release 2013.05.23

@dersphere code, from dersphere/plugin.video.myvideo_de.git
rewritten by @mc2avr
released in the Public Domain by the author
ref: https://github.com/rg3/youtube-dl/pull/842

Makefile

@@ -9,9 +9,19 @@ cleanall: clean
 PREFIX=/usr/local
 BINDIR=$(PREFIX)/bin
 MANDIR=$(PREFIX)/man
-SYSCONFDIR=/etc
 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
+
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
 	install -d $(DESTDIR)$(BINDIR)
 	install -m 755 youtube-dl $(DESTDIR)$(BINDIR)

README.md

@@ -31,7 +31,8 @@ which means you can modify it, redistribute it or use it however you like.
                                is restricted to one domain
     --list-extractors          List all supported extractors and the URLs they
                                would handle
-    --proxy None               Use the specified HTTP/HTTPS proxy
+    --proxy URL                Use the specified HTTP/HTTPS proxy
+    --no-check-certificate     Suppress HTTPS certificate validation.
 
 ## Video Selection:
     --playlist-start NUMBER    playlist video to start at (default is 1)
@@ -84,6 +85,7 @@ which means you can modify it, redistribute it or use it however you like.
                                file modification time
     --write-description        write video description to a .description file
     --write-info-json          write video metadata to a .info.json file
+    --write-thumbnail          write thumbnail image to disk
 
 ## Verbosity / Simulation Options:
     -q, --quiet                activates quiet mode
@@ -92,6 +94,7 @@ which means you can modify it, redistribute it or use it however you like.
     --skip-download            do not download the video
     -g, --get-url              simulate, quiet but print URL
     -e, --get-title            simulate, quiet but print title
+    --get-id                   simulate, quiet but print id
     --get-thumbnail            simulate, quiet but print thumbnail URL
     --get-description          simulate, quiet but print video description
     --get-filename             simulate, quiet but print output filename
@@ -113,7 +116,7 @@ which means you can modify it, redistribute it or use it however you like.
     -F, --list-formats         list all available formats (currently youtube
                                only)
     --write-sub                write subtitle file (currently youtube only)
-    --only-sub                 downloads only the subtitles (no video)
+    --only-sub                 [deprecated] alias of --skip-download
     --all-subs                 downloads all the available subtitles of the
                                video (currently youtube only)
     --list-subs                lists all available subtitles for the video

test/test_youtube_lists.py

@@ -29,7 +29,7 @@ class FakeDownloader(FileDownloader):
         self.params = parameters
     def to_screen(self, s):
         print(s)
-    def trouble(self, s):
+    def trouble(self, s, tb=None):
         raise Exception(s)
     def extract_info(self, url):
         self.result.append(url)

test/test_youtube_subtitles.py

@@ -12,6 +12,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from youtube_dl.InfoExtractors import YoutubeIE
 from youtube_dl.utils import *
+from youtube_dl import FileDownloader
 
 PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
 with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
@@ -24,13 +25,13 @@ proxy_handler = compat_urllib_request.ProxyHandler()
 opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
 compat_urllib_request.install_opener(opener)
 
-class FakeDownloader(object):
+class FakeDownloader(FileDownloader):
     def __init__(self):
         self.result = []
         self.params = parameters
     def to_screen(self, s):
         print(s)
-    def trouble(self, s):
+    def trouble(self, s, tb=None):
         raise Exception(s)
     def download(self, x):
         self.result.append(x)

