,7 +139,7 @@ class CamdemyFolderIE(InfoExtractor):
         parsed_url = list(compat_urlparse.urlparse(url))
         query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
         query.update({'displayMode': 'list'})
-        parsed_url[4] = compat_urllib_parse.urlencode(query)
+        parsed_url[4] = compat_urllib_parse_urlencode(query)
         final_url = compat_urlparse.urlunparse(parsed_url)
 
         page = self._download_webpage(final_url, folder_id)

youtube_dl/extractor/cbsnews.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 class CBSNewsIE(ThePlatformIE):
     IE_DESC = 'CBS News'
-    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
     _TESTS = [
         {
@@ -78,7 +78,7 @@ class CBSNewsIE(ThePlatformIE):
             pid = item.get('media' + format_id)
             if not pid:
                 continue
-            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid
+            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid
             tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
             formats.extend(tp_formats)
             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
@@ -96,7 +96,7 @@ class CBSNewsIE(ThePlatformIE):
 
 class CBSNewsLiveVideoIE(InfoExtractor):
     IE_DESC = 'CBS News Live Videos'
-    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
 
     _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',

youtube_dl/extractor/cbssports.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class CBSSportsIE(InfoExtractor):
-    _VALID_URL = r'http://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
 
     _TEST = {
         'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',

youtube_dl/extractor/cda.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    decode_packed_codes,
+    ExtractorError,
+    parse_duration
+)
+
+
+class CDAIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+    _TESTS = [{
+        'url': 'http://www.cda.pl/video/5749950c',
+        'md5': '6f844bf51b15f31fae165365707ae970',
+        'info_dict': {
+            'id': '5749950c',
+            'ext': 'mp4',
+            'height': 720,
+            'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
+            'duration': 39
+        }
+    }, {
+        'url': 'http://www.cda.pl/video/57413289',
+        'md5': 'a88828770a8310fc00be6c95faf7f4d5',
+        'info_dict': {
+            'id': '57413289',
+            'ext': 'mp4',
+            'title': 'Lądowanie na lotnisku na Maderze',
+            'duration': 137
+        }
+    }, {
+        'url': 'http://ebd.cda.pl/0x0/5749950c',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
+
+        if 'Ten film jest dostępny dla użytkowników premium' in webpage:
+            raise ExtractorError('This video is only available for premium users.', expected=True)
+
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
+
+        formats = []
+
+        info_dict = {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'duration': None,
+        }
+
+        def extract_format(page, version):
+            unpacked = decode_packed_codes(page)
+            format_url = self._search_regex(
+                r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False)
+            if not format_url:
+                return
+            f = {
+                'url': format_url,
+            }
+            m = re.search(
+                r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
+                page)
+            if m:
+                f.update({
+                    'format_id': m.group('format_id'),
+                    'height': int(m.group('height')),
+                })
+            info_dict['formats'].append(f)
+            if not info_dict['duration']:
+                info_dict['duration'] = parse_duration(self._search_regex(
+                    r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False))
+
+        extract_format(webpage, 'default')
+
+        for href, resolution in re.findall(
+                r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
+                webpage):
+            webpage = self._download_webpage(
+                href, video_id, 'Downloading %s version information' % resolution, fatal=False)
+            if not webpage:
+                # Manually report warning because empty page is returned when
+                # invalid version is requested.
+                self.report_warning('Unable to download %s version information' % resolution)
+                continue
+            extract_format(webpage, resolution)
+
+        self._sort_formats(formats)
+
+        return info_dict

youtube_dl/extractor/ceskatelevize.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
@@ -13,6 +12,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
@@ -102,7 +102,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         req = sanitized_Request(
             'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
-            data=compat_urllib_parse.urlencode(data))
+            data=urlencode_postdata(data))
 
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         req.add_header('x-addr', '127.0.0.1')
@@ -129,7 +129,8 @@ class CeskaTelevizeIE(InfoExtractor):
             formats = []
             for format_id, stream_url in item['streamUrls'].items():
                 formats.extend(self._extract_m3u8_formats(
-                    stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
+                    stream_url, playlist_id, 'mp4',
+                    entry_protocol='m3u8_native', fatal=False))
             self._sort_formats(formats)
 
             item_id = item.get('id') or item['assetId']

youtube_dl/extractor/cliphunter.py

@@ -19,7 +19,7 @@ def _decode(s):
 class CliphunterIE(InfoExtractor):
     IE_NAME = 'cliphunter'
 
-    _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
         (?P<id>[0-9]+)/
         (?P<seo>.+?)(?:$|[#\?])
     '''

youtube_dl/extractor/clipsyndicate.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class ClipsyndicateIE(InfoExtractor):
-    _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',

youtube_dl/extractor/cloudy.py

@@ -6,7 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_HTTPError,
 )
 from ..utils import (
@@ -64,7 +64,7 @@ class CloudyIE(InfoExtractor):
                 'errorUrl': error_url,
             })
 
-        data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
+        data_url = self._API_URL % (video_host, compat_urllib_parse_urlencode(form))
         player_data = self._download_webpage(
             data_url, video_id, 'Downloading player data')
         data = compat_parse_qs(player_data)

youtube_dl/extractor/clubic.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class ClubicIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
 
     _TESTS = [{
         'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',

youtube_dl/extractor/cnet.py

@@ -60,7 +60,7 @@ class CNETIE(ThePlatformIE):
         for (fkey, vid) in vdata['files'].items():
             if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
                 continue
-            release_url = 'http://link.theplatform.com/s/kYEXFC/%s?format=SMIL&mbr=true' % vid
+            release_url = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true' % vid
             if fkey == 'hds':
                 release_url += '&manifest=f4m'
             tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)

youtube_dl/extractor/comcarcoff.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class ComCarCoffIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
+    _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
     _TESTS = [{
         'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
         'info_dict': {

youtube_dl/extractor/comedycentral.py

@@ -5,7 +5,7 @@ import re
 from .mtv import MTVServicesInfoExtractor
 from ..compat import (
     compat_str,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     ExtractorError,
@@ -201,7 +201,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
         # Correct cc.com in uri
         uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
 
