from __future__ import unicode_literals
import base64
-import json
+import random
+import string
+import time
from .common import InfoExtractor
from ..compat import (
'''
_TESTS = [{
+ # MD5 is unstable
'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
- 'md5': '5f3af4192eabacc4501508d54a8cabd7',
'info_dict': {
'id': 'XMTc1ODE5Njcy_part1',
'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
'title': '武媚娘传奇 85',
},
'playlist_count': 11,
+ 'skip': 'Available in China only',
}, {
'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
'info_dict': {
'title': '花千骨 04',
},
'playlist_count': 13,
- 'skip': 'Available in China only',
}, {
'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
'note': 'Video protected with password',
# get oip
oip = data['security']['ip']
- # get fileid
- string_ls = list(
- 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
-
fileid_dict = {}
for stream in data['stream']:
format = stream.get('stream_type')
format = stream.get('stream_type')
video_urls = []
for dt in stream['segs']:
- #n = str(int(dt['size']))
n = str(stream['segs'].index(dt))
param = {
'K': dt['key'],
'hd': self.get_hd(format),
'myp': 0,
- #'ts': dt['total_milliseconds_video'],
'ypp': 0,
'ctype': 12,
'ev': 1,
video_url = \
'http://k.youku.com/player/getFlvPath/' + \
'sid/' + sid + \
- '_00'+ \
+ '_00' + \
'/st/' + self.parse_ext_l(format) + \
'/fileid/' + get_fileid(format, n) + '?' + \
compat_urllib_parse.urlencode(param)
return video_urls_dict
+ @staticmethod
+ def get_ysuid():
+ return '%d%s' % (int(time.time()), ''.join([
+ random.choice(string.ascii_letters) for i in range(3)]))
+
def get_hd(self, fm):
hd_id_dict = {
- 'flv': '0',
- 'mp4': '1',
- 'hd2': '2',
- 'hd3': '3',
'3gp': '0',
'3gphd': '1',
+ 'flv': '0',
'flvhd': '0',
+ 'mp4': '1',
'mp4hd': '1',
- 'mp4hd2': '1'
+ 'mp4hd2': '1',
+ 'mp4hd3': '1',
+ 'hd2': '2',
+ 'hd3': '3',
}
return hd_id_dict[fm]
def parse_ext_l(self, fm):
ext_dict = {
+ '3gp': 'flv',
+ '3gphd': 'mp4',
'flv': 'flv',
+ 'flvhd': 'flv',
'mp4': 'mp4',
'mp4hd': 'mp4',
'mp4hd2': 'flv',
'mp4hd3': 'flv',
'hd2': 'flv',
'hd3': 'flv',
- '3gp': 'flv',
- '3gphd': 'mp4',
- 'flvhd': 'flv'
}
return ext_dict[fm]
_dict = {
'3gp': 'h6',
'3gphd': 'h5',
- 'flvhd': 'h4',
'flv': 'h4',
+ 'flvhd': 'h4',
'mp4': 'h3',
- 'hd2': 'h2',
- 'hd3': 'h1',
'mp4hd': 'h3',
+ 'mp4hd2': 'h4',
'mp4hd3': 'h4',
- 'mp4hd2': 'h4'
+ 'hd2': 'h2',
+ 'hd3': 'h1',
}
return _dict[fm]
def _real_extract(self, url):
video_id = self._match_id(url)
- def retrieve_data(req_url, note):
-
+ self._set_cookie('youku.com', '__ysuid', self.get_ysuid())
+ def retrieve_data(req_url, note):
headers = {
- 'Referer': req_url,
- }
- self._set_cookie('youku.com','xreferrer','http://www.youku.com')
- req = sanitized_Request(req_url,headers=headers)
+ 'Referer': req_url,
+ }
+ self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
+ req = sanitized_Request(req_url, headers=headers)
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
if cn_verification_proxy:
req.add_header('Ytdl-request-proxy', cn_verification_proxy)
raw_data = self._download_json(req, video_id, note=note)
- js = json.dumps(raw_data)
return raw_data['data']
-
- video_password = self._downloader.params.get('videopassword', None)
+ video_password = self._downloader.params.get('videopassword')
# request basic data
- basic_data_url = "http://play.youku.com/play/get.json?vid=%s&ct=12" % video_id
+ basic_data_url = 'http://play.youku.com/play/get.json?vid=%s&ct=12' % video_id
if video_password:
basic_data_url += '&pwd=%s' % video_password
- data = retrieve_data(
- basic_data_url,
- 'Downloading JSON metadata 1')
+ data = retrieve_data(basic_data_url, 'Downloading JSON metadata')
error = data.get('error')
if error:
if error_note is not None and '因版权原因无法观看此视频' in error_note:
raise ExtractorError(
'Youku said: Sorry, this video is available in China only', expected=True)
+ elif error_note and '该视频被设为私密' in error_note:
+ raise ExtractorError(
+ 'Youku said: Sorry, this video is private', expected=True)
else:
msg = 'Youku server reported error %i' % error.get('code')
- if error is not None:
+ if error_note is not None:
msg += ': ' + error_note
raise ExtractorError(msg)
- #get video title
+ # get video title
title = data['video']['title']
-
# generate video_urls_dict
video_urls_dict = self.construct_video_urls(data)