test/tests.json

@@ -112,9 +112,8 @@
   {
     "name": "Escapist",
     "url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
-    "file": "6618-Breaking-Down-Baldurs-Gate.flv",
+    "file": "6618-Breaking-Down-Baldurs-Gate.mp4",
-    "md5": "c6793dbda81388f4264c1ba18684a74d",
+    "md5": "c6793dbda81388f4264c1ba18684a74d"
-    "skip": "Fails with timeout on Travis"
   },
   {
     "name": "GooglePlus",
@@ -153,7 +152,8 @@
     "file": "20274954.flv",
     "md5": "088f151799e8f572f84eb62f17d73e5c",
     "info_dict": {
-        "title": "Young Americans for Liberty February 7, 2012 2:28 AM"
+        "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
+        "uploader": "Young Americans for Liberty"
     }
   },
   {
@@ -344,8 +344,143 @@
     "file": "17258355236.mp4",
     "md5": "7c6a514d691b034ccf8567999e9e88a3",
     "info_dict": {
-        "title": "A sample video from LeeAnn. (If you need an idea..."
+        "title": "Calling all Pris! - A sample video from LeeAnn. (If you need an idea..."
+    }
+  },
+  {
+    "name": "SoundcloudSet",
+    "url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
+    "playlist":[
+      {
+        "file":"30510138.mp3",
+        "md5":"f9136bf103901728f29e419d2c70f55d",
+        "info_dict": {
+          "title":"D-D-Dance"
+        }
+      },
+      {
+        "file":"47127625.mp3",
+        "md5":"09b6758a018470570f8fd423c9453dd8",
+        "info_dict": {
+          "title":"The Royal Concept - Gimme Twice"
+        }
+      },
+      {
+        "file":"47127627.mp3",
+        "md5":"154abd4e418cea19c3b901f1e1306d9c",
+        "info_dict": {
+          "title":"Goldrushed"
+        }
+      },
+      {
+        "file":"47127629.mp3",
+        "md5":"2f5471edc79ad3f33a683153e96a79c1",
+        "info_dict": {
+          "title":"In the End"
+        }
+      },
+      {
+        "file":"47127631.mp3",
+        "md5":"f9ba87aa940af7213f98949254f1c6e2",
+        "info_dict": {
+          "title":"Knocked Up"
+        }
+      },
+      {
+        "file":"75206121.mp3",
+        "md5":"f9d1fe9406717e302980c30de4af9353",
+        "info_dict": {
+          "title":"World On Fire"
+        }
+      }
+    ]
+  },
+  {
+    "name":"Bandcamp",
+    "url":"http://youtube-dl.bandcamp.com/track/youtube-dl-test-song",
+    "file":"1812978515.mp3",
+    "md5":"cdeb30cdae1921719a3cbcab696ef53c",
+    "info_dict": {
+      "title":"youtube-dl test song \"'/\\ä↭"
+    },
+    "skip": "There is a limit of 200 free downloads / month for the test song"
+  },
+  {
+    "name": "RedTube",
+    "url": "http://www.redtube.com/66418",
+    "file": "66418.mp4",
+    "md5": "7b8c22b5e7098a3e1c09709df1126d2d",
+    "info_dict":{
+      "title":"Sucked on a toilet"
+    }
+  },
+  {
+    "name": "Photobucket",
+    "url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0",
+    "file": "zpsc0c3b9fa.mp4",
+    "md5": "7dabfb92b0a31f6c16cebc0f8e60ff99",
+    "info_dict":{
+      "title":"Tired of Link Building? Try BacklinkMyDomain.com!"
+    }
+  },
+  {
+    "name": "Ina",
+    "url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html",
+    "file": "I12055569.mp4",
+    "md5": "a667021bf2b41f8dc6049479d9bb38a3",
+    "info_dict":{
+      "title":"François Hollande \"Je crois que c'est clair\""
+    }
+  },
+  {
+    "name": "Yahoo",
+    "url": "http://screen.yahoo.com/obama-celebrates-iraq-victory-27592561.html",
+    "file": "27592561.flv",
+    "md5": "c6179bed843512823fd284fa2e7f012d",
+    "info_dict": {
+        "title": "Obama Celebrates Iraq Victory"
+    },
+    "skip": "Requires rtmpdump"
+  },
+  {
+    "name": "Howcast",
+    "url": "http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly",
+    "file": "390161.mp4",
+    "md5": "1d7ba54e2c9d7dc6935ef39e00529138",
+    "info_dict":{
+      "title":"How to Tie a Square Knot Properly",
+      "description":"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot."
+    }
+  },
+  {
+    "name": "Vine",
+    "url": "https://vine.co/v/b9KOOWX7HUx",
+    "file": "b9KOOWX7HUx.mp4",
+    "md5": "2f36fed6235b16da96ce9b4dc890940d",
+    "info_dict":{
+      "title": "Chicken.",
+      "uploader": "Jack Dorsey"
+    }
+  },
+  {
+    "name": "Flickr",
+    "url": "http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/",
+    "file": "5645318632.mp4",
+    "md5": "6fdc01adbc89d72fc9c4f15b4a4ba87b",
+    "info_dict":{
+      "title": "Dark Hollow Waterfalls",
+      "uploader_id": "forestwander-nature-pictures",
+      "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up."
+    }
+  },
+  {
+    "name": "Teamcoco",
+    "url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush",
+    "file": "19705.mp4",
+    "md5": "27b6f7527da5acf534b15f21b032656e",
+    "info_dict":{
+      "title": "Louis C.K. Interview Pt. 1 11/3/11",
+      "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
     }
   }
-
 ]

