projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[extractor/common] Extract HTTP (possibly f4m) URLs from a .smil file
[youtube-dl]
/
youtube_dl
/
extractor
/
bloomberg.py
diff --git
a/youtube_dl/extractor/bloomberg.py
b/youtube_dl/extractor/bloomberg.py
index 25fb79e146b18f50962ba506d01560fbd845dbf2..4a88ccd13caf604f3ea892c6784d603434fb06ee 100644
(file)
--- a/
youtube_dl/extractor/bloomberg.py
+++ b/
youtube_dl/extractor/bloomberg.py
@@
-6,11
+6,11
@@
from .common import InfoExtractor
class BloombergIE(InfoExtractor):
class BloombergIE(InfoExtractor):
- _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<
name
>.+?)\.html'
+ _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<
id
>.+?)\.html'
_TEST = {
'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
_TEST = {
'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
- 'md5': '7bf08858ff7c203c870e8a6190e221e5',
+ # The md5 checksum changes
'info_dict': {
'id': 'qurhIVlJSB6hzkVi229d8g',
'ext': 'flv',
'info_dict': {
'id': 'qurhIVlJSB6hzkVi229d8g',
'ext': 'flv',
@@
-20,9
+20,9
@@
class BloombergIE(InfoExtractor):
}
def _real_extract(self, url):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- name = mobj.group('name')
+ name = self._match_id(url)
webpage = self._download_webpage(url, name)
webpage = self._download_webpage(url, name)
+
f4m_url = self._search_regex(
r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
'f4m url')
f4m_url = self._search_regex(
r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
'f4m url')
@@
-31,8
+31,7
@@
class BloombergIE(InfoExtractor):
return {
'id': name.split('-')[-1],
'title': title,
return {
'id': name.split('-')[-1],
'title': title,
- 'url': f4m_url,
- 'ext': 'flv',
+ 'formats': self._extract_f4m_formats(f4m_url, name),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}