# coding: utf-8
from __future__ import unicode_literals
+import json
import base64
from .common import InfoExtractor
-from ..utils import ExtractorError
-
from ..compat import (
compat_urllib_parse,
+ compat_cookiejar,
+ compat_cookies,
+ compat_urllib_request,
compat_ord,
)
+from ..utils import (
+ ExtractorError,
+ sanitized_Request,
+)
class YoukuIE(InfoExtractor):
IE_NAME = 'youku'
+ IE_DESC = '优酷'
_VALID_URL = r'''(?x)
(?:
http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
(?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
'''
- _TEST = {
+ _TESTS = [{
'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
'md5': '5f3af4192eabacc4501508d54a8cabd7',
'info_dict': {
- 'id': 'XMTc1ODE5Njcy',
+ 'id': 'XMTc1ODE5Njcy_part1',
'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
'ext': 'flv'
}
- }
+ }, {
+ 'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
+ 'info_dict': {
+ 'id': 'XODgxNjg1Mzk2',
+ 'title': '武媚娘传奇 85',
+ },
+ 'playlist_count': 11,
+ }, {
+ 'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
+ 'info_dict': {
+ 'id': 'XMTI1OTczNDM5Mg',
+ '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',
+ 'info_dict': {
+ 'id': 'XNjA1NzA2Njgw',
+ 'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
+ },
+ 'playlist_count': 19,
+ 'params': {
+ 'videopassword': '100600',
+ },
+ }]
def construct_video_urls(self, data1, data2):
# get sid, token
return bytes(s)
sid, token = yk_t(
- b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
+ b'becaf9be', base64.b64decode(data2['security']['encrypt_string'].encode('ascii'))
).decode('ascii').split('_')
# get oip
- oip = data2['ip']
+ oip = data2['security']['ip']
# get fileid
string_ls = list(
'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
shuffled_string_ls = []
- seed = data1['seed']
+ seed = data1.get('seed')
+ seed = 0
N = len(string_ls)
for ii in range(N):
seed = (seed * 0xd3 + 0x754f) % 0x10000
del string_ls[idx]
fileid_dict = {}
- for format in data1['streamtypes']:
- streamfileid = [
- int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
- fileid = ''.join(
- [shuffled_string_ls[i] for i in streamfileid])
- fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
+ for stream in data1['stream']:
+ format = stream.get('stream_type')
+ #streamfileid = [
+ # int(i) for i in data1['stream']['streamfileids']#[format].strip('*').split('*')]
+ #fileid = ''.join(
+ # [shuffled_string_ls[i] for i in streamfileid])
+ fileid = stream['stream_fileid']
+ fileid_dict[format] = fileid
+ #fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
def get_fileid(format, n):
- fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
+ #fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
+ fileid = fileid_dict[format]
return fileid
# get ep
# generate video_urls
video_urls_dict = {}
- for format in data1['streamtypes']:
+ for stream in data1['stream']:
+ format = stream.get('stream_type')
video_urls = []
- for dt in data1['segs'][format]:
- n = str(int(dt['no']))
+ for dt in stream['segs']:
+ n = str(int(dt['size']))
param = {
- 'K': dt['k'],
+ 'K': dt['key'],
'hd': self.get_hd(format),
'myp': 0,
- 'ts': dt['seconds'],
+ 'ts': dt['total_milliseconds_video'],
'ypp': 0,
'ctype': 12,
'ev': 1,
'hd2': '2',
'hd3': '3',
'3gp': '0',
- '3gphd': '1'
+ '3gphd': '1',
+ 'flvhd': '0'
}
return hd_id_dict[fm]
'hd2': 'flv',
'hd3': 'flv',
'3gp': 'flv',
- '3gphd': 'mp4'
+ '3gphd': 'mp4',
+ 'flvhd': 'flv'
}
return ext_dict[fm]
_dict = {
'3gp': 'h6',
'3gphd': 'h5',
+ 'flvhd': 'h4',
'flv': 'h4',
'mp4': 'h3',
'hd2': 'h2',
def _real_extract(self, url):
video_id = self._match_id(url)
+ 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)
+
+ 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)
+ jsonDumpIn = json.dumps(raw_data,indent = 1)
+
+ return raw_data['data']
+
+
+ video_password = self._downloader.params.get('videopassword', None)
+
# request basic data
- data1_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id
- data2_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id
+ #basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id
+ basic_data_url = "http://play.youku.com/play/get.json?vid=%s&ct=12" % video_id
+ if video_password:
+ basic_data_url += '?password=%s' % video_password
- raw_data1 = self._download_json(data1_url, video_id)
- raw_data2 = self._download_json(data2_url, video_id)
- data1 = raw_data1['data'][0]
- data2 = raw_data2['data'][0]
+ data1 = retrieve_data(
+ basic_data_url,
+ 'Downloading JSON metadata 1')
+ data2 = retrieve_data(
+ #'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
+ "http://play.youku.com/play/get.json?vid=%s&ct=12" % video_id,
+ 'Downloading JSON metadata 2')
error_code = data1.get('error_code')
if error_code:
- # -8 means blocked outside China.
- # Chinese and English, separated by newline.
error = data1.get('error')
- raise ExtractorError(
- error or 'Server reported error %i' %
- error_code,
- expected=True)
+ if error is not None and '因版权原因无法观看此视频' in error:
+ raise ExtractorError(
+ 'Youku said: Sorry, this video is available in China only', expected=True)
+ else:
+ msg = 'Youku server reported error %i' % error_code
+ if error is not None:
+ msg += ': ' + error
+ raise ExtractorError(msg)
- title = data1['title']
+ #title = data1['title']
+ title = data1['video']['title']
# generate video_urls_dict
video_urls_dict = self.construct_video_urls(data1, data2)
# construct info
- entries = []
- for fm in data1['streamtypes']:
+ entries = [{
+ 'id': '%s_part%d' % (video_id, i + 1),
+ 'title': title,
+ 'formats': [],
+ # some formats are not available for all parts, we have to detect
+ # which one has all
+ } for i in range(max(len(v) for v in data1['stream']))]
+ for stream in data1['stream']:
+ fm = stream.get('stream_type')
video_urls = video_urls_dict[fm]
- for i in range(len(video_urls)):
- if len(entries) < i + 1:
- entries.append({'formats': []})
- entries[i]['formats'].append(
- {
- 'url': video_urls[i],
- 'format_id': self.get_format_name(fm),
- 'ext': self.parse_ext_l(fm),
- 'filesize': int(data1['segs'][fm][i]['size'])
- }
- )
-
- for i in range(len(entries)):
- entries[i].update(
- {
- 'id': '_part%d' % (i + 1),
- 'title': title,
- }
- )
+ for video_url, seg, entry in zip(video_urls, stream['segs'], entries):
+ entry['formats'].append({
+ 'url': video_url,
+ 'format_id': self.get_format_name(fm),
+ 'ext': self.parse_ext_l(fm),
+ 'filesize': int(seg['size']),
+ })
- if len(entries) > 1:
- info = {
- '_type': 'multi_video',
- 'id': video_id,
- 'title': title,
- 'entries': entries,
- }
- else:
- info = entries[0]
- info['id'] = video_id
-
- return info
+ return {
+ '_type': 'multi_video',
+ 'id': video_id,
+ 'title': title,
+ 'entries': entries,
+ }
projects / youtube-dl / blobdiff