Merge remote-tracking branch 'anovicecodemonkey/TEDIEimprovements'

This commit is contained in:
Philipp Hagemeister 2014-03-20 16:24:34 +01:00
commit 2bd9efd4c2
2 changed files with 11 additions and 1 deletions

View File

@ -487,6 +487,13 @@ def _real_extract(self, url):
if mobj is None: if mobj is None:
# Broaden the search a little bit: JWPlayer JS loader # Broaden the search a little bit: JWPlayer JS loader
mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage) mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
# Look for embedded TED player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'TED')
if mobj is None: if mobj is None:
# Try to find twitter cards info # Try to find twitter cards info
mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)

View File

@ -11,7 +11,7 @@
class TEDIE(SubtitlesInfoExtractor): class TEDIE(SubtitlesInfoExtractor):
_VALID_URL = r'''(?x)http://www\.ted\.com/ _VALID_URL = r'''(?x)http://(?P<type>www|embed)\.ted\.com/
( (
(?P<type_playlist>playlists(?:/\d+)?) # We have a playlist (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist
| |
@ -48,6 +48,9 @@ def _extract_info(self, webpage):
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE) m = re.match(self._VALID_URL, url, re.VERBOSE)
if m.group('type') == 'embed': # if the _VALID_URL is an embed
desktop_url = re.sub("embed", "www", url)
return self.url_result(desktop_url, 'TED') # pass the desktop version to the extractor
name = m.group('name') name = m.group('name')
if m.group('type_talk'): if m.group('type_talk'):
return self._talk_info(url, name) return self._talk_info(url, name)