etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[vimeo:channel] Improve playlist extraction

Browse source
This commit is contained in:
Sergey M․ 2016-06-23 01:28:36 +07:00
parent dfc8f46e1c
commit c8e3e0974b
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 21 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/vimeo.py
View file

@ -146,7 +146,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
\.
)?
vimeo(?P<pro>pro)?\.com/
(?!channels/[^/?#]+/?(?:$|[?#])|[^/]+/review/|(?:album|ondemand)/)
(?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)?
(?:
(?:
@ -314,6 +314,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
'only_matching': True,
},
{
'url': 'https://vimeo.com/album/2632481/video/79010983',
'only_matching': True,
},
{
# source file returns 403: Forbidden
'url': 'https://vimeo.com/7809605',
@ -651,8 +655,21 @@ def _title_and_entries(self, list_id, base_url):
webpage = self._login_list_password(page_url, list_id, webpage)
yield self._extract_list_title(webpage)
for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo', video_id=video_id)
# Try extracting href first since not all videos are available via
# short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
clips = re.findall(
r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage)
if clips:
for video_id, video_url in clips:
yield self.url_result(
compat_urlparse.urljoin(base_url, video_url),
VimeoIE.ie_key(), video_id=video_id)
# More relaxed fallback
else:
for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
yield self.url_result(
'https://vimeo.com/%s' % video_id,
VimeoIE.ie_key(), video_id=video_id)
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
@ -689,7 +706,7 @@ def _real_extract(self, url):
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = 'vimeo:album'
_VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
_VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)/?(?:$|[?#])'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
_TESTS = [{
'url': 'https://vimeo.com/album/2632481',