diff options
author | Sergey M․ <dstftw@gmail.com> | 2016-10-06 23:22:52 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-10-06 23:22:52 +0700 |
commit | 09b9c45e242cb9e85beaa98b4783ec02065f1ec6 (patch) | |
tree | 33ef39857eadda05d4242e7225056a616579a548 | |
parent | 33898fb19c1af161c503ebce8f9a4774fecee45e (diff) |
[generic] Add support for multiple vimeo embeds (Closes #10862)
-rw-r--r-- | youtube_dl/extractor/generic.py | 6 | ||||
-rw-r--r-- | youtube_dl/extractor/vimeo.py | 36 | ||||
-rw-r--r-- | youtube_dl/extractor/vk.py | 2 |
3 files changed, 24 insertions, 20 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 9ea306e3a..8ef8fb5f4 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1754,9 +1754,9 @@ 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_urls(url, webpage) + if vimeo_urls: + return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key()) vid_me_embed_url = self._search_regex( r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]', diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 309a47bf0..ea8fc5908 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -355,23 +355,27 @@ class VimeoIE(VimeoBaseInfoExtractor): return smuggle_url(url, {'http_headers': {'Referer': referrer_url}}) @staticmethod - def _extract_vimeo_url(url, webpage): + def _extract_urls(url, webpage): + urls = [] # Look for embedded (iframe) Vimeo player - mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage) - if mobj: - player_url = unescapeHTML(mobj.group('url')) - return VimeoIE._smuggle_referrer(player_url, url) - # 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) - # Look more for non-standard embedded Vimeo player - mobj = re.search( - r'<video[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)(?P=q1)', webpage) - if mobj: - return mobj.group('url') + for mobj in re.finditer( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage): + urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url)) + PLAIN_EMBED_RE = ( + # Look for embedded (swf embed) Vimeo player + r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1', + # Look more for non-standard embedded Vimeo player + r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1', + ) + for embed_re in PLAIN_EMBED_RE: + for mobj in re.finditer(embed_re, webpage): + urls.append(mobj.group('url')) + return urls + + @staticmethod + def _extract_url(url, webpage): + urls = VimeoIE._extract_urls(url, webpage) + return urls[0] if urls else None def _verify_player_video_password(self, url, video_id): password = self._downloader.params.get('videopassword') diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index ac77bc623..df43ba867 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -341,7 +341,7 @@ class VKIE(VKBaseIE): if youtube_url: return self.url_result(youtube_url, 'Youtube') - vimeo_url = VimeoIE._extract_vimeo_url(url, info_page) + vimeo_url = VimeoIE._extract_url(url, info_page) if vimeo_url is not None: return self.url_result(vimeo_url) |