From 3bb6165927c277c3af73d5ef1ffb6ce9ea663d10 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 27 Dec 2012 05:31:36 +0100 Subject: [PATCH] Allow ampersand right after ? in youtube URLs (Closes #602) --- ...utube_playlist_ids.py => test_all_urls.py} | 9 ++++++-- youtube_dl/InfoExtractors.py | 21 +++++++++++-------- 2 files changed, 19 insertions(+), 11 deletions(-) rename test/{test_youtube_playlist_ids.py => test_all_urls.py} (55%) diff --git a/test/test_youtube_playlist_ids.py b/test/test_all_urls.py similarity index 55% rename from test/test_youtube_playlist_ids.py rename to test/test_all_urls.py index 2eeb3216c..06de8e7b8 100644 --- a/test/test_youtube_playlist_ids.py +++ b/test/test_all_urls.py @@ -9,8 +9,8 @@ from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE -class TestYoutubePlaylistMatching(unittest.TestCase): - def test_playlist_matching(self): +class TestAllURLsMatching(unittest.TestCase): + def test_youtube_playlist_matching(self): self.assertTrue(YoutubePlaylistIE().suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')) self.assertTrue(YoutubePlaylistIE().suitable(u'PL63F0C78739B09958')) self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M')) @@ -18,5 +18,10 @@ def test_playlist_matching(self): def test_youtube_matching(self): 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__': unittest.main() diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 890ff7378..e3cf7e115 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -120,7 +120,7 @@ class YoutubeIE(InfoExtractor): |(?: # or the v= param in all its forms (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! - (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) + (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) v= ) )? # optional -> youtube.com/xxxx is OK @@ -325,22 +325,25 @@ def _real_initialize(self): self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) return - 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('/') - - # Extract video id from URL + def _extract_id(self, url): mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return 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 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: video_webpage_bytes = compat_urllib_request.urlopen(request).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: