1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 16:37:42 +00:00
youtube-dl/youtube_dl/extractor/sohu.py

203 lines
6.7 KiB
Python
Raw Normal View History

2016-10-02 11:39:18 +00:00
# coding: utf-8
2014-11-26 11:53:55 +00:00
from __future__ import unicode_literals
2013-08-02 09:58:46 +00:00
2013-08-28 11:59:08 +00:00
import re
2013-08-02 09:58:46 +00:00
from .common import InfoExtractor
2015-03-05 18:48:27 +00:00
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
2015-03-05 18:48:27 +00:00
)
2017-06-08 17:16:42 +00:00
from ..utils import (
ExtractorError,
int_or_none,
try_get,
)
2013-08-02 09:58:46 +00:00
class SohuIE(InfoExtractor):
_VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
2013-08-02 09:58:46 +00:00
2016-08-08 10:48:21 +00:00
# Sohu videos give different MD5 sums on Travis CI and my machine
_TESTS = [{
'note': 'This video is available only in Mainland China',
2014-11-26 11:53:55 +00:00
'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
'info_dict': {
'id': '382479172',
'ext': 'mp4',
'title': 'MVFar East Movement《The Illest》',
2013-08-02 09:58:46 +00:00
},
'skip': 'On available in China',
}, {
'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
'info_dict': {
'id': '409385080',
'ext': 'mp4',
'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》',
}
}, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【爱范品】第31期MWC见不到的奇葩手机',
}
}, {
'note': 'Multipart video',
'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
'info_dict': {
'id': '78910339',
2015-04-19 11:19:44 +00:00
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
},
'playlist': [{
'info_dict': {
'id': '78910339_part1',
'ext': 'mp4',
'duration': 294,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
'info_dict': {
'id': '78910339_part2',
'ext': 'mp4',
'duration': 300,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
'info_dict': {
'id': '78910339_part3',
'ext': 'mp4',
'duration': 150,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}]
2015-03-14 17:05:01 +00:00
}, {
2015-03-17 15:39:31 +00:00
'note': 'Video with title containing dash',
2015-03-14 17:05:01 +00:00
'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
'info_dict': {
'id': '78932792',
'ext': 'mp4',
'title': 'youtube-dl testing video',
},
'params': {
'skip_download': True
}
}]
2013-08-02 09:58:46 +00:00
def _real_extract(self, url):
2013-08-28 11:59:08 +00:00
def _fetch_data(vid_id, mytv=False):
if mytv:
base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
else:
2014-11-26 11:53:55 +00:00
base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
2015-03-17 15:39:31 +00:00
return self._download_json(
base_data_url + vid_id, video_id,
'Downloading JSON data for %s' % vid_id,
headers=self.geo_verification_headers())
2013-08-28 11:59:08 +00:00
2013-08-02 09:58:46 +00:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mytv = mobj.group('mytv') is not None
2013-08-28 11:59:08 +00:00
2013-08-02 09:58:46 +00:00
webpage = self._download_webpage(url, video_id)
2015-03-14 17:05:01 +00:00
2015-04-19 11:19:44 +00:00
title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage))
2013-08-02 09:58:46 +00:00
vid = self._html_search_regex(
r'var vid ?= ?["\'](\d+)["\']',
webpage, 'video path')
vid_data = _fetch_data(vid, mytv)
2015-05-09 05:19:54 +00:00
if vid_data['play'] != 1:
if vid_data.get('status') == 12:
raise ExtractorError(
2017-02-23 10:49:35 +00:00
'%s said: There\'s something wrong in the video.' % self.IE_NAME,
2015-05-09 05:19:54 +00:00
expected=True)
else:
2017-02-23 10:49:35 +00:00
self.raise_geo_restricted(
'%s said: The video is only licensed to users in Mainland China.' % self.IE_NAME)
2013-08-28 11:59:08 +00:00
formats_json = {}
for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
vid_id = vid_data['data'].get('%sVid' % format_id)
if not vid_id:
continue
vid_id = compat_str(vid_id)
formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv)
2013-08-28 11:59:08 +00:00
part_count = vid_data['data']['totalBlocks']
2013-08-28 11:59:08 +00:00
playlist = []
for i in range(part_count):
formats = []
for format_id, format_data in formats_json.items():
allot = format_data['allot']
data = format_data['data']
clips_url = data['clipsURL']
su = data['su']
2015-06-21 16:59:55 +00:00
video_url = 'newflv.sohu.ccgslb.net'
cdnId = None
retries = 0
2015-06-21 16:59:55 +00:00
while 'newflv.sohu.ccgslb.net' in video_url:
params = {
'prot': 9,
'file': clips_url[i],
'new': su[i],
'prod': 'flash',
2015-12-08 06:12:32 +00:00
'rb': 1,
2015-06-21 16:59:55 +00:00
}
2015-06-21 16:59:55 +00:00
if cdnId is not None:
params['idc'] = cdnId
download_note = 'Downloading %s video URL part %d of %d' % (
format_id, i + 1, part_count)
if retries > 0:
download_note += ' (retry #%d)' % retries
part_info = self._parse_json(self._download_webpage(
'http://%s/?%s' % (allot, compat_urllib_parse_urlencode(params)),
2015-06-21 16:59:55 +00:00
video_id, download_note), video_id)
video_url = part_info['url']
cdnId = part_info.get('nid')
retries += 1
if retries > 5:
raise ExtractorError('Failed to get video URL')
formats.append({
'url': video_url,
'format_id': format_id,
2017-06-08 17:16:42 +00:00
'filesize': int_or_none(
try_get(data, lambda x: x['clipsBytes'][i])),
'width': int_or_none(data.get('width')),
'height': int_or_none(data.get('height')),
'fps': int_or_none(data.get('fps')),
})
self._sort_formats(formats)
playlist.append({
'id': '%s_part%d' % (video_id, i + 1),
2013-08-02 09:58:46 +00:00
'title': title,
'duration': vid_data['data']['clipsDuration'][i],
'formats': formats,
})
2013-08-28 11:59:08 +00:00
if len(playlist) == 1:
info = playlist[0]
2013-08-03 02:29:58 +00:00
info['id'] = video_id
2013-08-28 11:59:08 +00:00
else:
info = {
2015-04-19 11:19:44 +00:00
'_type': 'multi_video',
2013-08-28 11:59:08 +00:00
'entries': playlist,
'id': video_id,
2015-04-19 11:19:44 +00:00
'title': title,
2013-08-28 11:59:08 +00:00
}
return info