-        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
+        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri}))
         idoc = self._download_xml(
             index_url, epTitle,
             'Downloading show index', 'Unable to download episode index')

youtube_dl/extractor/common.py

@@ -21,7 +21,7 @@ from ..compat import (
     compat_os_name,
     compat_str,
     compat_urllib_error,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -48,6 +48,7 @@ from ..utils import (
     determine_protocol,
     parse_duration,
     mimetype2ext,
+    update_url_query,
 )
 
 
@@ -105,7 +106,7 @@ class InfoExtractor(object):
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
-                                 "m3u8", or "m3u8_native".
+                                 "m3u8", "m3u8_native" or "http_dash_segments".
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
@@ -345,7 +346,7 @@ class InfoExtractor(object):
     def IE_NAME(self):
         return compat_str(type(self).__name__[:-2])
 
-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None):
         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)
@@ -354,6 +355,12 @@ class InfoExtractor(object):
                 self.to_screen('%s' % (note,))
             else:
                 self.to_screen('%s: %s' % (video_id, note))
+        # data, headers and query params will be ignored for `Request` objects
+        if isinstance(url_or_request, compat_str):
+            if query:
+                url_or_request = update_url_query(url_or_request, query)
+            if data or headers:
+                url_or_request = sanitized_Request(url_or_request, data, headers or {})
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
@@ -369,13 +376,13 @@ class InfoExtractor(object):
                 self._downloader.report_warning(errmsg)
                 return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None):
         """ Returns a tuple (page content as string, URL handle) """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
-        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
+        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)
         if urlh is False:
             assert not fatal
             return False
@@ -462,13 +469,13 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None):
         """ Returns the data of the page as a string """
         success = False
         try_count = 0
         while success is False:
             try:
-                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query)
                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1
@@ -483,10 +490,10 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',
-                      transform_source=None, fatal=True, encoding=None):
+                      transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
+            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query)
         if xml_string is False:
             return xml_string
         if transform_source:
@@ -497,10 +504,10 @@ class InfoExtractor(object):
                        note='Downloading JSON metadata',
                        errnote='Unable to download JSON metadata',
                        transform_source=None,
-                       fatal=True, encoding=None):
+                       fatal=True, encoding=None, data=None, headers=None, query=None):
         json_string = self._download_webpage(
             url_or_request, video_id, note, errnote, fatal=fatal,
-            encoding=encoding)
+            encoding=encoding, data=data, headers=headers, query=query)
         if (not fatal) and json_string is False:
             return None
         return self._parse_json(
@@ -855,6 +862,7 @@ class InfoExtractor(object):
             proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
 
             if f.get('vcodec') == 'none':  # audio only
+                preference -= 50
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
@@ -865,6 +873,8 @@ class InfoExtractor(object):
                 except ValueError:
                     audio_ext_preference = -1
             else:
+                if f.get('acodec') == 'none':  # video only
+                    preference -= 40
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['flv', 'mp4', 'webm']
                 else:
@@ -966,6 +976,13 @@ class InfoExtractor(object):
         if manifest is False:
             return []
 
+        return self._parse_f4m_formats(
+            manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+            transform_source=transform_source, fatal=fatal)
+
+    def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None,
+                           transform_source=lambda s: fix_xml_ampersands(s).strip(),
+                           fatal=True):
         formats = []
         manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
@@ -991,7 +1008,8 @@ class InfoExtractor(object):
                 # bitrate in f4m downloader
                 if determine_ext(manifest_url) == 'f4m':
                     formats.extend(self._extract_f4m_formats(
-                        manifest_url, video_id, preference, f4m_id, fatal=fatal))
+                        manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+                        transform_source=transform_source, fatal=fatal))
                     continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
@@ -1140,8 +1158,8 @@ class InfoExtractor(object):
                 out.append('{%s}%s' % (namespace, c))
         return '/'.join(out)
 
-    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None):
-        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None, transform_source=None):
+        smil = self._download_smil(smil_url, video_id, fatal=fatal, transform_source=transform_source)
 
         if smil is False:
             assert not fatal
@@ -1158,10 +1176,10 @@ class InfoExtractor(object):
             return {}
         return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
 
-    def _download_smil(self, smil_url, video_id, fatal=True):
+    def _download_smil(self, smil_url, video_id, fatal=True, transform_source=None):
         return self._download_xml(
             smil_url, video_id, 'Downloading SMIL file',
-            'Unable to download SMIL file', fatal=fatal)
+            'Unable to download SMIL file', fatal=fatal, transform_source=transform_source)
 
     def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
         namespace = self._parse_smil_namespace(smil)
@@ -1282,7 +1300,7 @@ class InfoExtractor(object):
                         'plugin': 'flowplayer-3.2.0.1',
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'
-                f4m_url += compat_urllib_parse.urlencode(f4m_params)
+                f4m_url += compat_urllib_parse_urlencode(f4m_params)
                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
                 continue
 
@@ -1447,8 +1465,9 @@ class InfoExtractor(object):
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
-                    mime_type = representation_attrib.get('mimeType')
-                    content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType')
+                    # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory
+                    mime_type = representation_attrib['mimeType']
+                    content_type = mime_type.split('/')[0]
                     if content_type == 'text':
                         # TODO implement WebVTT downloading
                         pass
@@ -1471,6 +1490,7 @@ class InfoExtractor(object):
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
+                            'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
                             'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),

youtube_dl/extractor/commonprotocols.py

@@ -0,0 +1,36 @@
+from __future__ import unicode_literals
+
+import os
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_urlparse,
+)
+from ..utils import url_basename
+
+
+class RtmpIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)rtmp[est]?://.+'
+
+    _TESTS = [{
+        'url': 'rtmp://cp44293.edgefcs.net/ondemand?auth=daEcTdydfdqcsb8cZcDbAaCbhamacbbawaS-bw7dBb-bWG-GqpGFqCpNCnGoyL&aifp=v001&slist=public/unsecure/audio/2c97899446428e4301471a8cb72b4b97--audio--pmg-20110908-0900a_flv_aac_med_int.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'rtmp://edge.live.hitbox.tv/live/dimak',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+        title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': [{
+                'url': url,
+                'ext': 'flv',
+                'format_id': compat_urlparse.urlparse(url).scheme,
+            }],
+        }

youtube_dl/extractor/condenast.py

@@ -5,7 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
     compat_urlparse,
 )
@@ -45,7 +45,7 @@ class CondeNastIE(InfoExtractor):
         'wmagazine': 'W Magazine',
     }
 
