mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 02:42:30 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[youtube] Extract base for entry list extractors and support multi page lists of playlists

Browse Source
This commit is contained in:
Sergey M․ 2015-11-22 05:01:01 +06:00
parent 82c4d7b0ce
commit 061a75edd6
1 changed files with 17 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/youtube.py
View File

@ -178,15 +178,13 @@ def _real_initialize(self):
return return
class YoutubePlaylistBaseInfoExtractor(InfoExtractor): class YoutubeEntryListBaseInfoExtractor(InfoExtractor):
# Extract the video ids from the playlist pages # Extract entries from page with "Load more" button
def _entries(self, page, playlist_id): def _entries(self, page, playlist_id):
more_widget_html = content_html = page more_widget_html = content_html = page
for page_num in itertools.count(1): for page_num in itertools.count(1):
for video_id, video_title in self.extract_videos_from_page(content_html): for entry in self._process_page(content_html):
yield self.url_result( yield entry
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj: if not mobj:
@ -203,6 +201,12 @@ def _entries(self, page, playlist_id):
break break
more_widget_html = more['load_more_widget_html'] more_widget_html = more['load_more_widget_html']
class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
def _process_page(self, content):
for video_id, video_title in self.extract_videos_from_page(content):
yield self.url_result(video_id, 'Youtube', video_id, video_title)
def extract_videos_from_page(self, page): def extract_videos_from_page(self, page):
ids_in_page = [] ids_in_page = []
titles_in_page = [] titles_in_page = []
@ -224,15 +228,17 @@ def extract_videos_from_page(self, page):
return zip(ids_in_page, titles_in_page) return zip(ids_in_page, titles_in_page)
class YoutubePlaylistsBaseInfoExtractor(InfoExtractor): class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
def _process_page(self, content):
for playlist_id in re.findall(r'href="/?playlist\?list=(.+?)"', content):
yield self.url_result(
'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result(compat_urlparse.urljoin(url, playlist), 'YoutubePlaylist')
for playlist in re.findall(r'href="(/playlist\?list=.+?)"', webpage)]
title = self._og_search_title(webpage, fatal=False) title = self._og_search_title(webpage, fatal=False)
return self.playlist_result(entries, playlist_id, title) return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
class YoutubeIE(YoutubeBaseInfoExtractor): class YoutubeIE(YoutubeBaseInfoExtractor):