mirror of
https://source.netsyms.com/Mirrors/youtube-dl
synced 2026-03-25 14:30:50 +00:00
Compare commits
13 Commits
2016.05.30
...
2016.06.02
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5e3856a2c5 | ||
|
|
6e6b9f600f | ||
|
|
6a1df4fb5f | ||
|
|
dde1ce7c06 | ||
|
|
811586ebcf | ||
|
|
0ff3749bfe | ||
|
|
28bab13348 | ||
|
|
877032314f | ||
|
|
8ec2b2c41c | ||
|
|
197a5da1d0 | ||
|
|
abbb2938fa | ||
|
|
f657b1a5f2 | ||
|
|
86a52881c6 |
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.05.30*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.05.30**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.02**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] youtube-dl version 2016.05.30
|
||||
[debug] youtube-dl version 2016.06.02
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
@@ -14,7 +14,6 @@ script: nosetests test --verbose
|
||||
notifications:
|
||||
email:
|
||||
- filippo.valsorda@gmail.com
|
||||
- phihag@phihag.de
|
||||
- yasoob.khld@gmail.com
|
||||
# irc:
|
||||
# channels:
|
||||
|
||||
@@ -162,7 +162,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
(experimental)
|
||||
|
||||
## Download Options:
|
||||
-r, --rate-limit LIMIT Maximum download rate in bytes per second
|
||||
-r, --limit-rate RATE Maximum download rate in bytes per second
|
||||
(e.g. 50K or 4.2M)
|
||||
-R, --retries RETRIES Number of retries (default is 10), or
|
||||
"infinite".
|
||||
|
||||
@@ -55,6 +55,7 @@
|
||||
- **arte.tv:future**
|
||||
- **arte.tv:info**
|
||||
- **arte.tv:magazine**
|
||||
- **arte.tv:playlist**
|
||||
- **AtresPlayer**
|
||||
- **ATTTechChannel**
|
||||
- **AudiMedia**
|
||||
|
||||
@@ -61,10 +61,7 @@ class ArteTvIE(InfoExtractor):
|
||||
}
|
||||
|
||||
|
||||
class ArteTVPlus7IE(InfoExtractor):
|
||||
IE_NAME = 'arte.tv:+7'
|
||||
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)'
|
||||
|
||||
class ArteTVBaseIE(InfoExtractor):
|
||||
@classmethod
|
||||
def _extract_url_info(cls, url):
|
||||
mobj = re.match(cls._VALID_URL, url)
|
||||
@@ -78,60 +75,6 @@ class ArteTVPlus7IE(InfoExtractor):
|
||||
video_id = mobj.group('id')
|
||||
return video_id, lang
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, lang = self._extract_url_info(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
return self._extract_from_webpage(webpage, video_id, lang)
|
||||
|
||||
def _extract_from_webpage(self, webpage, video_id, lang):
|
||||
patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
|
||||
ids = (video_id, '')
|
||||
# some pages contain multiple videos (like
|
||||
# http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
|
||||
# so we first try to look for json URLs that contain the video id from
|
||||
# the 'vid' parameter.
|
||||
patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
|
||||
json_url = self._html_search_regex(
|
||||
patterns, webpage, 'json vp url', default=None)
|
||||
if not json_url:
|
||||
def find_iframe_url(webpage, default=NO_DEFAULT):
|
||||
return self._html_search_regex(
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
|
||||
webpage, 'iframe url', group='url', default=default)
|
||||
|
||||
iframe_url = find_iframe_url(webpage, None)
|
||||
if not iframe_url:
|
||||
embed_url = self._html_search_regex(
|
||||
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
|
||||
if embed_url:
|
||||
player = self._download_json(
|
||||
embed_url, video_id, 'Downloading player page')
|
||||
iframe_url = find_iframe_url(player['html'])
