Merge branch 'master' of github.com:rg3/youtube-dl

This commit is contained in:
Philipp Hagemeister 2013-09-07 22:28:54 +02:00
commit a27a2470cd
6 changed files with 92 additions and 15 deletions

View File

@ -21,14 +21,15 @@ def assertMatch(self, url, ie_list):
self.assertEqual(self.matching_ies(url), ie_list)
def test_youtube_playlist_matching(self):
self.assertTrue(YoutubePlaylistIE.suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
self.assertTrue(YoutubePlaylistIE.suitable(u'UUBABnxM4Ar9ten8Mdjj1j0Q')) #585
self.assertTrue(YoutubePlaylistIE.suitable(u'PL63F0C78739B09958'))
self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q'))
self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC'))
self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
self.assertFalse(YoutubePlaylistIE.suitable(u'PLtS2H6bU1M'))
assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
assertPlaylist(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist(u'UUBABnxM4Ar9ten8Mdjj1j0Q') #585
assertPlaylist(u'PL63F0C78739B09958')
assertPlaylist(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
assertPlaylist(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
@ -37,13 +38,23 @@ def test_youtube_matching(self):
self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
def test_youtube_channel_matching(self):
self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM'))
self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec'))
self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos'))
assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
def test_youtube_user_matching(self):
self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
def test_youtube_feeds(self):
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
def test_youtube_show_matching(self):
self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
def test_justin_tv_channelid_matching(self):
self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))

View File

@ -52,6 +52,7 @@
from .liveleak import LiveLeakIE
from .livestream import LivestreamIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mit import TechTVMITIE, MITIE
from .mixcloud import MixcloudIE
from .mtv import MTVIE

View File

@ -14,7 +14,7 @@
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
IE_NAME = u'dailymotion'
_TEST = {
u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
@ -33,6 +33,7 @@ def _real_extract(self, url):
video_id = mobj.group(1).split('_')[0].split('?')[0]
video_extension = 'mp4'
url = 'http://www.dailymotion.com/video/%s' % video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)

View File

@ -109,6 +109,11 @@ def http_error_405(self, req, fp, code, msg, headers):
return new_url
def _real_extract(self, url):
parsed_url = compat_urlparse.urlparse(url)
if not parsed_url.scheme:
self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
return self.url_result('http://' + url)
try:
new_url = self._test_redirect(url)
if new_url:

View File

@ -0,0 +1,55 @@
import re
import xml.etree.ElementTree
import operator
from .common import InfoExtractor
class MetacriticIE(InfoExtractor):
_VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)'
_TEST = {
u'url': u'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',
u'file': u'3698222.mp4',
u'info_dict': {
u'title': u'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors',
u'description': u'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.',
u'duration': 221,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
# The xml is not well formatted, there are raw '&'
info_xml = self._download_webpage('http://www.metacritic.com/video_data?video=' + video_id,
video_id, u'Downloading info xml').replace('&', '&amp;')
info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id)
formats = []
for videoFile in clip.findall('httpURI/videoFile'):
rate_str = videoFile.find('rate').text
video_url = videoFile.find('filePath').text
formats.append({
'url': video_url,
'ext': 'mp4',
'format_id': rate_str,
'rate': int(rate_str),
})
formats.sort(key=operator.itemgetter('rate'))
description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>',
webpage, u'description', flags=re.DOTALL)
info = {
'id': video_id,
'title': clip.find('title').text,
'formats': formats,
'description': description,
'duration': int(clip.find('duration').text),
}
# TODO: Remove when #980 has been merged
info.update(formats[-1])
return info

View File

@ -386,7 +386,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
if YoutubePlaylistIE.suitable(url) or YoutubeSubscriptionsIE.suitable(url): return False
if YoutubePlaylistIE.suitable(url): return False
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_video_webpage_download(self, video_id):
@ -1015,14 +1015,18 @@ def _real_extract(self, url):
class YoutubeUserIE(InfoExtractor):
IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)([A-Za-z0-9_-]+)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)(?!feed/)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_GDATA_PAGE_SIZE = 50
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json'
IE_NAME = u'youtube:user'
@classmethod
def suitable(cls, url):
if YoutubeIE.suitable(url): return False
# Don't return True if the url can be extracted with other youtube
# extractor, the regex would is too permissive and it would match.
other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls)
if any(ie.suitable(url) for ie in other_ies): return False
else: return super(YoutubeUserIE, cls).suitable(url)
def _real_extract(self, url):