youtube_dl/FileDownloader.py

@@ -7,6 +7,7 @@ import math
 import io
 import os
 import re
+import shutil
 import socket
 import subprocess
 import sys
@@ -53,6 +54,7 @@ class FileDownloader(object):
     quiet:             Do not print messages to stdout.
     forceurl:          Force printing final URL.
     forcetitle:        Force printing title.
+    forceid:           Force printing ID.
     forcethumbnail:    Force printing thumbnail URL.
     forcedescription:  Force printing description.
     forcefilename:     Force printing final filename.
@@ -79,8 +81,8 @@ class FileDownloader(object):
     updatetime:        Use the Last-modified header to set output file timestamps.
     writedescription:  Write the video description to a .description file
     writeinfojson:     Write the video description to a .info.json file
+    writethumbnail:    Write the thumbnail image to a file
     writesubtitles:    Write the video subtitles to a file
-    onlysubtitles:     Downloads only the subtitles of the video
     allsubtitles:      Downloads all the subtitles of the video
     listsubtitles:     Lists all available subtitles for the video
     subtitlesformat:   Subtitle format [sbv/srt] (default=srt)
@@ -90,6 +92,7 @@ class FileDownloader(object):
     min_filesize:      Skip files smaller than this size
     max_filesize:      Skip files larger than this size
     daterange:         A DateRange object, download only if the upload_date is in the range.
+    skip_download:     Skip the actual download of the video file
     """
 
     params = None
@@ -345,12 +348,13 @@ class FileDownloader(object):
         """Report download progress."""
         if self.params.get('noprogress', False):
             return
+        clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
         if self.params.get('progress_with_newline', False):
             self.to_screen(u'[download] %s of %s at %s ETA %s' %
                 (percent_str, data_len_str, speed_str, eta_str))
         else:
-            self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
+            self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
-                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+                (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
         self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
                 (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
 
@@ -432,47 +436,45 @@ class FileDownloader(object):
                 return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
         return None
         
-    def extract_info(self, url, download = True, ie_name = None):
+    def extract_info(self, url, download=True, ie_key=None, extra_info={}):
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
+        extra_info is a dict containing the extra values to add to each result
          '''
-        suitable_found = False
         
-        #We copy the original list
+        if ie_key:
-        ies = list(self._ies)
+            ie = get_info_extractor(ie_key)()
-
+            ie.set_downloader(self)
-        if ie_name is not None:
+            ies = [ie]
-            #We put in the first place the given info extractor
+        else:
-            first_ie = get_info_extractor(ie_name)()
+            ies = self._ies
-            first_ie.set_downloader(self)
-            ies.insert(0, first_ie)
 
         for ie in ies:
-            # Go to next InfoExtractor if not suitable
             if not ie.suitable(url):
                 continue
 
-            # Warn if the _WORKING attribute is False
             if not ie.working():
-                self.report_warning(u'the program functionality for this site has been marked as broken, '
+                self.report_warning(u'The program functionality for this site has been marked as broken, '
-                               u'and will probably not work. If you want to go on, use the -i option.')
+                                    u'and will probably not work.')
 