|
||||
# en and es URLs produce react-based pages with different layout (e.g.
|
||||
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
|
||||
if not iframe_url:
|
||||
program = self._search_regex(
|
||||
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
|
||||
webpage, 'program', default=None)
|
||||
if program:
|
||||
embed_html = self._parse_json(program, video_id)
|
||||
if embed_html:
|
||||
iframe_url = find_iframe_url(embed_html['embed_html'])
|
||||
if iframe_url:
|
||||
json_url = compat_parse_qs(
|
||||
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
|
||||
if json_url:
|
||||
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, title=None):
|
||||
info = self._download_json(json_url, video_id)
|
||||
player_info = info['videoJsonPlayer']
|
||||
@@ -235,6 +178,74 @@ class ArteTVPlus7IE(InfoExtractor):
|
||||
return info_dict
|
||||
|
||||
|
||||
class ArteTVPlus7IE(ArteTVBaseIE):
|
||||
IE_NAME = 'arte.tv:+7'
|
||||
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, lang = self._extract_url_info(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
return self._extract_from_webpage(webpage, video_id, lang)
|
||||
|
||||
def _extract_from_webpage(self, webpage, video_id, lang):
|
||||
patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
|
||||
ids = (video_id, '')
|
||||
# some pages contain multiple videos (like
|
||||
# http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
|
||||
# so we first try to look for json URLs that contain the video id from
|
||||
# the 'vid' parameter.
|
||||
patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
|
||||
json_url = self._html_search_regex(
|
||||
patterns, webpage, 'json vp url', default=None)
|
||||
if not json_url:
|
||||
def find_iframe_url(webpage, default=NO_DEFAULT):
|
||||
return self._html_search_regex(
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
|
||||
webpage, 'iframe url', group='url', default=default)
|
||||
|
||||
iframe_url = find_iframe_url(webpage, None)
|
||||
if not iframe_url:
|
||||
embed_url = self._html_search_regex(
|
||||
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
|
||||
if embed_url:
|
||||
player = self._download_json(
|
||||
embed_url, video_id, 'Downloading player page')
|
||||
iframe_url = find_iframe_url(player['html'])
|
||||
# en and es URLs produce react-based pages with different layout (e.g.
|
||||
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
|
||||
if not iframe_url:
|
||||
program = self._search_regex(
|
||||
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
|
||||
webpage, 'program', default=None)
|
||||
if program:
|
||||
embed_html = self._parse_json(program, video_id)
|
||||
if embed_html:
|
||||
iframe_url = find_iframe_url(embed_html['embed_html'])
|
||||
if iframe_url:
|
||||
json_url = compat_parse_qs(
|
||||
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
|
||||
if json_url:
|
||||
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)
|
||||
|
||||
|
||||
# It also uses the arte_vp_url url from the webpage to extract the information
|
||||
class ArteTVCreativeIE(ArteTVPlus7IE):
|
||||
IE_NAME = 'arte.tv:creative'
|
||||
@@ -267,7 +278,7 @@ class ArteTVInfoIE(ArteTVPlus7IE):
|
||||
IE_NAME = 'arte.tv:info'
|
||||
_VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
|
||||
'info_dict': {
|
||||
'id': '067528-000-A',
|
||||
@@ -275,7 +286,7 @@ class ArteTVInfoIE(ArteTVPlus7IE):
|
||||
'title': 'Service civique, un cache misère ?',
|
||||
'upload_date': '20160403',
|
||||
},
|
||||
}
|
||||
}]
|
||||
|
||||
|
||||
class ArteTVFutureIE(ArteTVPlus7IE):
|
||||
@@ -300,6 +311,8 @@ class ArteTVDDCIE(ArteTVPlus7IE):
|
||||
IE_NAME = 'arte.tv:ddc'
|
||||
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
|
||||
|
||||
_TESTS = []
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, lang = self._extract_url_info(url)
|
||||
