- _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
-
- def _gen_sid(self):
- nowTime = int(time.time() * 1000)
- random1 = random.randint(1000,1998)
- random2 = random.randint(1000,9999)
-
- return "%d%d%d" %(nowTime,random1,random2)
-
- def _get_file_ID_mix_string(self, seed):
- mixed = []
- source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
- seed = float(seed)
- for i in range(len(source)):
- seed = (seed * 211 + 30031 ) % 65536
- index = math.floor(seed / 65536 * len(source) )
- mixed.append(source[int(index)])
- source.remove(source[int(index)])
- #return ''.join(mixed)
- return mixed
-
- def _get_file_id(self, fileId, seed):
- mixed = self._get_file_ID_mix_string(seed)
- ids = fileId.split('*')
- realId = []
- for ch in ids:
- if ch:
- realId.append(mixed[int(ch)])
- return ''.join(realId)
+ IE_NAME = 'youku'
+ IE_DESC = '优酷'
+ _VALID_URL = r'''(?x)
+ (?:
+ http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+ youku:)
+ (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
+ '''
+
+ _TESTS = [{
+ # MD5 is unstable
+ 'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
+ 'info_dict': {
+ '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,
+ 'skip': 'Available in China only',
+ }, {
+ 'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
+ 'info_dict': {
+ 'id': 'XMTI1OTczNDM5Mg',
+ 'title': '花千骨 04',
+ },
+ 'playlist_count': 13,
+ }, {
+ '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',
+ },
+ }, {
+ # /play/get.json contains streams with "channel_type":"tail"
+ 'url': 'http://v.youku.com/v_show/id_XOTUxMzg4NDMy.html',
+ 'info_dict': {
+ 'id': 'XOTUxMzg4NDMy',
+ 'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
+ },
+ 'playlist_count': 6,
+ }]
+
+ def construct_video_urls(self, data):
+ # get sid, token
+ def yk_t(s1, s2):
+ ls = list(range(256))
+ t = 0
+ for i in range(256):
+ t = (t + ls[i] + compat_ord(s1[i % len(s1)])) % 256
+ ls[i], ls[t] = ls[t], ls[i]
+ s = bytearray()
+ x, y = 0, 0
+ for i in range(len(s2)):
+ y = (y + 1) % 256
+ x = (x + ls[y]) % 256
+ ls[x], ls[y] = ls[y], ls[x]
+ s.append(compat_ord(s2[i]) ^ ls[(ls[x] + ls[y]) % 256])
+ return bytes(s)
+
+ sid, token = yk_t(
+ b'becaf9be', base64.b64decode(data['security']['encrypt_string'].encode('ascii'))
+ ).decode('ascii').split('_')
+
+ # get oip
+ oip = data['security']['ip']
+
+ fileid_dict = {}
+ for stream in data['stream']:
+ if stream.get('channel_type') == 'tail':
+ continue
+ format = stream.get('stream_type')
+ fileid = try_get(
+ stream, lambda x: x['segs'][0]['fileid'],
+ compat_str) or stream['stream_fileid']
+ fileid_dict[format] = fileid
+
+ def get_fileid(format, n):
+ number = hex(int(str(n), 10))[2:].upper()
+ if len(number) == 1:
+ number = '0' + number
+ streamfileids = fileid_dict[format]
+ fileid = streamfileids[0:8] + number + streamfileids[10:]
+ return fileid
+
+ # get ep
+ def generate_ep(format, n):
+ fileid = get_fileid(format, n)
+ ep_t = yk_t(
+ b'bf7e5f01',
+ ('%s_%s_%s' % (sid, fileid, token)).encode('ascii')
+ )
+ ep = base64.b64encode(ep_t).decode('ascii')
+ return ep
+
+ # generate video_urls
+ video_urls_dict = {}
+ for stream in data['stream']:
+ if stream.get('channel_type') == 'tail':
+ continue
+ format = stream.get('stream_type')
+ video_urls = []
+ for dt in stream['segs']:
+ n = str(stream['segs'].index(dt))
+ param = {
+ 'K': dt['key'],
+ 'hd': self.get_hd(format),
+ 'myp': 0,
+ 'ypp': 0,
+ 'ctype': 12,
+ 'ev': 1,
+ 'token': token,
+ 'oip': oip,
+ 'ep': generate_ep(format, n)
+ }
+ video_url = \
+ 'http://k.youku.com/player/getFlvPath/' + \
+ 'sid/' + sid + \
+ '_00' + \
+ '/st/' + self.parse_ext_l(format) + \
+ '/fileid/' + get_fileid(format, n) + '?' + \
+ compat_urllib_parse_urlencode(param)
+ video_urls.append(video_url)
+ video_urls_dict[format] = video_urls
+
+ 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 = {
+ '3gp': '0',
+ '3gphd': '1',
+ 'flv': '0',
+ 'flvhd': '0',
+ 'mp4': '1',
+ 'mp4hd': '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',
+ }
+ return ext_dict[fm]
+
+ def get_format_name(self, fm):
+ _dict = {
+ '3gp': 'h6',
+ '3gphd': 'h5',
+ 'flv': 'h4',
+ 'flvhd': 'h4',
+ 'mp4': 'h3',
+ 'mp4hd': 'h3',
+ 'mp4hd2': 'h4',
+ 'mp4hd3': 'h4',
+ 'hd2': 'h2',
+ 'hd3': 'h1',
+ }
+ return _dict[fm]
Rapsys Git / youtubedl / blobdiff