-            # Suitable InfoExtractor found
-            suitable_found = True
-
-            # Extract information from URL and process it
             try:
-                ie_results = ie.extract(url)
+                ie_result = ie.extract(url)
-                if ie_results is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
+                if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
                     break
-                results = []
+                if isinstance(ie_result, list):
-                for ie_result in ie_results:
+                    # Backwards compatibility: old IE result format
-                    if not 'extractor' in ie_result:
+                    for result in ie_result:
-                        #The extractor has already been set somewhere else
+                        result.update(extra_info)
-                        ie_result['extractor'] = ie.IE_NAME
+                    ie_result = {
-                    results.append(self.process_ie_result(ie_result, download))
+                        '_type': 'compat_list',
-                return results
+                        'entries': ie_result,
+                    }
+                else:
+                    ie_result.update(extra_info)
+                if 'extractor' not in ie_result:
+                    ie_result['extractor'] = ie.IE_NAME
+                return self.process_ie_result(ie_result, download=download)
             except ExtractorError as de: # An error we somewhat expected
                 self.report_error(compat_str(de), de.format_traceback())
                 break
@@ -482,33 +484,36 @@ class FileDownloader(object):
                     break
                 else:
                     raise
-        if not suitable_found:
+        else:
-                self.report_error(u'no suitable InfoExtractor: %s' % url)
+            self.report_error(u'no suitable InfoExtractor: %s' % url)
         
-    def process_ie_result(self, ie_result, download = True):
+    def process_ie_result(self, ie_result, download=True, extra_info={}):
         """
-        Take the result of the ie and return a list of videos.
+        Take the result of the ie(may be modified) and resolve all unresolved
-        For url elements it will search the suitable ie and get the videos
+        references (URLs, playlist items).
-        For playlist elements it will process each of the elements of the 'entries' key
+
-        
         It will also download the videos if 'download'.
+        Returns the resolved ie_result.
         """
-        result_type = ie_result.get('_type', 'video') #If not given we suppose it's a video, support the dafault old system
+
+        result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
         if result_type == 'video':
             if 'playlist' not in ie_result:
-                #It isn't part of a playlist
+                # It isn't part of a playlist
                 ie_result['playlist'] = None
                 ie_result['playlist_index'] = None
             if download:
-                #Do the download:
                 self.process_info(ie_result)
             return ie_result
         elif result_type == 'url':
-            #We get the video pointed by the url
+            # We have to add extra_info to the results because it may be
-            result = self.extract_info(ie_result['url'], download, ie_name = ie_result['ie_key'])[0]
+            # contained in a playlist
-            return result
+            return self.extract_info(ie_result['url'],
+                                     download,
+                                     ie_key=ie_result.get('ie_key'),
+                                     extra_info=extra_info)
         elif result_type == 'playlist':
-            #We process each entry in the playlist
+            # We process each entry in the playlist
             playlist = ie_result.get('title', None) or ie_result.get('id', None)
             self.to_screen(u'[download] Downloading playlist: %s'  % playlist)
 
