diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-09-09 10:33:12 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-09-09 10:33:12 +0200 |
| commit | 8963d9c2661b7de8832b7afcf1cdbc197275d8e3 (patch) | |
| tree | 3ce44ff77fb188ccc3ef86b2a7ecdaf8b13b7fc4 | |
| parent | 890f62e86805c9eed8444450a209f894bbd74e7b (diff) | |
[youtube] Modify the regex to match ids of length 11 (fixes #1396)
In urls like http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930 you can't split the query string and ids always have that length.
| -rw-r--r-- | test/test_all_urls.py | 11 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 2 |
2 files changed, 8 insertions, 5 deletions
diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 5d8d93e0e..99fc7bd28 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -72,10 +72,13 @@ class TestAllURLsMatching(unittest.TestCase): self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361")) 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') - self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch_popup?v=BaW_jenozKc'), 'BaW_jenozKc') + assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id) + assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc') + assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc') + assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc') + assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc') + assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc') + assertExtractId('BaW_jenozKc', 'BaW_jenozKc') def test_no_duplicates(self): ies = gen_extractors() diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index bad15cb44..6a8351293 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -150,7 +150,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): |youtu\.be/ # just youtu.be/xxxx ) )? # all until now is optional -> you can pass the naked ID - ([0-9A-Za-z_-]+) # here is it! the YouTube video ID + ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID (?(1).+)? # if we found the ID, everything can follow $""" _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |