commit f74e22ae280ac1680251350c4672abfeb2a047fe
parent 16c73c2e513829197c4af5ee62bde88b2b2272e4
Author: Gergely Imreh <imrehg@gmail.com>
Date: Mon, 31 Jan 2011 18:54:47 +0800
Enable artist playlists in YoutubePlaylistIE
Artist playlist pages have different format compared to user playlists,
thus more format checking is needed to construct the correct URL.
From the artist playlist this method downloads all listed below the
"Videos by [Artist Name]" header, plus usually there's one more
video on the side, titled "Youtube Mix for [Artist Name]", which
has a link format that currently cannot be distinguished from the other
videos in the list.
Diffstat:
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/youtube-dl b/youtube-dl
@@ -2096,8 +2096,8 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/|p/)([^&]+).*'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/)([^&]+).*'
+ _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
@@ -2125,13 +2125,19 @@ class YoutubePlaylistIE(InfoExtractor):
return
# Download playlist pages
- playlist_id = mobj.group(1)
+ # prefix is 'p' as default for playlists but there are other types that need extra care
+ playlist_prefix = mobj.group(1)
+ if playlist_prefix == 'a':
+ playlist_access = 'artist'
+ else:
+ playlist_access = 'view_play_list'
+ playlist_id = mobj.group(2)
video_ids = []
pagenum = 1
while True:
self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum))
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
