summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2013-12-09 04:49:32 +0100
committerPhilipp Hagemeister <[email protected]>2013-12-09 04:49:32 +0100
commitffa8f0df0a878463078467709f615b1e57c61ec1 (patch)
treeca1d84977f876fcc72e6989cd4de60bc4f834167
parent693b8b2d310e119417787e7b06d1e1832d16f05d (diff)
parent0a688bc0b28c970e9af965b3fa0c7927507eeb97 (diff)
downloadyoutube-dl-ffa8f0df0a878463078467709f615b1e57c61ec1.tar.gz
youtube-dl-ffa8f0df0a878463078467709f615b1e57c61ec1.zip
Merge remote-tracking branch 'jaimeMF/yt-toplists'
-rw-r--r--test/test_youtube_lists.py8
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/youtube.py35
3 files changed, 44 insertions, 0 deletions
diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py
index 95f07d129..33db09f43 100644
--- a/test/test_youtube_lists.py
+++ b/test/test_youtube_lists.py
@@ -15,6 +15,7 @@ from youtube_dl.extractor import (
YoutubeIE,
YoutubeChannelIE,
YoutubeShowIE,
+ YoutubeTopListIE,
)
@@ -116,5 +117,12 @@ class TestYoutubeLists(unittest.TestCase):
original_video = entries[0]
self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
+ def test_youtube_toplist(self):
+ dl = FakeYDL()
+ ie = YoutubeTopListIE(dl)
+ result = ie.extract('yttoplist:music:Top Tracks')
+ entries = result['entries']
+ self.assertTrue(len(entries) >= 9)
+
if __name__ == '__main__':
unittest.main()
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 2b78cc84d..3f740baa1 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -211,6 +211,7 @@ from .youtube import (
YoutubeWatchLaterIE,
YoutubeFavouritesIE,
YoutubeHistoryIE,
+ YoutubeTopListIE,
)
from .zdf import ZDFIE
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 7f7508c74..874429b78 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -1572,6 +1572,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
if playlist_id.startswith('RD'):
# Mixes require a custom extraction process
return self._extract_mix(playlist_id)
+ if playlist_id.startswith('TL'):
+ raise ExtractorError(u'For downloading YouTube.com top lists, use '
+ u'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
# Extract the video ids from the playlist pages
ids = []
@@ -1594,6 +1597,38 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
return self.playlist_result(url_results, playlist_id, playlist_title)
+class YoutubeTopListIE(YoutubePlaylistIE):
+ IE_NAME = u'youtube:toplist'
+ IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"'
+ u' (Example: "yttoplist:music:Top Tracks")')
+ _VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ channel = mobj.group('chann')
+ title = mobj.group('title')
+ query = compat_urllib_parse.urlencode({'title': title})
+ playlist_re = 'href="([^"]+?%s[^"]+?)"' % re.escape(query)
+ channel_page = self._download_webpage('https://www.youtube.com/%s' % channel, title)
+ link = self._html_search_regex(playlist_re, channel_page, u'list')
+ url = compat_urlparse.urljoin('https://www.youtube.com/', link)
+
+ video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"'
+ ids = []
+ # sometimes the webpage doesn't contain the videos
+ # retry until we get them
+ for i in itertools.count(0):
+ msg = u'Downloading Youtube mix'
+ if i > 0:
+ msg += ', retry #%d' % i
+ webpage = self._download_webpage(url, title, msg)
+ ids = orderedSet(re.findall(video_re, webpage))
+ if ids:
+ break
+ url_results = self._ids_to_results(ids)
+ return self.playlist_result(url_results, playlist_title=title)
+
+
class YoutubeChannelIE(InfoExtractor):
IE_DESC = u'YouTube.com channels'
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"