if lang == 'folge':
|
||||
@@ -318,7 +331,7 @@ class ArteTVConcertIE(ArteTVPlus7IE):
|
||||
IE_NAME = 'arte.tv:concert'
|
||||
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
|
||||
'md5': '9ea035b7bd69696b67aa2ccaaa218161',
|
||||
'info_dict': {
|
||||
@@ -328,14 +341,14 @@ class ArteTVConcertIE(ArteTVPlus7IE):
|
||||
'upload_date': '20140128',
|
||||
'description': 'md5:486eb08f991552ade77439fe6d82c305',
|
||||
},
|
||||
}
|
||||
}]
|
||||
|
||||
|
||||
class ArteTVCinemaIE(ArteTVPlus7IE):
|
||||
IE_NAME = 'arte.tv:cinema'
|
||||
_VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://cinema.arte.tv/de/node/38291',
|
||||
'md5': '6b275511a5107c60bacbeeda368c3aa1',
|
||||
'info_dict': {
|
||||
@@ -345,7 +358,7 @@ class ArteTVCinemaIE(ArteTVPlus7IE):
|
||||
'upload_date': '20160122',
|
||||
'description': 'md5:7f749bbb77d800ef2be11d54529b96bc',
|
||||
},
|
||||
}
|
||||
}]
|
||||
|
||||
|
||||
class ArteTVMagazineIE(ArteTVPlus7IE):
|
||||
@@ -390,9 +403,41 @@ class ArteTVEmbedIE(ArteTVPlus7IE):
|
||||
)
|
||||
'''
|
||||
|
||||
_TESTS = []
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
lang = mobj.group('lang')
|
||||
json_url = mobj.group('json_url')
|
||||
return self._extract_from_json_url(json_url, video_id, lang)
|
||||
|
||||
|
||||
class ArteTVPlaylistIE(ArteTVBaseIE):
|
||||
IE_NAME = 'arte.tv:playlist'
|
||||
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV',
|
||||
'info_dict': {
|
||||
'id': 'PL-013263',
|
||||
'title': 'Areva & Uramin',
|
||||
},
|
||||
'playlist_mincount': 6,
|
||||
}, {
|
||||
'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id, lang = self._extract_url_info(url)
|
||||
collection = self._download_json(
|
||||
'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
|
||||
% (lang, playlist_id), playlist_id)
|
||||
title = collection.get('title')
|
||||
description = collection.get('shortDescription') or collection.get('teaserText')
|
||||
entries = [
|
||||
self._extract_from_json_url(
|
||||
video['jsonUrl'], video.get('programId') or playlist_id, lang)
|
||||
for video in collection['videos'] if video.get('jsonUrl')]
|
||||
return self.playlist_result(entries, playlist_id, title, description)
|
||||
|
||||
@@ -56,6 +56,7 @@ from .arte import (
|
||||
ArteTVDDCIE,
|
||||
ArteTVMagazineIE,
|
||||
ArteTVEmbedIE,
|
||||
ArteTVPlaylistIE,
|
||||
)
|
||||
from .atresplayer import AtresPlayerIE
|
||||
from .atttechchannel import ATTTechChannelIE
|
||||
|
||||
@@ -881,18 +881,6 @@ class GenericIE(InfoExtractor):
|
||||
'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
|
||||
}
|
||||
},
|
||||
# Kaltura embed
|
||||
{
|
||||
'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
|
||||
'info_dict': {
|
||||
'id': '1_eergr3h1',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20150226',
|
||||
'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
|
||||
'timestamp': int,
|
||||
'title': 'John Carlson Postgame 2/25/15',
|
||||
},
|
||||
},
|
||||
# Kaltura embed (different embed code)
|
||||
{
|
||||
'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
|
||||
@@ -918,6 +906,19 @@ class GenericIE(InfoExtractor):
|
||||
'uploader_id': 'echojecka',
|
||||
},
|
||||
},
|
||||
# Kaltura embed with single quotes
|
||||
{
|
||||
'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
|
||||
'info_dict': {
|
||||
'id': '0_izeg5utt',
|
||||
'ext': 'mp4',
|
||||
'title': '35871',
|
||||
'timestamp': 1355743100,
|
||||
'upload_date': '20121217',
|
||||
'uploader_id': 'batchUser',
|
||||
},
|
||||
'add_ie': ['Kaltura'],
|
||||
},
|
||||
# Eagle.Platform embed (generic URL)
|
||||
{
|
||||
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
|
||||
@@ -1032,14 +1033,18 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
# UDN embed
|
||||
{
|
||||
'url': 'http://www.udn.com/news/story/7314/822787',
|
||||
'url': 'https://video.udn.com/news/300346',