-    _VALID_URL = r'http://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
+    _VALID_URL = r'https?://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
     EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed(?:js)?)/.+?' % '|'.join(_SITES.keys())
@@ -97,7 +97,7 @@ class CondeNastIE(InfoExtractor):
         video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
         player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
         target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
-        data = compat_urllib_parse.urlencode({'videoId': video_id,
+        data = compat_urllib_parse_urlencode({'videoId': video_id,
                                               'playerId': player_id,
                                               'target': target,
                                               })

youtube_dl/extractor/crunchyroll.py

@@ -11,8 +11,8 @@ from math import pow, sqrt, floor
 from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
-    compat_urllib_parse,
     compat_urllib_parse_unquote,
+    compat_urllib_parse_urlencode,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -54,7 +54,7 @@ class CrunchyrollBaseIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
+    def _download_webpage(self, url_or_request, *args, **kwargs):
         request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
                    else sanitized_Request(url_or_request))
         # Accept-Language must be set explicitly to accept any language to avoid issues
@@ -65,8 +65,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         # Crunchyroll to not work in georestriction cases in some browsers that don't place
         # the locale lang first in header. However allowing any language seems to workaround the issue.
         request.add_header('Accept-Language', '*')
-        return super(CrunchyrollBaseIE, self)._download_webpage(
-            request, video_id, note, errnote, fatal, tries, timeout, encoding)
+        return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
 
     @staticmethod
     def _add_skip_wall(url):
@@ -79,7 +78,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         # See https://github.com/rg3/youtube-dl/issues/7202.
         qs['skip_wall'] = ['1']
         return compat_urlparse.urlunparse(
-            parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
+            parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
 
 
 class CrunchyrollIE(CrunchyrollBaseIE):
@@ -309,7 +308,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
         playerdata_req = sanitized_Request(playerdata_url)
-        playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
+        playerdata_req.data = urlencode_postdata({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
         playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
 
@@ -323,7 +322,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             streamdata_req = sanitized_Request(
                 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
                 % (stream_id, stream_format, stream_quality),
-                compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
+                compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata = self._download_xml(
                 streamdata_req, video_id,

youtube_dl/extractor/cspan.py

@@ -15,7 +15,7 @@ from .senateisvp import SenateISVPIE
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
     IE_DESC = 'C-SPAN'
     _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',

youtube_dl/extractor/ctsnews.py

@@ -8,7 +8,7 @@ from ..utils import parse_iso8601, ExtractorError
 class CtsNewsIE(InfoExtractor):
     IE_DESC = '華視新聞'
     # https connection failed (Connection reset)
-    _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{
         'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
         'md5': 'a9875cb790252b08431186d741beaabe',

youtube_dl/extractor/daum.py

@@ -8,8 +8,8 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
-    compat_urllib_parse,
     compat_urllib_parse_unquote,
+    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -70,7 +70,7 @@ class DaumIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = compat_urllib_parse_unquote(self._match_id(url))
-        query = compat_urllib_parse.urlencode({'vid': video_id})
+        query = compat_urllib_parse_urlencode({'vid': video_id})
         movie_data = self._download_json(
             'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
             video_id, 'Downloading video formats info')
@@ -86,7 +86,7 @@ class DaumIE(InfoExtractor):
         formats = []
         for format_el in movie_data['output_list']['output_list']:
             profile = format_el['profile']
-            format_query = compat_urllib_parse.urlencode({
+            format_query = compat_urllib_parse_urlencode({
                 'vid': video_id,
                 'profile': profile,
             })

youtube_dl/extractor/dcn.py

@@ -6,7 +6,7 @@ import base64
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_str,
 )
 from ..utils import (
@@ -15,6 +15,7 @@ from ..utils import (
     sanitized_Request,
     smuggle_url,
     unsmuggle_url,
+    urlencode_postdata,
 )
 
 
@@ -106,7 +107,7 @@ class DCNVideoIE(DCNBaseIE):
 
         webpage = self._download_webpage(
             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
-            compat_urllib_parse.urlencode({
+            compat_urllib_parse_urlencode({
                 'id': video_data['id'],
                 'user_id': video_data['user_id'],
                 'signature': video_data['signature'],
@@ -133,7 +134,7 @@ class DCNLiveIE(DCNBaseIE):
 
         webpage = self._download_webpage(
             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
-            compat_urllib_parse.urlencode({
+            compat_urllib_parse_urlencode({
                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
                 'signature': channel_data['signature'],
@@ -174,7 +175,7 @@ class DCNSeasonIE(InfoExtractor):
         data['show_id'] = show_id
         request = sanitized_Request(
             'http://admin.mangomolo.com/analytics/index.php/plus/show',
-            compat_urllib_parse.urlencode(data),
+            urlencode_postdata(data),
             {
                 'Origin': 'http://www.dcndigital.ae',
                 'Content-Type': 'application/x-www-form-urlencoded'

youtube_dl/extractor/dctp.py

@@ -6,7 +6,7 @@ from ..compat import compat_str
 
 
 class DctpTvIE(InfoExtractor):
-    _VALID_URL = r'http://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+    _VALID_URL = r'https?://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
     _TEST = {
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
         'info_dict': {

youtube_dl/extractor/defense.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 class DefenseGouvFrIE(InfoExtractor):
     IE_NAME = 'defense.gouv.fr'
-    _VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
+    _VALID_URL = r'https?://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
 
