From b4e1576aee7cf18f5842714c87985ae0b72f1546 Mon Sep 17 00:00:00 2001
From: fnord <fnord@fnord.mobi>
Date: Sat, 13 Jun 2015 06:09:44 -0500
Subject: [PATCH 1/2] Brightcove extractor: support customBC.createVideo(...);
method found in http://www.americanbar.org/groups/family_law.html and
http://america.aljazeera.com/watch/shows/america-tonight/2015/6/exclusive-hunting-isil-with-the-pkk.html
---
youtube_dl/extractor/brightcove.py | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index c1d4320e1..20a6ed965 100644
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -188,7 +188,19 @@ class BrightcoveIE(InfoExtractor):
[^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
).+?>\s*</object>''',
webpage)
- return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+ 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
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
From af9cdee9cba610aa3924f90a8a3fcd7dd43c65eb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sat, 13 Jun 2015 19:53:32 +0600
Subject: [PATCH 2/2] [brightcove] Improve and generalize brightcove URL
extraction from JS
---
youtube_dl/extractor/brightcove.py | 35 +++++++++++++++++++++---------
1 file changed, 25 insertions(+), 10 deletions(-)
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index 20a6ed965..d768f99e6 100644
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -156,6 +156,28 @@ class BrightcoveIE(InfoExtractor):
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 @@ class BrightcoveIE(InfoExtractor):
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, {})