From aab74fa10655213c24c6f38a5b0c6b18049e737a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 20 Mar 2014 16:33:23 +0100 Subject: [PATCH] [ted] Simplify embed code (#2587) --- youtube_dl/extractor/generic.py | 12 ++++++++++++ youtube_dl/extractor/ted.py | 11 +++++++---- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 273a3e282..8065b5611 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -159,6 +159,18 @@ class GenericIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + }, + # Embedded TED video + { + 'url': 'http://en.support.wordpress.com/videos/ted-talks/', + 'md5': 'deeeabcc1085eb2ba205474e7235a3d5', + 'info_dict': { + 'id': '981', + 'ext': 'mp4', + 'title': 'My web playroom', + 'uploader': 'Ze Frank', + 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b', + } } ] diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index aab026936..ad1a46c33 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -11,7 +11,9 @@ class TEDIE(SubtitlesInfoExtractor): - _VALID_URL = r'''(?x)http://(?Pwww|embed)\.ted\.com/ + _VALID_URL = r'''(?x) + (?Phttps?://) + (?Pwww|embed)(?P\.ted\.com/ ( (?Pplaylists(?:/\d+)?) # We have a playlist | @@ -19,6 +21,7 @@ class TEDIE(SubtitlesInfoExtractor): ) (/lang/(.*?))? # The url may contain the language /(?P\w+) # Here goes the name and then ".html" + .*)$ ''' _TEST = { 'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html', @@ -48,9 +51,9 @@ def _extract_info(self, webpage): 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 + if m.group('type') == 'embed': + desktop_url = m.group('proto') + 'www' + m.group('urlmain') + return self.url_result(desktop_url, 'TED') name = m.group('name') if m.group('type_talk'): return self._talk_info(url, name)