     _TEST = {
         'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',

youtube_dl/extractor/discovery.py

@@ -9,7 +9,7 @@ from ..compat import compat_str
 
 
 class DiscoveryIE(InfoExtractor):
-    _VALID_URL = r'''(?x)http://(?:www\.)?(?:
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(?:
             discovery|
             investigationdiscovery|
             discoverylife|

youtube_dl/extractor/douyutv.py

@@ -10,7 +10,7 @@ from ..compat import (compat_str, compat_basestring)
 
 class DouyuTVIE(InfoExtractor):
     IE_DESC = '斗鱼'
-    _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'http://www.douyutv.com/iseven',
         'info_dict': {
@@ -60,6 +60,9 @@ class DouyuTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.douyu.com/xiaocang',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dplay.py

@@ -10,7 +10,7 @@ from ..utils import int_or_none
 
 
 class DPlayIE(InfoExtractor):
-    _VALID_URL = r'http://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
 
     _TESTS = [{
         'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',

youtube_dl/extractor/dramafever.py

@@ -6,7 +6,6 @@ import itertools
 from .amp import AMPIE
 from ..compat import (
     compat_HTTPError,
-    compat_urllib_parse,
     compat_urlparse,
 )
 from ..utils import (
@@ -14,6 +13,7 @@ from ..utils import (
     clean_html,
     int_or_none,
     sanitized_Request,
+    urlencode_postdata
 )
 
 
@@ -50,7 +50,7 @@ class DramaFeverBaseIE(AMPIE):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+            self._LOGIN_URL, urlencode_postdata(login_form))
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 

youtube_dl/extractor/dreisat.py

@@ -7,7 +7,7 @@ from .zdf import ZDFIE
 
 class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
-    _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TESTS = [
         {
             'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',

youtube_dl/extractor/dvtv.py

@@ -15,7 +15,7 @@ class DVTVIE(InfoExtractor):
     IE_NAME = 'dvtv'
     IE_DESC = 'http://video.aktualne.cz/'
 
-    _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
+    _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
 
     _TESTS = [{
         'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',

youtube_dl/extractor/dw.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+from ..compat import compat_urlparse
+
+
+class DWIE(InfoExtractor):
+    IE_NAME = 'dw'
+    _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
+    _TESTS = [{
+        # video
+        'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
+        'md5': '7372046e1815c5a534b43f3c3c36e6e9',
+        'info_dict': {
+            'id': '19112290',
+            'ext': 'mp4',
+            'title': 'Intelligent light',
+            'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
+            'upload_date': '20160311',
+        }
+    }, {
+        # audio
+        'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
+        'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
+        'info_dict': {
+            'id': '19111941',
+            'ext': 'mp3',
+            'title': 'WorldLink: My business',
+            'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
+            'upload_date': '20160311',
+        }
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id)
+        hidden_inputs = self._hidden_inputs(webpage)
+        title = hidden_inputs['media_title']
+
+        formats = []
+        if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
+            formats = self._extract_smil_formats(
+                'http://www.dw.com/smil/v-%s' % media_id, media_id,
+                transform_source=lambda s: s.replace(
+                    'rtmp://tv-od.dw.de/flash/',
+                    'http://tv-download.dw.de/dwtv_video/flv/'))
+        else:
+            formats = [{'url': hidden_inputs['file_name']}]
+
+        return {
+            'id': media_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': hidden_inputs.get('preview_image'),
+            'duration': int_or_none(hidden_inputs.get('file_duration')),
+            'upload_date': hidden_inputs.get('display_date'),
+            'formats': formats,
+        }
+
+
+class DWArticleIE(InfoExtractor):
+    IE_NAME = 'dw:article'
+    _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
+        'md5': '8ca657f9d068bbef74d6fc38b97fc869',
+        'info_dict': {
+            'id': '19105868',
+            'ext': 'mp4',
+            'title': 'The harsh life of refugees in Idomeni',
+            'description': 'md5:196015cc7e48ebf474db9399420043c7',
+            'upload_date': '20160310',
+        }
+    }
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        webpage = self._download_webpage(url, article_id)
+        hidden_inputs = self._hidden_inputs(webpage)
+        media_id = hidden_inputs['media_id']
+        media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
+        media_url = compat_urlparse.urljoin(url, media_path)
+        return self.url_result(media_url, 'DW', media_id)

youtube_dl/extractor/echomsk.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class EchoMskIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.echo.msk.ru/sounds/1464134.html',
         'md5': '2e44b3b78daff5b458e4dbc37f191f7c',

youtube_dl/extractor/eroprofile.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
     unescapeHTML
@@ -43,7 +43,7 @@ class EroProfileIE(InfoExtractor):
         if username is None:
             return
 
-        query = compat_urllib_parse.urlencode({
+        query = compat_urllib_parse_urlencode({
             'username': username,
             'password': password,
             'url': 'http://www.eroprofile.com/',

youtube_dl/extractor/exfm.py

@@ -8,7 +8,7 @@ from .common import InfoExtractor
 class ExfmIE(InfoExtractor):
     IE_NAME = 'exfm'
     IE_DESC = 'ex.fm'
-    _VALID_URL = r'http://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
     _SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
     _TESTS = [
         {

youtube_dl/extractor/facebook.py

@@ -37,7 +37,9 @@ class FacebookIE(InfoExtractor):
                                 video/embed|
                                 story\.php
                             )\?(?:.*?)(?:v|video_id|story_fbid)=|
-                            [^/]+/videos/(?:[^/]+/)?
+                            [^/]+/videos/(?:[^/]+/)?|
+                            [^/]+/posts/|
+                            groups/[^/]+/permalink/
                         )|
                     facebook:
                 )
@@ -50,6 +52,8 @@ class FacebookIE(InfoExtractor):
 
