Modified Youtube video/playlist matching; fixes #668; fixes #585

This commit is contained in:
Filippo Valsorda 2013-02-26 19:02:31 +01:00
parent 6324fd1d74
commit 89de9eb125
3 changed files with 59 additions and 33 deletions

View File

@ -11,12 +11,18 @@ from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE
class TestAllURLsMatching(unittest.TestCase): class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self): def test_youtube_playlist_matching(self):
self.assertTrue(YoutubePlaylistIE().suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')) self.assertTrue(YoutubePlaylistIE.suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
self.assertTrue(YoutubePlaylistIE().suitable(u'PL63F0C78739B09958')) self.assertTrue(YoutubePlaylistIE.suitable(u'UUBABnxM4Ar9ten8Mdjj1j0Q')) #585
self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M')) 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'))
def test_youtube_matching(self): def test_youtube_matching(self):
self.assertTrue(YoutubeIE().suitable(u'PLtS2H6bU1M')) self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
def test_youtube_extract(self): def test_youtube_extract(self):
self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')

View File

@ -41,6 +41,18 @@ class TestYoutubeLists(unittest.TestCase):
self.assertEqual(map(lambda x: YoutubeIE()._extract_id(x[0]), DL.result), self.assertEqual(map(lambda x: YoutubeIE()._extract_id(x[0]), DL.result),
[ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE' ]) [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE' ])
#661
DL = FakeDownloader()
IE = YoutubePlaylistIE(DL)
IE.extract('PLMCmkNmxw6Z9eduM7BZjSEh7HiU543Ig0')
self.assertTrue(len(DL.result) > 20)
#673
DL = FakeDownloader()
IE = YoutubePlaylistIE(DL)
IE.extract('PLBB231211A4F62143')
self.assertTrue(len(DL.result) > 40)
def test_youtube_playlist_long(self): def test_youtube_playlist_long(self):
DL = FakeDownloader() DL = FakeDownloader()
IE = YoutubePlaylistIE(DL) IE = YoutubePlaylistIE(DL)
@ -48,6 +60,7 @@ class TestYoutubeLists(unittest.TestCase):
self.assertTrue(len(DL.result) >= 799) self.assertTrue(len(DL.result) >= 799)
def test_youtube_playlist_with_deleted(self): def test_youtube_playlist_with_deleted(self):
#651
DL = FakeDownloader() DL = FakeDownloader()
IE = YoutubePlaylistIE(DL) IE = YoutubePlaylistIE(DL)
IE.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') IE.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')

View File

@ -74,13 +74,15 @@ class InfoExtractor(object):
self._ready = False self._ready = False
self.set_downloader(downloader) self.set_downloader(downloader)
def suitable(self, url): @classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url) is not None return re.match(cls._VALID_URL, url) is not None
def working(self): @classmethod
def working(cls):
"""Getter method for _WORKING.""" """Getter method for _WORKING."""
return self._WORKING return cls._WORKING
def initialize(self): def initialize(self):
"""Initializes an instance (authentication, etc).""" """Initializes an instance (authentication, etc)."""
@ -137,7 +139,6 @@ class YoutubeIE(InfoExtractor):
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls (?:.*?\#/)? # handle anchor (#/) redirect urls
(?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID: (?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/ (?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms |(?: # or the v= param in all its forms
@ -189,9 +190,11 @@ class YoutubeIE(InfoExtractor):
} }
IE_NAME = u'youtube' IE_NAME = u'youtube'
def suitable(self, url): @classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None if YoutubePlaylistIE.suitable(url): return False
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self): def report_lang(self):
"""Report attempt to set language.""" """Report attempt to set language."""
@ -1668,17 +1671,17 @@ class YoutubePlaylistIE(InfoExtractor):
(?:\w+\.)? (?:\w+\.)?
youtube\.com/ youtube\.com/
(?: (?:
(?:course|view_play_list|my_playlists|artist|playlist) (?:course|view_play_list|my_playlists|artist|playlist|watch)
\? .*? (p|a|list)= \? (?:.*?&)*? (?:p|a|list)=
| user/.*?/user/ | user/.*?/user/
| p/ | p/
| user/.*?#[pg]/c/ | user/.*?#[pg]/c/
) )
(?:PL|EC)? ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
|PL|EC) .*
([0-9A-Za-z-_]{10,}) |
(?:/.*?/([0-9A-Za-z_-]+))? ((?:PL|EC|UU)[0-9A-Za-z-_]{10,})
.*""" )"""
_TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json' _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json'
_MAX_RESULTS = 50 _MAX_RESULTS = 50
IE_NAME = u'youtube:playlist' IE_NAME = u'youtube:playlist'
@ -1686,9 +1689,10 @@ class YoutubePlaylistIE(InfoExtractor):
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
def suitable(self, url): @classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_download_page(self, playlist_id, pagenum): def report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number.""" """Report attempt to download playlist page with given number."""
@ -1701,13 +1705,8 @@ class YoutubePlaylistIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid url: %s' % url) self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return return
# Single video case
if mobj.group(3) is not None:
self._downloader.download([mobj.group(3)])
return
# Download playlist videos from API # Download playlist videos from API
playlist_id = mobj.group(2) playlist_id = mobj.group(1) or mobj.group(2)
page_num = 1 page_num = 1
videos = [] videos = []
@ -1727,7 +1726,12 @@ class YoutubePlaylistIE(InfoExtractor):
self._downloader.trouble(u'ERROR: Invalid JSON in API response: ' + compat_str(err)) self._downloader.trouble(u'ERROR: Invalid JSON in API response: ' + compat_str(err))
return return
videos += [(entry['yt$position']['$t'], entry['content']['src']) for entry in response['feed']['entry']] if not 'feed' in response or not 'entry' in response['feed']:
self._downloader.trouble(u'ERROR: Got a malformed response from YouTube API')
return
videos += [ (entry['yt$position']['$t'], entry['content']['src'])
for entry in response['feed']['entry']
if 'content' in entry ]
if len(response['feed']['entry']) < self._MAX_RESULTS: if len(response['feed']['entry']) < self._MAX_RESULTS:
break break
@ -2313,9 +2317,10 @@ class ComedyCentralIE(InfoExtractor):
'400': '384x216', '400': '384x216',
} }
def suitable(self, url): @classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_extraction(self, episode_id): def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
@ -3628,9 +3633,10 @@ class SteamIE(InfoExtractor):
(?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
""" """
def suitable(self, url): @classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE) m = re.match(self._VALID_URL, url, re.VERBOSE)
@ -4004,9 +4010,10 @@ class TEDIE(InfoExtractor):
/(?P<name>\w+) # Here goes the name and then ".html" /(?P<name>\w+) # Here goes the name and then ".html"
''' '''
def suitable(self, url): @classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url): def _real_extract(self, url):
m=re.match(self._VALID_URL, url, re.VERBOSE) m=re.match(self._VALID_URL, url, re.VERBOSE)