diff options
| author | Philipp Hagemeister <[email protected]> | 2014-03-20 16:24:34 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <[email protected]> | 2014-03-20 16:24:34 +0100 |
| commit | 2bd9efd4c2227a2a9a93e0f1d15ad8fa89d33867 (patch) | |
| tree | a43ce72a0a36d7336fee0e7eede4f89cab661bc3 | |
| parent | 39a743fb9baa74a5eb7b1e3af5a8bf0c5f93c096 (diff) | |
| parent | fc26023120375c1a5ecad248241770f20c60b01e (diff) | |
| download | youtube-dl-2bd9efd4c2227a2a9a93e0f1d15ad8fa89d33867.tar.gz youtube-dl-2bd9efd4c2227a2a9a93e0f1d15ad8fa89d33867.zip | |
Merge remote-tracking branch 'anovicecodemonkey/TEDIEimprovements'
| -rw-r--r-- | youtube_dl/extractor/generic.py | 7 | ||||
| -rw-r--r-- | youtube_dl/extractor/ted.py | 5 |
2 files changed, 11 insertions, 1 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5a4933146..273a3e282 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -487,6 +487,13 @@ class GenericIE(InfoExtractor): if mobj is None: # Broaden the search a little bit: JWPlayer JS loader 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: # Try to find twitter cards info mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 3968b718e..aab026936 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -11,7 +11,7 @@ from ..utils import ( 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 | @@ -48,6 +48,9 @@ class TEDIE(SubtitlesInfoExtractor): def _real_extract(self, url): 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') if m.group('type_talk'): return self._talk_info(url, name) |