     _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
 
+    _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
+
     _TESTS = [{
         'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
         'md5': '6a40d33c0eccbb1af76cf0485a052659',
@@ -81,6 +85,33 @@ class FacebookIE(InfoExtractor):
             'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
             'uploader': 'Demy de Zeeuw',
         },
+    }, {
+        'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
+        'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
+        'info_dict': {
+            'id': '544765982287235',
+            'ext': 'mp4',
+            'title': '"What are you doing running in the snow?"',
+            'uploader': 'FailArmy',
+        }
+    }, {
+        'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903',
+        'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3',
+        'info_dict': {
+            'id': '1035862816472149',
+            'ext': 'mp4',
+            'title': 'What the Flock Is Going On In New Zealand  Credit: ViralHog',
+            'uploader': 'S. Saint',
+        },
+    }, {
+        'note': 'swf params escaped',
+        'url': 'https://www.facebook.com/barackobama/posts/10153664894881749',
+        'md5': '97ba073838964d12c70566e0085c2b91',
+        'info_dict': {
+            'id': '10153664894881749',
+            'ext': 'mp4',
+            'title': 'Facebook video #10153664894881749',
+        },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -94,7 +125,7 @@ class FacebookIE(InfoExtractor):
         'url': 'facebook:544765982287235',
         'only_matching': True,
     }, {
-        'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903',
+        'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/',
         'only_matching': True,
     }]
 
@@ -164,19 +195,19 @@ class FacebookIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
+    def _extract_from_url(self, url, video_id, fatal_if_no_video=True):
+        req = sanitized_Request(url)
         req.add_header('User-Agent', self._CHROME_USER_AGENT)
         webpage = self._download_webpage(req, video_id)
 
         video_data = None
 
-        BEFORE = '{swf.addParam(param[0], param[1]);});\n'
+        BEFORE = '{swf.addParam(param[0], param[1]);});'
         AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
-        m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
+        m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage)
         if m:
-            data = dict(json.loads(m.group(1)))
+            swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"')
+            data = dict(json.loads(swf_params))
             params_raw = compat_urllib_parse_unquote(data['params'])
             video_data = json.loads(params_raw)['video_data']
 
@@ -189,13 +220,15 @@ class FacebookIE(InfoExtractor):
 
         if not video_data:
             server_js_data = self._parse_json(self._search_regex(
-                r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id)
+                r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id)
             for item in server_js_data.get('instances', []):
                 if item[1][0] == 'VideoConfig':
                     video_data = video_data_list2dict(item[2][0]['videoData'])
                     break
 
         if not video_data:
+            if not fatal_if_no_video:
+                return webpage, False
             m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
             if m_msg is not None:
                 raise ExtractorError(
@@ -241,39 +274,36 @@ class FacebookIE(InfoExtractor):
             video_title = 'Facebook video #%s' % video_id
         uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
 
-        return {
+        info_dict = {
             'id': video_id,
             'title': video_title,
             'formats': formats,
             'uploader': uploader,
         }
 
-
-class FacebookPostIE(InfoExtractor):
-    IE_NAME = 'facebook:post'
-    _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)'
-    _TEST = {
-        'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
-        'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
-        'info_dict': {
-            'id': '544765982287235',
-            'ext': 'mp4',
-            'title': '"What are you doing running in the snow?"',
-            'uploader': 'FailArmy',
-        }
-    }
+        return webpage, info_dict
 
     def _real_extract(self, url):
-        post_id = self._match_id(url)
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, post_id)
+        real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url
+        webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False)
 
-        entries = [
-            self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
-            for video_id in self._parse_json(
-                self._search_regex(
-                    r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
-                    webpage, 'video ids', group='ids'),
-                post_id)]
+        if info_dict:
+            return info_dict
 
-        return self.playlist_result(entries, post_id)
+        if '/posts/' in url:
+            entries = [
+                self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
+                for vid in self._parse_json(
+                    self._search_regex(
+                        r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
+                        webpage, 'video ids', group='ids'),
+                    video_id)]
+
+            return self.playlist_result(entries, video_id)
+        else:
+            _, info_dict = self._extract_from_url(
+                self._VIDEO_PAGE_TEMPLATE % video_id,
+                video_id, fatal_if_no_video=True)
+            return info_dict

youtube_dl/extractor/fc2.py

@@ -5,19 +5,18 @@ import hashlib
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
 )
 from ..utils import (
-    encode_dict,
     ExtractorError,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
 class FC2IE(InfoExtractor):
-    _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
+    _VALID_URL = r'^https?://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
     IE_NAME = 'fc2'
     _NETRC_MACHINE = 'fc2'
     _TESTS = [{
@@ -57,7 +56,7 @@ class FC2IE(InfoExtractor):
             'Submit': ' Login ',
         }
 
-        login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
+        login_data = urlencode_postdata(login_form_strs)
         request = sanitized_Request(
             'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
 

youtube_dl/extractor/firstpost.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class FirstpostIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
 
     _TEST = {
         'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',

youtube_dl/extractor/firsttv.py

@@ -8,7 +8,7 @@ from ..utils import int_or_none
 class FirstTVIE(InfoExtractor):
     IE_NAME = '1tv'
     IE_DESC = 'Первый канал'
-    _VALID_URL = r'http://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
 
     _TESTS = [{
         'url': 'http://www.1tv.ru/videoarchive/73390',

youtube_dl/extractor/fivemin.py

@@ -4,8 +4,8 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
     compat_parse_qs,
+    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
     compat_urlparse,
 )
@@ -109,7 +109,7 @@ class FiveMinIE(InfoExtractor):
 
         response = self._download_json(
             'https://syn.5min.com/handlers/SenseHandler.ashx?' +
-            compat_urllib_parse.urlencode({
+            compat_urllib_parse_urlencode({
                 'func': 'GetResults',
                 'playlist': video_id,
                 'sid': sid,

youtube_dl/extractor/fktv.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class FKTVIE(InfoExtractor):
     IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
+    _VALID_URL = r'https?://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
 