@@ -530,23 +535,35 @@ class FileDownloader(object):
 
             for i,entry in enumerate(entries,1):
                 self.to_screen(u'[download] Downloading video #%s of %s' %(i, n_entries))
-                entry_result = self.process_ie_result(entry, False)
+                extra = {
-                entry_result['playlist'] = playlist
+                         'playlist': playlist, 
-                entry_result['playlist_index'] = i + playliststart
+                         'playlist_index': i + playliststart,
-                #We must do the download here to correctly set the 'playlist' key
+                         }
-                if download:
+                entry_result = self.process_ie_result(entry,
-                    self.process_info(entry_result)
+                                                      download=download,
+                                                      extra_info=extra)
                 playlist_results.append(entry_result)
-            result = ie_result.copy()
+            ie_result['entries'] = playlist_results
-            result['entries'] = playlist_results
+            return ie_result
-            return result
+        elif result_type == 'compat_list':
+            def _fixup(r):
+                r.setdefault('extractor', ie_result['extractor'])
+                return r
+            ie_result['entries'] = [
+                self.process_ie_result(_fixup(r), download=download)
+                for r in ie_result['entries']
+            ]
+            return ie_result
+        else:
+            raise Exception('Invalid result type: %s' % result_type)
 
     def process_info(self, info_dict):
-        """Process a single dictionary returned by an InfoExtractor."""
+        """Process a single resolved IE result."""
 
+        assert info_dict.get('_type', 'video') == 'video'
         #We increment the download the download count here to match the previous behaviour.
         self.increment_downloads()
-        
+
         info_dict['fulltitle'] = info_dict['title']
         if len(info_dict['title']) > 200:
             info_dict['title'] = info_dict['title'][:197] + u'...'
@@ -572,6 +589,8 @@ class FileDownloader(object):
         # Forced printings
         if self.params.get('forcetitle', False):
             compat_print(info_dict['title'])
+        if self.params.get('forceid', False):
+            compat_print(info_dict['id'])
         if self.params.get('forceurl', False):
             compat_print(info_dict['url'])
         if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
@@ -592,7 +611,7 @@ class FileDownloader(object):
 
         try:
             dn = os.path.dirname(encodeFilename(filename))
-            if dn != '' and not os.path.exists(dn): # dn is already encoded
+            if dn != '' and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
             self.report_error(u'unable to create directory ' + compat_str(err))
@@ -625,8 +644,6 @@ class FileDownloader(object):
                 except (OSError, IOError):
                     self.report_error(u'Cannot write subtitles file ' + descfn)
                     return
-            if self.params.get('onlysubtitles', False):
-                return 
 
         if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
             subtitles = info_dict['subtitles']
@@ -644,8 +661,6 @@ class FileDownloader(object):
                     except (OSError, IOError):
                         self.report_error(u'Cannot write subtitles file ' + descfn)
                         return
-            if self.params.get('onlysubtitles', False):
-                return 
 
         if self.params.get('writeinfojson', False):
             infofn = filename + u'.info.json'
@@ -657,6 +672,20 @@ class FileDownloader(object):
                 self.report_error(u'Cannot write metadata to JSON file ' + infofn)
                 return
 
+        if self.params.get('writethumbnail', False):
+            if 'thumbnail' in info_dict:
+                thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2]
+                if not thumb_format:
+                    thumb_format = 'jpg'
+                thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
+                self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
+                               (info_dict['extractor'], info_dict['id']))
+                uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+                with open(thumb_filename, 'wb') as thumbf:
+                    shutil.copyfileobj(uf, thumbf)
+                self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
+                               (info_dict['extractor'], info_dict['id'], thumb_filename))
+
         if not self.params.get('skip_download', False):
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
                 success = True
@@ -719,7 +748,7 @@ class FileDownloader(object):
             except (IOError, OSError):
                 self.report_warning(u'Unable to remove downloaded video file')
 
-    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path):
+    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
 
