etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
Code Issues Projects Releases Wiki Activity

[vk.com] Updated the extract_videos_from_page function with a much simpler 1-liner.

Browse source
This commit is contained in:
Will Sewell 2014-11-21 23:16:12 +00:00
parent 53d1cd1f77
commit e1e8b6897b
1 changed files with 3 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
youtube_dl/extractor/vk.py
View file

@ -11,7 +11,8 @@
compat_urllib_parse, compat_urllib_parse,
compat_str, compat_str,
unescapeHTML, unescapeHTML,
unified_strdate) unified_strdate,
orderedSet)
class VKIE(InfoExtractor): class VKIE(InfoExtractor):
@ -216,13 +217,6 @@ class VKUserVideosIE(InfoExtractor):
'playlist_mincount': 4, 'playlist_mincount': 4,
} }
def extract_videos_from_page(self, page):
ids_in_page = []
for mobj in re.finditer(r'href="/video([0-9_]+)"', page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
return ids_in_page
def _real_extract(self, url): def _real_extract(self, url):
# Extract page id # Extract page id
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -232,7 +226,7 @@ def _real_extract(self, url):
# Download page and get video ids # Download page and get video ids
page_id = mobj.group(1) page_id = mobj.group(1)
page = self._download_webpage(url, page_id) page = self._download_webpage(url, page_id)
video_ids = self.extract_videos_from_page(page) video_ids = orderedSet(m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
self._downloader.to_screen('[vk] User videos %s: Found %i videos' % (page_id, len(video_ids))) self._downloader.to_screen('[vk] User videos %s: Found %i videos' % (page_id, len(video_ids)))