     _TEST = {
         'url': 'http://fernsehkritik.tv/folge-1',

youtube_dl/extractor/flickr.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -42,7 +42,7 @@ class FlickrIE(InfoExtractor):
         }
         if secret:
             query['secret'] = secret
-        data = self._download_json(self._API_BASE_URL + compat_urllib_parse.urlencode(query), video_id, note)
+        data = self._download_json(self._API_BASE_URL + compat_urllib_parse_urlencode(query), video_id, note)
         if data['stat'] != 'ok':
             raise ExtractorError(data['message'])
         return data

youtube_dl/extractor/footyroom.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class FootyRoomIE(InfoExtractor):
-    _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://footyroom\.com/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
         'info_dict': {

youtube_dl/extractor/foxgay.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class FoxgayIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
+    _VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
     _TEST = {
         'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
         'md5': '80d72beab5d04e1655a56ad37afe6841',

youtube_dl/extractor/franceinter.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class FranceInterIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
         'md5': '4764932e466e6f6c79c317d2e74f6884',

youtube_dl/extractor/francetv.py

@@ -60,28 +60,31 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                     video_id, 'Downloading f4m manifest token', fatal=False)
                 if f4m_url:
                     formats.extend(self._extract_f4m_formats(
-                        f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id))
+                        f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
+                        video_id, f4m_id=format_id, fatal=False))
             elif ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id=format_id, fatal=False))
             elif video_url.startswith('rtmp'):
                 formats.append({
                     'url': video_url,
                     'format_id': 'rtmp-%s' % format_id,
                     'ext': 'flv',
-                    'preference': 1,
                 })
             else:
-                formats.append({
-                    'url': video_url,
-                    'format_id': format_id,
-                    'preference': -1,
-                })
+                if self._is_valid_url(video_url, video_id, format_id):
+                    formats.append({
+                        'url': video_url,
+                        'format_id': format_id,
+                    })
         self._sort_formats(formats)
 
         title = info['titre']
         subtitle = info.get('sous_titre')
         if subtitle:
             title += ' - %s' % subtitle
+        title = title.strip()
 
         subtitles = {}
         subtitles_list = [{
@@ -125,13 +128,13 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
+    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
         'info_dict': {
             'id': '84981923',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Soir 3',
             'upload_date': '20130826',
             'timestamp': 1377548400,
@@ -139,6 +142,10 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
                 'fr': 'mincount:2',
             },
         },
+        'params': {
+            # m3u8 downloads
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
         'info_dict': {
@@ -155,11 +162,32 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
         'md5': 'f485bda6e185e7d15dbc69b72bae993e',
         'info_dict': {
-            'id': '556e03339473995ee145930c',
+            'id': 'NI_173343',
             'ext': 'mp4',
             'title': 'Les entreprises familiales : le secret de la réussite',
             'thumbnail': 're:^https?://.*\.jpe?g$',
-        }
+            'timestamp': 1433273139,
+            'upload_date': '20150602',
+        },
+        'params': {
+            # m3u8 downloads
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
+        'md5': 'f485bda6e185e7d15dbc69b72bae993e',
+        'info_dict': {
+            'id': 'NI_657393',
+            'ext': 'mp4',
+            'title': 'Olivier Monthus, réalisateur de "Bretagne, le choix de l’Armor"',
+            'description': 'md5:a3264114c9d29aeca11ced113c37b16c',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
+            'timestamp': 1458300695,
+            'upload_date': '20160318',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
@@ -172,7 +200,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
             return self.url_result(dmcloud_url, 'DailymotionCloud')
 
         video_id, catalogue = self._search_regex(
-            r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
+            (r'id-video=([^@]+@[^"]+)',
+             r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
+            webpage, 'video id').split('@')
         return self._extract_video(video_id, catalogue)
 
 

youtube_dl/extractor/freevideo.py

@@ -5,7 +5,7 @@ from ..utils import ExtractorError
 
 
 class FreeVideoIE(InfoExtractor):
-    _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
+    _VALID_URL = r'^https?://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
 
     _TEST = {
         'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',

youtube_dl/extractor/funimation.py

@@ -5,7 +5,6 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     determine_ext,
-    encode_dict,
     int_or_none,
     sanitized_Request,
     ExtractorError,
@@ -54,10 +53,10 @@ class FunimationIE(InfoExtractor):
         (username, password) = self._get_login_info()
         if username is None:
             return
-        data = urlencode_postdata(encode_dict({
+        data = urlencode_postdata({
             'email_field': username,
             'password_field': password,
-        }))
+        })
         login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
             'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
             'Content-Type': 'application/x-www-form-urlencoded'

youtube_dl/extractor/gameinformer.py

@@ -2,42 +2,27 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import int_or_none
 
 
 class GameInformerIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx'
     _TEST = {
         'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
+        'md5': '292f26da1ab4beb4c9099f1304d2b071',
         'info_dict': {
             'id': '4515472681001',
-            'ext': 'm3u8',
+            'ext': 'mp4',
             'title': 'Replay - Animal Crossing',
             'description': 'md5:2e211891b215c85d061adc7a4dd2d930',
-            'timestamp': 1443457610706,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'timestamp': 1443457610,
+            'upload_date': '20150928',
+            'uploader_id': '694940074001',
         },
     }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-
-        bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url')
-        json_data = self._download_json(
-            bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions',
-            display_id)
-
-        return {
-            'id': compat_str(json_data['id']),
-            'display_id': display_id,
-            'url': json_data['IOSRenditions'][0]['url'],
-            'title': json_data['name'],
-            'description': json_data.get('shortDescription'),
-            'timestamp': int_or_none(json_data.get('publishedDate')),
-            'duration': int_or_none(json_data.get('length')),
-        }
+        brightcove_id = self._search_regex(r"getVideo\('[^']+video_id=(\d+)", webpage, 'brightcove id')
+        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

youtube_dl/extractor/gamekings.py

@@ -10,7 +10,7 @@ from .youtube import YoutubeIE
 
 
 class GamekingsIE(InfoExtractor):
-    _VALID_URL = r'http://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
     _TESTS = [{
         # YouTube embed video
         'url': 'http://www.gamekings.nl/videos/phoenix-wright-ace-attorney-dual-destinies-review/',

youtube_dl/extractor/gamespot.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class GameSpotIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
+    _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
     _TESTS = [{
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',

youtube_dl/extractor/gamestar.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class GameStarIE(InfoExtractor):
-    _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
     _TEST = {
         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
         'md5': '96974ecbb7fd8d0d20fca5a00810cea7',

youtube_dl/extractor/gametrailers.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class GametrailersIE(InfoExtractor):
-    _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
+    _VALID_URL = r'https?://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
 
