github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

Merge branch 'master' of github.com:rg3/youtube-dl into remitamine-ndr

Browse source
This commit is contained in:
Sergey M․ 2015-09-13 01:10:39 +06:00
parent 3ebc121293 f665ef8fc5
commit d5867276a9
1 changed files with 18 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
youtube_dl/extractor/tudou.py
View file

@ -2,14 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
class TudouIE(InfoExtractor): class TudouIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])' _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/([^/]+/)*(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])'
_TESTS = [{ _TESTS = [{
'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
'md5': '140a49ed444bd22f93330985d8475fcb', 'md5': '140a49ed444bd22f93330985d8475fcb',
@ -27,41 +25,41 @@ class TudouIE(InfoExtractor):
'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
} }
}, {
'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html',
'only_matching': True,
}] }]
_PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
def _url_for_id(self, id, quality=None): def _url_for_id(self, video_id, quality=None):
info_url = "http://v2.tudou.com/f?id=" + str(id) info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)
if quality: if quality:
info_url += '&hd' + quality info_url += '&hd' + quality
webpage = self._download_webpage(info_url, id, "Opening the info webpage") xml_data = self._download_xml(info_url, video_id, "Opening the info XML page")
final_url = self._html_search_regex('>(.+?)</f>', webpage, 'video url') final_url = xml_data.text
return final_url return final_url
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) youku_vcode = self._search_regex(
if m and m.group(1): r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None)
return { if youku_vcode:
'_type': 'url', return self.url_result('youku:' + youku_vcode, ie='Youku')
'url': 'youku:' + m.group(1),
'ie_key': 'Youku'
}
title = self._search_regex( title = self._search_regex(
r",kw:\s*['\"](.+?)[\"']", webpage, 'title') r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title')
thumbnail_url = self._search_regex( thumbnail_url = self._search_regex(
r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False)
player_url = self._search_regex( player_url = self._search_regex(
r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']", r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]',
webpage, 'player URL', default=self._PLAYER_URL) webpage, 'player URL', default=self._PLAYER_URL)
segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segments = self._parse_json(self._search_regex(
segments = json.loads(segs_json) r'segs: \'([^\']+)\'', webpage, 'segments'), video_id)
# It looks like the keys are the arguments that have to be passed as # 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 # the hd field in the request url, we pick the higher
# Also, filter non-number qualities (see issue #3643). # Also, filter non-number qualities (see issue #3643).