R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Generic/VimeoIE: Return a playlist of all vimeo iframes/embeds (try2)

Browse Source 
Vimeo extraction logic is restricted to the first video only, even if
a page has multiple videos:

youtube-dl http://www.theguardian.com/environment/2015/jun/10/climate-change-has-left-us-exposed-in-arctic-say-military-experts --get-title
WARNING: Falling back on generic information extractor.
The Climate 25: Sherri Goodman

After patch:

youtube-dl http://www.theguardian.com/environment/2015/jun/10/climate-change-has-left-us-exposed-in-arctic-say-military-experts --get-title
WARNING: Falling back on generic information extractor.
The Climate 25: Sherri Goodman
The Climate 25: David Titley
The Climate 25: Steve Cheney
The Climate 25: General Charles Jacoby
The Climate 25: Henry Paulson
This commit is contained in:
fnord 2015-06-23 02:13:26 -05:00
parent 255f5694aa
commit 073741b132
2 changed files with 10 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
youtube_dl/extractor/generic.py
View File

@ -1124,9 +1124,9 @@ class GenericIE(InfoExtractor):
if matches:
return _playlist_from_matches(matches, ie='RtlNl')
vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
if vimeo_url is not None:
return self.url_result(vimeo_url)
vimeo_urls = VimeoIE._extract_vimeo_urls(url, webpage)
if vimeo_urls is not None:
return _playlist_from_matches(vimeo_urls, ie='Vimeo')
# Look for embedded YouTube player
matches = re.findall(r'''(?x)

18
youtube_dl/extractor/vimeo.py
View File

@ -175,19 +175,15 @@ class VimeoIE(VimeoBaseInfoExtractor):
]
@staticmethod
def _extract_vimeo_url(url, webpage):
def _extract_vimeo_urls(url, webpage):
# Look for embedded (iframe) Vimeo player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
mobj = re.findall(
r'<(?:iframe|embed)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:player\.vimeo\.com/video/|(?:www\.)?vimeo\.com/moogaloop\.swf).+?)\1', webpage)
if mobj:
player_url = unescapeHTML(mobj.group('url'))
surl = smuggle_url(player_url, {'Referer': url})
return surl
# Look for embedded (swf embed) Vimeo player
mobj = re.search(
r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
if mobj:
return mobj.group(1)
return map(
lambda m: smuggle_url(unescapeHTML(m[1]), {'Referer': url}),
mobj
)
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)