     _TEST = {
         'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',

youtube_dl/extractor/gdcvault.py

@@ -3,11 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
 from ..utils import (
     remove_end,
     HEADRequest,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
@@ -123,7 +123,7 @@ class GDCVaultIE(InfoExtractor):
             'password': password,
         }
 
-        request = sanitized_Request(login_url, compat_urllib_parse.urlencode(login_form))
+        request = sanitized_Request(login_url, urlencode_postdata(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self._download_webpage(request, display_id, 'Logging in')
         start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')

youtube_dl/extractor/generic.py

@@ -59,6 +59,7 @@ from .videomore import VideomoreIE
 from .googledrive import GoogleDriveIE
 from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
+from .instagram import InstagramIE
 
 
 class GenericIE(InfoExtractor):
@@ -239,6 +240,35 @@ class GenericIE(InfoExtractor):
                 'format': 'bestvideo',
             },
         },
+        # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
+        {
+            'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
+            'info_dict': {
+                'id': 'content',
+                'ext': 'mp4',
+                'title': 'content',
+                'formats': 'mincount:8',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
+        },
+        # m3u8 served with Content-Type: text/plain
+        {
+            'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
+            'info_dict': {
+                'id': 'index',
+                'ext': 'mp4',
+                'title': 'index',
+                'upload_date': '20140720',
+                'formats': 'mincount:11',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
+        },
         # google redirect
         {
             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
@@ -1242,28 +1272,30 @@ class GenericIE(InfoExtractor):
             full_response = self._request_webpage(request, video_id)
             head_response = full_response
 
+        info_dict = {
+            'id': video_id,
+            'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
+        }
+
         # Check for direct link to a video
-        content_type = head_response.headers.get('Content-Type', '')
-        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
+        content_type = head_response.headers.get('Content-Type', '').lower()
+        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
         if m:
-            upload_date = unified_strdate(
-                head_response.headers.get('Last-Modified'))
-            formats = []
-            if m.group('format_id').endswith('mpegurl'):
+            format_id = m.group('format_id')
+            if format_id.endswith('mpegurl'):
                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
+            elif format_id == 'f4m':
+                formats = self._extract_f4m_formats(url, video_id)
             else:
                 formats = [{
                     'format_id': m.group('format_id'),
                     'url': url,
                     'vcodec': 'none' if m.group('type') == 'audio' else None
                 }]
-            return {
-                'id': video_id,
-                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
-                'direct': True,
-                'formats': formats,
-                'upload_date': upload_date,
-            }
+                info_dict['direct'] = True
+            info_dict['formats'] = formats
+            return info_dict
 
         if not self._downloader.params.get('test', False) and not is_intentional:
             force = self._downloader.params.get('force_generic_extractor', False)
@@ -1283,21 +1315,23 @@ class GenericIE(InfoExtractor):
             request.add_header('Accept-Encoding', '*')
             full_response = self._request_webpage(request, video_id)
 
+        first_bytes = full_response.read(512)
+
+        # Is it an M3U playlist?
+        if first_bytes.startswith(b'#EXTM3U'):
+            info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
+            return info_dict
+
         # Maybe it's a direct link to a video?
         # Be careful not to download the whole thing!
-        first_bytes = full_response.read(512)
         if not is_html(first_bytes):
             self._downloader.report_warning(
                 'URL could be a direct video link, returning it as such.')
-            upload_date = unified_strdate(
-                head_response.headers.get('Last-Modified'))
-            return {
-                'id': video_id,
-                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            info_dict.update({
                 'direct': True,
                 'url': url,
-                'upload_date': upload_date,
-            }
+            })
+            return info_dict
 
         webpage = self._webpage_read_content(
             full_response, url, video_id, prefix=first_bytes)
@@ -1314,12 +1348,12 @@ class GenericIE(InfoExtractor):
             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
-                return {
-                    'id': video_id,
-                    'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
-                    'formats': self._parse_mpd_formats(
-                        doc, video_id, mpd_base_url=url.rpartition('/')[0]),
-                }
+                info_dict['formats'] = self._parse_mpd_formats(
+                    doc, video_id, mpd_base_url=url.rpartition('/')[0])
+                return info_dict
+            elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
+                info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
+                return info_dict
         except compat_xml_parse_error:
             pass
 
@@ -1876,6 +1910,19 @@ class GenericIE(InfoExtractor):
                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
                 'AdobeTVVideo')
 
+        # Look for Vine embeds
+        mobj = re.search(
+            r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
+            webpage)
+        if mobj is not None:
+            return self.url_result(
+                self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
+
+        # Look for Instagram embeds
+        instagram_embed_url = InstagramIE._extract_embed_url(webpage)
+        if instagram_embed_url is not None:
+            return self.url_result(instagram_embed_url, InstagramIE.ie_key())
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
@@ -1985,6 +2032,8 @@ class GenericIE(InfoExtractor):
                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
             elif ext == 'mpd':
                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
+            elif ext == 'f4m':
+                entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
             else:
                 entry_info_dict['url'] = video_url
 

youtube_dl/extractor/googledrive.py

@@ -10,8 +10,8 @@ from ..utils import (
 
 
 class GoogleDriveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
+    _TESTS = [{
         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
         'md5': '881f7700aec4f538571fa1e0eed4a7b6',
         'info_dict': {
@@ -20,7 +20,11 @@ class GoogleDriveIE(InfoExtractor):
             'title': 'Big Buck Bunny.mp4',
             'duration': 46,
         }
-    }
+    }, {
+        # video id is longer than 28 characters
+        'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
+        'only_matching': True,
+    }]
     _FORMATS_EXT = {
         '5': 'flv',
         '6': 'flv',
@@ -43,7 +47,7 @@ class GoogleDriveIE(InfoExtractor):
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
+            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
             webpage)
         if mobj:
             return 'https://drive.google.com/file/d/%s' % mobj.group('id')

