From 238755752f4f9169a1edda91067c8627afe19cce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 5 Aug 2015 23:07:52 +0600 Subject: [PATCH] [tudou] Extract player URL from the webpage --- youtube_dl/extractor/tudou.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 9b934cb57..84fe71aef 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -30,7 +30,7 @@ class TudouIE(InfoExtractor): }] _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' - + def _url_for_id(self, id, quality=None): info_url = "http://v2.tudou.com/f?id=" + str(id) if quality: @@ -56,6 +56,10 @@ class TudouIE(InfoExtractor): thumbnail_url = self._search_regex( r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) + player_url = self._search_regex( + r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']", + webpage, 'player URL', default=self._PLAYER_URL) + segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segments = json.loads(segs_json) # It looks like the keys are the arguments that have to be passed as @@ -79,7 +83,7 @@ class TudouIE(InfoExtractor): 'title': title, 'thumbnail': thumbnail_url, 'http_headers': { - 'Referer': self._PLAYER_URL, + 'Referer': player_url, }, } result.append(part_info)