pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-05 09:57:59 +09:00
Code Issues Projects Releases Wiki Activity

[weibo] Modernize

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-04-11 13:59:00 +02:00
parent 6a4f3528c8
commit 97b5196960
1 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/weibo.py
View File

@ -1,10 +1,11 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
class WeiboIE(InfoExtractor): class WeiboIE(InfoExtractor):
""" """
The videos in Weibo come from different sites, this IE just finds the link The videos in Weibo come from different sites, this IE just finds the link
@ -13,16 +14,16 @@ class WeiboIE(InfoExtractor):
_VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm' _VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm'
_TEST = { _TEST = {
u'add_ie': ['Sina'], 'url': 'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm',
u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm', 'info_dict': {
u'file': u'98322879.flv', 'id': '98322879',
u'info_dict': { 'ext': 'flv',
u'title': u'魔声耳机最新广告“All Eyes On Us”', 'title': '魔声耳机最新广告“All Eyes On Us”',
}, },
u'note': u'Sina video', 'params': {
u'params': { 'skip_download': True,
u'skip_download': True,
}, },
'add_ie': ['Sina'],
} }
# Additional example videos from different sites # Additional example videos from different sites
@ -33,17 +34,16 @@ class WeiboIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
video_id = mobj.group('id') video_id = mobj.group('id')
info_url = 'http://video.weibo.com/?s=v&a=play_list&format=json&mix_video_id=t_%s' % video_id info_url = 'http://video.weibo.com/?s=v&a=play_list&format=json&mix_video_id=t_%s' % video_id
info_page = self._download_webpage(info_url, video_id) info = self._download_json(info_url, video_id)
info = json.loads(info_page)
videos_urls = map(lambda v: v['play_page_url'], info['result']['data']) videos_urls = map(lambda v: v['play_page_url'], info['result']['data'])
# Prefer sina video since they have thumbnails # Prefer sina video since they have thumbnails
videos_urls = sorted(videos_urls, key=lambda u: u'video.sina.com' in u) videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u)
player_url = videos_urls[-1] player_url = videos_urls[-1]
m_sina = re.match(r'https?://video.sina.com.cn/v/b/(\d+)-\d+.html', player_url) m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html',
player_url)
if m_sina is not None: if m_sina is not None:
self.to_screen('Sina video detected') self.to_screen('Sina video detected')
sina_id = m_sina.group(1) sina_id = m_sina.group(1)
player_url = 'http://you.video.sina.com.cn/swf/quotePlayer.swf?vid=%s' % sina_id player_url = 'http://you.video.sina.com.cn/swf/quotePlayer.swf?vid=%s' % sina_id
return self.url_result(player_url) return self.url_result(player_url)