github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[sohu] add support for my.tv.sohu.com urls (fixes #1398)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-09-09 19:56:16 +02:00
parent 061b2889a9
commit 6d2d21f713
1 changed files with 10 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
youtube_dl/extractor/sohu.py
View file

@ -8,7 +8,7 @@
class SohuIE(InfoExtractor): class SohuIE(InfoExtractor):
_VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?' _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
_TEST = { _TEST = {
u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super', u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
@ -21,7 +21,10 @@ class SohuIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
def _fetch_data(vid_id): def _fetch_data(vid_id, mytv=False):
if mytv:
base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
else:
base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
data_url = base_data_url + str(vid_id) data_url = base_data_url + str(vid_id)
data_json = self._download_webpage( data_json = self._download_webpage(
@ -31,15 +34,16 @@ def _fetch_data(vid_id):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
mytv = mobj.group('mytv') is not None
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>', raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
webpage, u'video title') webpage, u'video title')
title = raw_title.partition('-')[0].strip() title = raw_title.partition('-')[0].strip()
vid = self._html_search_regex(r'var vid="(\d+)"', webpage, vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
u'video path') u'video path')
data = _fetch_data(vid) data = _fetch_data(vid, mytv)
QUALITIES = ('ori', 'super', 'high', 'nor') QUALITIES = ('ori', 'super', 'high', 'nor')
vid_ids = [data['data'][q + 'Vid'] vid_ids = [data['data'][q + 'Vid']
@ -51,7 +55,7 @@ def _fetch_data(vid_id):
# For now, we just pick the highest available quality # For now, we just pick the highest available quality
vid_id = vid_ids[-1] vid_id = vid_ids[-1]
format_data = data if vid == vid_id else _fetch_data(vid_id) format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
part_count = format_data['data']['totalBlocks'] part_count = format_data['data']['totalBlocks']
allot = format_data['allot'] allot = format_data['allot']
prot = format_data['prot'] prot = format_data['prot']