Allow ampersand right after ? in youtube URLs (Closes #602)

This commit is contained in:
Philipp Hagemeister 2012-12-27 05:31:36 +01:00
parent d0d4f277da
commit 3bb6165927
2 changed files with 19 additions and 11 deletions

View file

@ -9,8 +9,8 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE
class TestYoutubePlaylistMatching(unittest.TestCase): class TestAllURLsMatching(unittest.TestCase):
def test_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'PL63F0C78739B09958'))
self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M')) self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M'))
@ -18,5 +18,10 @@ class TestYoutubePlaylistMatching(unittest.TestCase):
def test_youtube_matching(self): def test_youtube_matching(self):
self.assertTrue(YoutubeIE().suitable(u'PLtS2H6bU1M')) self.assertTrue(YoutubeIE().suitable(u'PLtS2H6bU1M'))
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('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

View file

@ -120,7 +120,7 @@ class YoutubeIE(InfoExtractor):
|(?: # or the v= param in all its forms |(?: # or the v= param in all its forms
(?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #! (?:\?|\#!?) # the params delimiter ? or # or #!
(?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v= v=
) )
)? # optional -> youtube.com/xxxx is OK )? # optional -> youtube.com/xxxx is OK
@ -325,22 +325,25 @@ class YoutubeIE(InfoExtractor):
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
return return
def _real_extract(self, url): def _extract_id(self, url):
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
# Extract video id from URL
mobj = re.match(self._VALID_URL, url, re.VERBOSE) mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return return
video_id = mobj.group(2) video_id = mobj.group(2)
return video_id
def _real_extract(self, url):
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self._extract_id(url)
# Get video webpage # Get video webpage
self.report_video_webpage_download(video_id) self.report_video_webpage_download(video_id)
request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
request = compat_urllib_request.Request(url)
try: try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read() video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: