projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
82c4d7b
)
[youtube] Extract base for entry list extractors and support multi page lists of...
author
Sergey M․
<dstftw@gmail.com>
Sat, 21 Nov 2015 23:01:01 +0000
(
05:01
+0600)
committer
Sergey M․
<dstftw@gmail.com>
Sat, 21 Nov 2015 23:01:01 +0000
(
05:01
+0600)
youtube_dl/extractor/youtube.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/youtube.py
b/youtube_dl/extractor/youtube.py
index c56f8a0a248a521902246fe6b1032762a435ba1f..8352ad1dae46b68559409d05e27865b023ca9d44 100644
(file)
--- a/
youtube_dl/extractor/youtube.py
+++ b/
youtube_dl/extractor/youtube.py
@@
-178,15
+178,13
@@
class YoutubeBaseInfoExtractor(InfoExtractor):
return
return
-class Youtube
Playl
istBaseInfoExtractor(InfoExtractor):
- # Extract
the video ids from the playlist pages
+class Youtube
EntryL
istBaseInfoExtractor(InfoExtractor):
+ # Extract
entries from page with "Load more" button
def _entries(self, page, playlist_id):
more_widget_html = content_html = page
for page_num in itertools.count(1):
def _entries(self, page, playlist_id):
more_widget_html = content_html = page
for page_num in itertools.count(1):
- for video_id, video_title in self.extract_videos_from_page(content_html):
- yield self.url_result(
- video_id, 'Youtube', video_id=video_id,
- video_title=video_title)
+ for entry in self._process_page(content_html):
+ yield entry
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
@@
-203,6
+201,12
@@
class YoutubePlaylistBaseInfoExtractor(InfoExtractor):
break
more_widget_html = more['load_more_widget_html']
break
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):
ids_in_page = []
titles_in_page = []
def extract_videos_from_page(self, page):
ids_in_page = []
titles_in_page = []
@@
-224,15
+228,17
@@
class YoutubePlaylistBaseInfoExtractor(InfoExtractor):
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):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
def _real_extract(self, url):
playlist_id = self._match_id(url)
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):