|
||||
'md5': 'fd2060e988c326991037b9aff9df21a6',
|
||||
'info_dict': {
|
||||
'id': '300346',
|
||||
'ext': 'mp4',
|
||||
'title': '中一中男師變性 全校師生力挺',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
}
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
# Ooyala embed
|
||||
{
|
||||
@@ -1903,7 +1908,7 @@ class GenericIE(InfoExtractor):
|
||||
return self.url_result(mobj.group('url'), 'Zapiks')
|
||||
|
||||
# Look for Kaltura embeds
|
||||
mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
|
||||
mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?(?P<q1>['\"])wid(?P=q1)\s*:\s*(?P<q2>['\"])_?(?P<partner_id>[^'\"]+)(?P=q2),.*?(?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*(?P<q4>['\"])(?P<id>[^'\"]+)(?P=q4),", webpage) or
|
||||
re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
|
||||
if mobj is not None:
|
||||
return self.url_result(smuggle_url(
|
||||
|
||||
@@ -96,20 +96,18 @@ class SpankwireIE(InfoExtractor):
|
||||
formats = []
|
||||
for height, video_url in zip(heights, video_urls):
|
||||
path = compat_urllib_parse_urlparse(video_url).path
|
||||
_, quality = path.split('/')[4].split('_')[:2]
|
||||
f = {
|
||||
'url': video_url,
|
||||
'height': height,
|
||||
}
|
||||
tbr = self._search_regex(r'^(\d+)[Kk]$', quality, 'tbr', default=None)
|
||||
if tbr:
|
||||
f.update({
|
||||
'tbr': int(tbr),
|
||||
'format_id': '%dp' % height,
|
||||
})
|
||||
m = re.search(r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', path)
|
||||
if m:
|
||||
tbr = int(m.group('tbr'))
|
||||
height = int(m.group('height'))
|
||||
else:
|
||||
f['format_id'] = quality
|
||||
formats.append(f)
|
||||
tbr = None
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': '%dp' % height,
|
||||
'height': height,
|
||||
'tbr': tbr,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
age_limit = self._rta_search(webpage)
|
||||
|
||||
@@ -48,6 +48,6 @@ class TF1IE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
wat_id = self._html_search_regex(
|
||||
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})(?:.*?)?\1',
|
||||
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8}).*?\1',
|
||||
webpage, 'wat id', group='id')
|
||||
return self.url_result('wat:%s' % wat_id, 'Wat')
|
||||
|
||||
@@ -2,10 +2,13 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
ExtractorError,
|
||||
)
|
||||
from ..compat import compat_urlparse
|
||||
|
||||
@@ -16,13 +19,16 @@ class UDNEmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?:' + _PROTOCOL_RELATIVE_VALID_URL
|
||||
_TESTS = [{
|
||||
'url': 'http://video.udn.com/embed/news/300040',
|
||||
'md5': 'de06b4c90b042c128395a88f0384817e',
|
||||
'info_dict': {
|
||||
'id': '300040',
|
||||
'ext': 'mp4',
|
||||
'title': '生物老師男變女 全校挺"做自己"',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
}
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://video.udn.com/embed/news/300040',
|
||||
'only_matching': True,
|
||||
@@ -38,39 +44,53 @@ class UDNEmbedIE(InfoExtractor):
|
||||
page = self._download_webpage(url, video_id)
|
||||
|
||||
options = json.loads(js_to_json(self._html_search_regex(
|
||||
r'var options\s*=\s*([^;]+);', page, 'video urls dictionary')))
|
||||
r'var\s+options\s*=\s*([^;]+);', page, 'video urls dictionary')))
|
||||
|
||||
video_urls = options['video']
|
||||
|
||||
if video_urls.get('youtube'):
|
||||
return self.url_result(video_urls.get('youtube'), 'Youtube')
|
||||
|
||||
try:
|
||||
del video_urls['youtube']
|
||||
except KeyError:
|
||||
pass
|
||||
formats = []
|
||||
for video_type, api_url in video_urls.items():
|
||||
if not api_url:
|
||||
continue
|
||||
|
||||
formats = [{
|
||||
'url': self._download_webpage(
|
||||
video_url = self._download_webpage(
|
||||
compat_urlparse.urljoin(url, api_url), video_id,
|
||||
'retrieve url for %s video' % video_type),
|
||||
'format_id': video_type,
|
||||
