Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

[brightcove] Improve and generalize brightcove URL extraction from JS

Browse Source
This commit is contained in:
Sergey M․ 2015-06-13 19:53:32 +06:00
parent b4e1576aee
commit af9cdee9cb
1 changed files with 25 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
youtube_dl/extractor/brightcove.py
View File

@ -156,6 +156,28 @@ def find_param(name):
linkBase = find_param('linkBaseURL')
if linkBase is not None:
params['linkBaseURL'] = linkBase
return cls._make_brightcove_url(params)
@classmethod
def _build_brighcove_url_from_js(cls, object_js):
# The layout of JS is as follows:
# customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) {
# // build Brightcove <object /> XML
# }
m = re.search(
r'''(?x)customBC.\createVideo\(
.*? # skipping width and height
["\'](?P<playerID>\d+)["\']\s*,\s* # playerID
["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s* # playerKey begins with AQ and is 50 characters
# in length, however it's appended to itself
# in places, so truncate
["\'](?P<videoID>\d+)["\'] # @videoPlayer
''', object_js)
if m:
return cls._make_brightcove_url(m.groupdict())
@classmethod
def _make_brightcove_url(cls, params):
data = compat_urllib_parse.urlencode(params)
return cls._FEDERATED_URL_TEMPLATE % data
@ -191,16 +213,9 @@ def _extract_brightcove_urls(cls, webpage):
if matches:
return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
custombcs = re.findall(r'customBC.\createVideo\((.+?)\);',webpage)
if custombcs:
urls = []
for match in custombcs:
# brightcove playerkey begins with AQ and is 50 characters in length,
# however it's appended to itself in places, so truncate.
f = re.search(r'["\'](AQ[^"\']{48}).*?["\'](\d+)["\']', match)
if f:
urls.append('brightcove:playerKey='+f.group(1)+'&%40videoPlayer='+f.group(2))
return urls
return list(filter(None, [
cls._build_brighcove_url_from_js(custom_bc)
for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})