fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Support multiple embedded YouTube URLs (Fixes #1787)

This commit is contained in:
Philipp Hagemeister 2013-11-18 13:28:26 +01:00
parent 83aa529330
commit 887c6acdf2
1 changed files with 17 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/generic.py
View File

@ -162,6 +162,16 @@ class GenericIE(InfoExtractor):
raise ExtractorError(u'Failed to download URL: %s' % url) raise ExtractorError(u'Failed to download URL: %s' % url)
self.report_extraction(video_id) self.report_extraction(video_id)
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
video_title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'video title', default=u'video', flags=re.DOTALL)
# Look for BrightCove: # Look for BrightCove:
bc_url = BrightcoveIE._extract_brightcove_url(webpage) bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if bc_url is not None: if bc_url is not None:
@ -177,11 +187,13 @@ class GenericIE(InfoExtractor):
return self.url_result(surl, 'Vimeo') return self.url_result(surl, 'Vimeo')
# Look for embedded YouTube player # Look for embedded YouTube player
mobj = re.search( matches = re.findall(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?youtube.com/embed/.+?)\1', webpage) r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube.com/embed/.+?)\1', webpage)
if mobj: if matches:
surl = unescapeHTML(mobj.group(u'url')) urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
return self.url_result(surl, 'Youtube') for tuppl in matches]
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for Bandcamp pages with custom domain # Look for Bandcamp pages with custom domain
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
@ -226,15 +238,6 @@ class GenericIE(InfoExtractor):
video_extension = os.path.splitext(video_id)[1][1:] video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0] video_id = os.path.splitext(video_id)[0]
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
video_title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'video title', default=u'video', flags=re.DOTALL)
# video uploader is domain name # video uploader is domain name
video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*', video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
url, u'video uploader') url, u'video uploader')