'preference': 0 if video_type == 'mp4' else -1,
|
||||
} for video_type, api_url in video_urls.items() if api_url]
|
||||
note='retrieve url for %s video' % video_type)
|
||||
|
||||
if not formats:
|
||||
raise ExtractorError('No videos found', expected=True)
|
||||
ext = determine_ext(video_url)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
video_url, video_id, ext='mp4', m3u8_id='hls'))
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
video_url, video_id, f4m_id='hds'))
|
||||
else:
|
||||
mobj = re.search(r'_(?P<height>\d+)p_(?P<tbr>\d+).mp4', video_url)
|
||||
a_format = {
|
||||
'url': video_url,
|
||||
# video_type may be 'mp4', which confuses YoutubeDL
|
||||
'format_id': 'http-' + video_type,
|
||||
}
|
||||
if mobj:
|
||||
a_format.update({
|
||||
'height': int_or_none(mobj.group('height')),
|
||||
'tbr': int_or_none(mobj.group('tbr')),
|
||||
})
|
||||
formats.append(a_format)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = None
|
||||
|
||||
if options.get('gallery') and len(options['gallery']):
|
||||
thumbnail = options['gallery'][0].get('original')
|
||||
thumbnails = [{
|
||||
'url': img_url,
|
||||
'id': img_type,
|
||||
} for img_type, img_url in options.get('gallery', [{}])[0].items() if img_url]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': options['title'],
|
||||
'thumbnail': thumbnail
|
||||
'thumbnails': thumbnails,
|
||||
}
|
||||
|
||||
@@ -141,6 +141,10 @@ class ViewLiftIE(ViewLiftBaseIE):
|
||||
}, {
|
||||
'url': 'http://www.kesari.tv/news/video/1461919076414',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Was once Kaltura embed
|
||||
'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -20,18 +20,24 @@ class YandexMusicBaseIE(InfoExtractor):
|
||||
error = response.get('error')
|
||||
if error:
|
||||
raise ExtractorError(error, expected=True)
|
||||
if response.get('type') == 'captcha' or 'captcha' in response:
|
||||
YandexMusicBaseIE._raise_captcha()
|
||||
|
||||
@staticmethod
|
||||
def _raise_captcha():
|
||||
raise ExtractorError(
|
||||
'YandexMusic has considered youtube-dl requests automated and '
|
||||
'asks you to solve a CAPTCHA. You can either wait for some '
|
||||
'time until unblocked and optionally use --sleep-interval '
|
||||
'in future or alternatively you can go to https://music.yandex.ru/ '
|
||||
'solve CAPTCHA, then export cookies and pass cookie file to '
|
||||
'youtube-dl with --cookies',
|
||||
expected=True)
|
||||
|
||||
def _download_webpage(self, *args, **kwargs):
|
||||
webpage = super(YandexMusicBaseIE, self)._download_webpage(*args, **kwargs)
|
||||
if 'Нам очень жаль, но запросы, поступившие с вашего IP-адреса, похожи на автоматические.' in webpage:
|
||||
raise ExtractorError(
|
||||
'YandexMusic has considered youtube-dl requests automated and '
|
||||
'asks you to solve a CAPTCHA. You can either wait for some '
|
||||
'time until unblocked and optionally use --sleep-interval '
|
||||
'in future or alternatively you can go to https://music.yandex.ru/ '
|
||||
'solve CAPTCHA, then export cookies and pass cookie file to '
|
||||
'youtube-dl with --cookies',
|
||||
expected=True)
|
||||
self._raise_captcha()
|
||||
return webpage
|
||||
|
||||
def _download_json(self, *args, **kwargs):
|
||||
|
||||
@@ -395,8 +395,8 @@ def parseOpts(overrideArguments=None):
|
||||
|
||||
downloader = optparse.OptionGroup(parser, 'Download Options')
|
||||
downloader.add_option(
|
||||
'-r', '--rate-limit',
|
||||
dest='ratelimit', metavar='LIMIT',
|
||||
'-r', '--limit-rate', '--rate-limit',
|
||||
dest='ratelimit', metavar='RATE',
|
||||
help='Maximum download rate in bytes per second (e.g. 50K or 4.2M)')
|
||||
downloader.add_option(
|
||||
'-R', '--retries',
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2016.05.30'
|
||||
__version__ = '2016.06.02'
|
||||
|
||||
Reference in New Issue
Block a user