diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-09-12 22:51:49 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-09-12 22:51:49 +0800 |
commit | 141ba36996f77a420df69903a59792f6f93ae314 (patch) | |
tree | 5a6c2604e203915f217d602b2528c9c2ded42288 /youtube_dl/extractor | |
parent | d434ca5448b62568e6c56c2e9ea83d10c9da196d (diff) |
[tudou] Modernize
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/tudou.py | 18 |
1 files changed, 6 insertions, 12 deletions
diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 68712cb4a..c9d80a7ef 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -2,9 +2,6 @@ from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor @@ -46,13 +43,10 @@ class TudouIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) - if m and m.group(1): - return { - '_type': 'url', - 'url': 'youku:' + m.group(1), - 'ie_key': 'Youku' - } + youku_vcode = self._search_regex( + r'vcode:\s*[\'"](.+?)[\'"]', webpage, 'youku vcode', default=None) + if youku_vcode: + return self.url_result('youku:' + youku_vcode, ie='Youku') title = self._search_regex( r",kw:\s*['\"](.+?)[\"']", webpage, 'title') @@ -63,8 +57,8 @@ class TudouIE(InfoExtractor): 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) + segments = self._parse_json(self._search_regex( + r'segs: \'(.*)\'', webpage, 'segments'), video_id) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher # Also, filter non-number qualities (see issue #3643). |