|
@ -1,4 +1,5 @@ |
|
|
# encoding: utf-8 |
|
|
# encoding: utf-8 |
|
|
|
|
|
from __future__ import unicode_literals |
|
|
|
|
|
|
|
|
import json |
|
|
import json |
|
|
import re |
|
|
import re |
|
@ -11,13 +12,14 @@ class SohuIE(InfoExtractor): |
|
|
_VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|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'file': u'382479172.mp4', |
|
|
|
|
|
u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7', |
|
|
|
|
|
u'info_dict': { |
|
|
|
|
|
u'title': u'MV:Far East Movement《The Illest》', |
|
|
|
|
|
|
|
|
'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super', |
|
|
|
|
|
'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7', |
|
|
|
|
|
'info_dict': { |
|
|
|
|
|
'id': '382479172', |
|
|
|
|
|
'ext': 'mp4', |
|
|
|
|
|
'title': 'MV:Far East Movement《The Illest》', |
|
|
}, |
|
|
}, |
|
|
u'skip': u'Only available from China', |
|
|
|
|
|
|
|
|
'skip': 'Only available from China', |
|
|
} |
|
|
} |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
def _real_extract(self, url): |
|
@ -26,7 +28,7 @@ class SohuIE(InfoExtractor): |
|
|
if mytv: |
|
|
if mytv: |
|
|
base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' |
|
|
base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' |
|
|
else: |
|
|
else: |
|
|
base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' |
|
|
|
|
|
|
|
|
base_data_url = '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( |
|
|
data_url, video_id, |
|
|
data_url, video_id, |
|
@ -39,11 +41,11 @@ class SohuIE(InfoExtractor): |
|
|
|
|
|
|
|
|
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, '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') |
|
|
|
|
|
|
|
|
'video path') |
|
|
data = _fetch_data(vid, mytv) |
|
|
data = _fetch_data(vid, mytv) |
|
|
|
|
|
|
|
|
QUALITIES = ('ori', 'super', 'high', 'nor') |
|
|
QUALITIES = ('ori', 'super', 'high', 'nor') |
|
|