aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--test/test_playlists.py12
-rw-r--r--youtube_dl/extractor/__init__.py5
-rw-r--r--youtube_dl/extractor/imdb.py29
3 files changed, 44 insertions, 2 deletions
diff --git a/test/test_playlists.py b/test/test_playlists.py
index 1b7b4e3d8..9d522b357 100644
--- a/test/test_playlists.py
+++ b/test/test_playlists.py
@@ -28,7 +28,8 @@ from youtube_dl.extractor import (
BandcampAlbumIE,
SmotriCommunityIE,
SmotriUserIE,
- IviCompilationIE
+ IviCompilationIE,
+ ImdbListIE,
)
@@ -187,6 +188,15 @@ class TestPlaylists(unittest.TestCase):
self.assertEqual(result['id'], u'dezhurnyi_angel/season2')
self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012) 2 сезон')
self.assertTrue(len(result['entries']) >= 20)
+
+ def test_imdb_list(self):
+ dl = FakeYDL()
+ ie = ImdbListIE(dl)
+ result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'sMjedvGDd8U')
+ self.assertEqual(result['title'], u'Animated and Family Films')
+ self.assertTrue(len(result['entries']) >= 48)
if __name__ == '__main__':
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 1e8fd1f8e..5319a9292 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -80,7 +80,10 @@ from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ign import IGNIE, OneUPIE
-from .imdb import ImdbIE
+from .imdb import (
+ ImdbIE,
+ ImdbListIE
+)
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index e5332cce8..16926b4d3 100644
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -55,3 +55,32 @@ class ImdbIE(InfoExtractor):
'description': descr,
'thumbnail': format_info['slate'],
}
+
+class ImdbListIE(InfoExtractor):
+ IE_NAME = u'imdb:list'
+ IE_DESC = u'Internet Movie Database lists'
+ _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ list_id = mobj.group('id')
+
+ # RSS XML is sometimes malformed
+ rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, u'Downloading list RSS')
+ list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, u'list title')
+
+ # Export is independent of actual author_id, but returns 404 if no author_id is provided.
+ # However, passing dummy author_id seems to be enough.
+ csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
+ list_id, u'Downloading list CSV')
+
+ entries = []
+ for item in csv.split('\n')[1:]:
+ cols = item.split(',')
+ if len(cols) < 2:
+ continue
+ item_id = cols[1][1:-1]
+ if item_id.startswith('vi'):
+ entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
+
+ return self.playlist_result(entries, list_id, list_title) \ No newline at end of file