youtube_dl/extractor/hbo.py

@@ -0,0 +1,122 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    xpath_element,
+    int_or_none,
+    parse_duration,
+)
+
+
+class HBOIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
+        'md5': '1c33253f0c7782142c993c0ba62a8753',
+        'info_dict': {
+            'id': '1437839',
+            'ext': 'mp4',
+            'title': 'Ep. 64 Clip: Encryption',
+        }
+    }
+    _FORMATS_INFO = {
+        '1920': {
+            'width': 1280,
+            'height': 720,
+        },
+        '640': {
+            'width': 768,
+            'height': 432,
+        },
+        'highwifi': {
+            'width': 640,
+            'height': 360,
+        },
+        'high3g': {
+            'width': 640,
+            'height': 360,
+        },
+        'medwifi': {
+            'width': 400,
+            'height': 224,
+        },
+        'med3g': {
+            'width': 400,
+            'height': 224,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_xml(
+            'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
+        title = xpath_text(video_data, 'title', 'title', True)
+
+        formats = []
+        for source in xpath_element(video_data, 'videos', 'sources', True):
+            if source.tag == 'size':
+                path = xpath_text(source, './/path')
+                if not path:
+                    continue
+                width = source.attrib.get('width')
+                format_info = self._FORMATS_INFO.get(width, {})
+                height = format_info.get('height')
+                fmt = {
+                    'url': path,
+                    'format_id': 'http%s' % ('-%dp' % height if height else ''),
+                    'width': format_info.get('width'),
+                    'height': height,
+                }
+                rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', path)
+                if rtmp:
+                    fmt.update({
+                        'url': rtmp.group('url'),
+                        'play_path': rtmp.group('playpath'),
+                        'app': rtmp.group('app'),
+                        'ext': 'flv',
+                        'format_id': fmt['format_id'].replace('http', 'rtmp'),
+                    })
+                formats.append(fmt)
+            else:
+                video_url = source.text
+                if not video_url:
+                    continue
+                if source.tag == 'tarball':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url.replace('.tar', '/base_index_w8.m3u8'),
+                        video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+                else:
+                    format_info = self._FORMATS_INFO.get(source.tag, {})
+                    formats.append({
+                        'format_id': 'http-%s' % source.tag,
+                        'url': video_url,
+                        'width': format_info.get('width'),
+                        'height': format_info.get('height'),
+                    })
+        self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
+
+        thumbnails = []
+        card_sizes = xpath_element(video_data, 'titleCardSizes')
+        if card_sizes is not None:
+            for size in card_sizes:
+                path = xpath_text(size, 'path')
+                if not path:
+                    continue
+                width = int_or_none(size.get('width'))
+                thumbnails.append({
+                    'id': width,
+                    'url': path,
+                    'width': width,
+                })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'duration': parse_duration(xpath_element(video_data, 'duration/tv14')),
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/hotnewhiphop.py

@@ -3,16 +3,16 @@ from __future__ import unicode_literals
 import base64
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
 from ..utils import (
     ExtractorError,
     HEADRequest,
     sanitized_Request,
+    urlencode_postdata,
 )
 
 
 class HotNewHipHopIE(InfoExtractor):
-    _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
+    _VALID_URL = r'https?://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
     _TEST = {
         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
@@ -35,7 +35,7 @@ class HotNewHipHopIE(InfoExtractor):
                 r'"contentUrl" content="(.*?)"', webpage, 'content URL')
             return self.url_result(video_url, ie='Youtube')
 
-        reqdata = compat_urllib_parse.urlencode([
+        reqdata = urlencode_postdata([
             ('mediaType', 's'),
             ('mediaId', video_id),
         ])

youtube_dl/extractor/hypem.py

@@ -4,7 +4,7 @@ import json
 import time
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
     sanitized_Request,
@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class HypemIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
     _TEST = {
         'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
         'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
@@ -28,7 +28,7 @@ class HypemIE(InfoExtractor):
         track_id = self._match_id(url)
 
         data = {'ax': 1, 'ts': time.time()}
-        request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data))
+        request = sanitized_Request(url + '?' + compat_urllib_parse_urlencode(data))
         response, urlh = self._download_webpage_handle(
             request, track_id, 'Downloading webpage with the url')
 

youtube_dl/extractor/imdb.py

@@ -12,7 +12,7 @@ from ..utils import (
 class ImdbIE(InfoExtractor):
     IE_NAME = 'imdb'
     IE_DESC = 'Internet Movie Database trailers'
-    _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
@@ -70,7 +70,7 @@ class ImdbIE(InfoExtractor):
 class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
-    _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+    _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
     _TEST = {
         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
         'info_dict': {

youtube_dl/extractor/instagram.py

@@ -4,8 +4,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    get_element_by_attribute,
     int_or_none,
     limit_length,
+    lowercase_escape,
 )
 
 
@@ -38,6 +40,18 @@ class InstagramIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_embed_url(webpage):
+        blockquote_el = get_element_by_attribute(
+            'class', 'instagram-media', webpage)
+        if blockquote_el is None:
+            return
+
+        mobj = re.search(
+            r'<a[^>]+href=([\'"])(?P<link>[^\'"]+)\1', blockquote_el)
+        if mobj:
+            return mobj.group('link')
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -46,6 +60,8 @@ class InstagramIE(InfoExtractor):
                                          webpage, 'uploader id', fatal=False)
         desc = self._search_regex(
             r'"caption":"(.+?)"', webpage, 'description', default=None)
+        if desc is not None:
+            desc = lowercase_escape(desc)
 
         return {
             'id': video_id,

youtube_dl/extractor/internetvideoarchive.py

@@ -5,7 +5,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_urlparse,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     xpath_with_ns,
@@ -38,7 +38,7 @@ class InternetVideoArchiveIE(InfoExtractor):
         # Other player ids return m3u8 urls
         cleaned_dic['playerid'] = '247'
         cleaned_dic['videokbrate'] = '100000'
-        return compat_urllib_parse.urlencode(cleaned_dic)
+        return compat_urllib_parse_urlencode(cleaned_dic)
 
     def _real_extract(self, url):
         query = compat_urlparse.urlparse(url).query