diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-01-28 03:29:10 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-01-28 03:29:10 +0100 |
| commit | c1e60cc2bf4d0130dac154e9014913e7d63d25ff (patch) | |
| tree | dc9d5354315bcb4fcff3c44d814a2d2949c06ae2 | |
| parent | 117bec936c18e9c3b1d467c8710075ed4376e254 (diff) | |
| parent | 98669ed79c10bbcfc5678a520de98df79ca6b1b4 (diff) | |
Merge remote-tracking branch 'dstftw/master'
| -rw-r--r-- | test/test_playlists.py | 8 | ||||
| -rw-r--r-- | youtube_dl/extractor/imdb.py | 5 |
2 files changed, 5 insertions, 8 deletions
diff --git a/test/test_playlists.py b/test/test_playlists.py index 5eeba091e..a8f4a49f4 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -195,11 +195,11 @@ class TestPlaylists(unittest.TestCase): def test_imdb_list(self): dl = FakeYDL() ie = ImdbListIE(dl) - result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U') + result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0') self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'sMjedvGDd8U') - self.assertEqual(result['title'], 'Animated and Family Films') - self.assertTrue(len(result['entries']) >= 48) + self.assertEqual(result['id'], 'JFs9NWw6XI0') + self.assertEqual(result['title'], 'March 23, 2012 Releases') + self.assertEqual(len(result['entries']), 7) def test_khanacademy_topic(self): dl = FakeYDL() diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 1763af020..7cee505c0 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -69,12 +69,9 @@ class ImdbListIE(InfoExtractor): list_id = mobj.group('id') webpage = self._download_webpage(url, list_id) - list_code = self._search_regex( - r'(?s)<div\s+class="list\sdetail">(.*?)class="see-more"', - webpage, 'list code') entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb') - for m in re.findall(r'href="(/video/imdb/vi[^"]+)"', webpage)] + for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)] list_title = self._html_search_regex( r'<h1 class="header">(.*?)</h1>', webpage, 'list title') |