@@ -734,12 +763,15 @@ class FileDownloader(object):
         # the connection was interrumpted and resuming appears to be
         # possible. This is part of rtmpdump's normal usage, AFAIK.
         basic_args = ['rtmpdump', '-q', '-r', url, '-o', tmpfilename]
+        if self.params.get('verbose', False): basic_args[1] = '-v'
         if player_url is not None:
             basic_args += ['-W', player_url]
         if page_url is not None:
             basic_args += ['--pageUrl', page_url]
         if play_path is not None:
             basic_args += ['-y', play_path]
+        if tc_url is not None:
+            basic_args += ['--tcUrl', url]
         args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
         if self.params.get('verbose', False):
             try:
@@ -795,7 +827,8 @@ class FileDownloader(object):
             return self._download_with_rtmpdump(filename, url,
                                                 info_dict.get('player_url', None),
                                                 info_dict.get('page_url', None),
-                                                info_dict.get('play_path', None))
+                                                info_dict.get('play_path', None),
+                                                info_dict.get('tc_url', None))
 
         tmpfilename = self.temp_name(filename)
         stream = None

youtube_dl/PostProcessor.py

@@ -85,8 +85,9 @@ class FFmpegPostProcessor(PostProcessor):
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         stdout,stderr = p.communicate()
         if p.returncode != 0:
+            stderr = stderr.decode('utf-8', 'replace')
             msg = stderr.strip().split('\n')[-1]
-            raise FFmpegPostProcessorError(msg.decode('utf-8', 'replace'))
+            raise FFmpegPostProcessorError(msg)
 
     def _ffmpeg_filename_argument(self, fn):
         # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
@@ -188,6 +189,11 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
 
         prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
         new_path = prefix + sep + extension
+
+        # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
+        if new_path == path:
+            self._nopostoverwrites = True
+
         try:
             if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
                 self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
@@ -210,7 +216,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
                 self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
 
         information['filepath'] = new_path
-        return False,information
+        return self._nopostoverwrites,information
 
 class FFmpegVideoConvertor(FFmpegPostProcessor):
     def __init__(self, downloader=None,preferedformat=None):

youtube_dl/__init__.py

@@ -25,10 +25,14 @@ __authors__  = (
     'Jeff Crouse',
     'Osama Khalid',
     'Michael Walter',
+    'M. Yasoob Ullah Khalid',
+    'Julien Fraichard',
+    'Johny Mo Swag',
     )
 
 __license__ = 'Public Domain'
 
+import codecs
 import getpass
 import optparse
 import os
@@ -146,7 +150,8 @@ def parseOpts(overrideArguments=None):
     general.add_option('--list-extractors',
             action='store_true', dest='list_extractors',
             help='List all supported extractors and the URLs they would handle', default=False)
-    general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy')
+    general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
+    general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
     general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
 
     selection.add_option('--playlist-start',
@@ -186,8 +191,8 @@ def parseOpts(overrideArguments=None):
             action='store_true', dest='writesubtitles',
             help='write subtitle file (currently youtube only)', default=False)
     video_format.add_option('--only-sub',
-            action='store_true', dest='onlysubtitles',
+            action='store_true', dest='skip_download',
-            help='downloads only the subtitles (no video)', default=False)
+            help='[deprecated] alias of --skip-download', default=False)
     video_format.add_option('--all-subs',
             action='store_true', dest='allsubtitles',
             help='downloads all the available subtitles of the video (currently youtube only)', default=False)
@@ -211,6 +216,8 @@ def parseOpts(overrideArguments=None):
             action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
     verbosity.add_option('-e', '--get-title',
             action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+    verbosity.add_option('--get-id',
+            action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
     verbosity.add_option('--get-thumbnail',
             action='store_true', dest='getthumbnail',
             help='simulate, quiet but print thumbnail URL', default=False)
@@ -284,6 +291,9 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option('--write-info-json',
             action='store_true', dest='writeinfojson',
             help='write video metadata to a .info.json file', default=False)
+    filesystem.add_option('--write-thumbnail',
+            action='store_true', dest='writethumbnail',
+            help='write thumbnail image to disk', default=False)
 
 
     postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
@@ -331,6 +341,11 @@ def parseOpts(overrideArguments=None):
     return parser, opts, args
 
 def _real_main(argv=None):
+    # Compatibility fixes for Windows
+    if sys.platform == 'win32':
+        # https://github.com/rg3/youtube-dl/issues/820
+        codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
+
     parser, opts, args = parseOpts(argv)
 
     # Open appropriate CookieJar
@@ -385,7 +400,8 @@ def _real_main(argv=None):
         if 'http' in proxies and 'https' not in proxies:
             proxies['https'] = proxies['http']
     proxy_handler = compat_urllib_request.ProxyHandler(proxies)
-    opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+    https_handler = make_HTTPS_handler(opts)
+    opener = compat_urllib_request.build_opener(https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
     compat_urllib_request.install_opener(opener)
     socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
 
@@ -481,15 +497,16 @@ def _real_main(argv=None):
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
-        'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+        'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
+        'forceid': opts.getid,
         'forcethumbnail': opts.getthumbnail,
         'forcedescription': opts.getdescription,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
         'simulate': opts.simulate,
-        'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+        'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
         'format': opts.format,
         'format_limit': opts.format_limit,
         'listformats': opts.listformats,
@@ -513,8 +530,8 @@ def _real_main(argv=None):
         'updatetime': opts.updatetime,
         'writedescription': opts.writedescription,
         'writeinfojson': opts.writeinfojson,
+        'writethumbnail': opts.writethumbnail,
         'writesubtitles': opts.writesubtitles,
-        'onlysubtitles': opts.onlysubtitles,
         'allsubtitles': opts.allsubtitles,
         'listsubtitles': opts.listsubtitles,
         'subtitlesformat': opts.subtitlesformat,
@@ -529,7 +546,7 @@ def _real_main(argv=None):
         'keepvideo': opts.keepvideo,
         'min_filesize': opts.min_filesize,
         'max_filesize': opts.max_filesize,
-        'daterange': date
+        'daterange': date,
         })
 
     if opts.verbose:

youtube_dl/utils.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+import errno
 import gzip
 import io
 import json
@@ -149,6 +150,10 @@ try:
 except NameError:
     compat_chr = chr
 
+def compat_ord(c):
+    if type(c) is int: return c
+    else: return ord(c)
+
 std_headers = {
     'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
     'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
@@ -334,12 +339,20 @@ def sanitize_open(filename, open_mode):
         stream = open(encodeFilename(filename), open_mode)
         return (stream, filename)
     except (IOError, OSError) as err:
-        # In case of error, try to remove win32 forbidden chars
+        if err.errno in (errno.EACCES,):
-        filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename)
+            raise
 
-        # An exception here should be caught in the caller
+        # In case of error, try to remove win32 forbidden chars
-        stream = open(encodeFilename(filename), open_mode)
+        alt_filename = os.path.join(
-        return (stream, filename)
+                        re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part)
+                        for path_part in os.path.split(filename)
+                       )
+        if alt_filename == filename:
+            raise
+        else:
+            # An exception here should be caught in the caller
+            stream = open(encodeFilename(filename), open_mode)
+            return (stream, alt_filename)
 
 
 def timeconvert(timestr):
@@ -430,6 +443,28 @@ def decodeOption(optval):
     assert isinstance(optval, compat_str)
     return optval
 
+def formatSeconds(secs):
+    if secs > 3600:
+        return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
+    elif secs > 60:
+        return '%d:%02d' % (secs // 60, secs % 60)
+    else:
+        return '%d' % secs
+
+def make_HTTPS_handler(opts):
+    if sys.version_info < (3,2):
+        # Python's 2.x handler is very simplistic
+        return compat_urllib_request.HTTPSHandler()
+    else:
+        import ssl
+        context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
+        context.set_default_verify_paths()
+        
+        context.verify_mode = (ssl.CERT_NONE
+                               if opts.no_check_certificate
+                               else ssl.CERT_REQUIRED)
+        return compat_urllib_request.HTTPSHandler(context=context)
+
 class ExtractorError(Exception):
     """Error during info extraction."""
     def __init__(self, msg, tb=None):

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2013.04.30'
+__version__ = '2013.05.23'