nhyatt/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2025-06-30 11:02:51 -05:00
Code Issues Projects Releases Wiki Activity

[brightcove:legacy] Improve embeds detection (closes #11523)

Browse Source
This commit is contained in:
Sergey M․
2016-12-24 22:46:27 +07:00
parent 264e77c406
commit 53a664edf4
2 changed files with 29 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
youtube_dl/extractor/brightcove.py
View File

@ -232,13 +232,16 @@ class BrightcoveLegacyIE(InfoExtractor):
"""Return a list of all Brightcove URLs from the webpage """
url_m = re.search(
r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
webpage)
r'''(?x)
<meta\s+
(?:property|itemprop)=([\'"])(?:og:video|embedURL)\1[^>]+
content=([\'"])(?P<url>https?://(?:secure|c)\.brightcove.com/(?:(?!\2).)+)\2
''', webpage)
if url_m:
url = unescapeHTML(url_m.group(1))
url = unescapeHTML(url_m.group('url'))
# Some sites don't add it, we can't download with this url, for example:
# http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
if 'playerKey' in url or 'videoId' in url:
if 'playerKey' in url or 'videoId' in url or 'idVideo' in url:
return [url]
matches = re.findall(
@ -259,7 +262,7 @@ class BrightcoveLegacyIE(InfoExtractor):
url, smuggled_data = unsmuggle_url(url, {})
# Change the 'videoId' and others field to '@videoPlayer'
url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
url = re.sub(r'(?<=[?&])(videoI(d|D)|idVideo|bctid)', '%40videoPlayer', url)
# Change bckey (used by bcove.me urls) to playerKey
url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
mobj = re.match(self._VALID_URL, url)