Fixed downloading of unrelated videos when downloading a YouTube playlist

This commit is contained in:
cryzed 2012-03-09 22:05:35 +01:00
parent 9c228928b6
commit 7151f63a5f
1 changed files with 21 additions and 16 deletions

View File

@ -2519,7 +2519,7 @@ class YoutubePlaylistIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None _youtube_ie = None
IE_NAME = u'youtube:playlist' IE_NAME = u'youtube:playlist'
@ -2571,7 +2571,8 @@ class YoutubePlaylistIE(InfoExtractor):
# Extract video identifiers # Extract video identifiers
ids_in_page = [] ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page): video_indicator = self._VIDEO_INDICATOR_TEMPLATE % playlist_id
for mobj in re.finditer(video_indicator, page):
if mobj.group(1) not in ids_in_page: if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1)) ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page) video_ids.extend(ids_in_page)
@ -2582,7 +2583,11 @@ class YoutubePlaylistIE(InfoExtractor):
playliststart = self._downloader.params.get('playliststart', 1) - 1 playliststart = self._downloader.params.get('playliststart', 1) - 1
playlistend = self._downloader.params.get('playlistend', -1) playlistend = self._downloader.params.get('playlistend', -1)
video_ids = video_ids[playliststart:playlistend]
if playlistend == -1:
video_ids = video_ids[playliststart:]
else:
video_ids = video_ids[playliststart:playlistend]
for id in video_ids: for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)