You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
youtube-dl/youtube_dl/extractor/sohu.py

95 lines
3.1 KiB
Python

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# encoding: utf-8
import json
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class SohuIE(InfoExtractor):
_VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
_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'MVFar East Movement《The Illest》',
},
}
def _real_extract(self, url):
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='
data_url = base_data_url + str(vid_id)
data_json = self._download_webpage(
data_url, video_id,
note=u'Downloading JSON data for ' + str(vid_id))
return json.loads(data_json)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mytv = mobj.group('mytv') is not None
webpage = self._download_webpage(url, video_id)
raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
webpage, u'video title')
title = raw_title.partition('-')[0].strip()
vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
u'video path')
data = _fetch_data(vid, mytv)
QUALITIES = ('ori', 'super', 'high', 'nor')
vid_ids = [data['data'][q + 'Vid']
for q in QUALITIES
if data['data'][q + 'Vid'] != 0]
if not vid_ids:
raise ExtractorError(u'No formats available for this video')
# For now, we just pick the highest available quality
vid_id = vid_ids[-1]
format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
part_count = format_data['data']['totalBlocks']
allot = format_data['allot']
prot = format_data['prot']
clipsURL = format_data['data']['clipsURL']
su = format_data['data']['su']
playlist = []
for i in range(part_count):
part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
(allot, prot, clipsURL[i], su[i]))
part_str = self._download_webpage(
part_url, video_id,
note=u'Downloading part %d of %d' % (i+1, part_count))
part_info = part_str.split('|')
video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
video_info = {
'id': '%s_part%02d' % (video_id, i + 1),
'title': title,
'url': video_url,
'ext': 'mp4',
}
playlist.append(video_info)
if len(playlist) == 1:
info = playlist[0]
info['id'] = video_id
else:
info = {
'_type': 'playlist',
'entries': playlist,
'id': video_id,
}
return info