Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/letv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import datetime
   5 import re
   6 import time
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_urllib_parse,
  11     compat_urllib_request,
  12     compat_urlparse,
  13 )
  14 from ..utils import (
  15     determine_ext,
  16     ExtractorError,
  17     parse_iso8601,
  18 )
  19
  20
  21 class LetvIE(InfoExtractor):
  22     IE_DESC = '乐视网'
  23     _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
  24
  25     _TESTS = [{
  26         'url': 'http://www.letv.com/ptv/vplay/22005890.html',
  27         'md5': 'cab23bd68d5a8db9be31c9a222c1e8df',
  28         'info_dict': {
  29             'id': '22005890',
  30             'ext': 'mp4',
  31             'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
  32             'timestamp': 1424747397,
  33             'upload_date': '20150224',
  34             'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
  35         }
  36     }, {
  37         'url': 'http://www.letv.com/ptv/vplay/1415246.html',
  38         'info_dict': {
  39             'id': '1415246',
  40             'ext': 'mp4',
  41             'title': '美人天下01',
  42             'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
  43         },
  44     }, {
  45         'note': 'This video is available only in Mainland China, thus a proxy is needed',
  46         'url': 'http://www.letv.com/ptv/vplay/1118082.html',
  47         'md5': 'f80936fbe20fb2f58648e81386ff7927',
  48         'info_dict': {
  49             'id': '1118082',
  50             'ext': 'mp4',
  51             'title': '与龙共舞 完整版',
  52             'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
  53         },
  54         'skip': 'Only available in China',
  55     }]
  56
  57     @staticmethod
  58     def urshift(val, n):
  59         return val >> n if val >= 0 else (val + 0x100000000) >> n
  60
  61     # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
  62     def ror(self, param1, param2):
  63         _loc3_ = 0
  64         while _loc3_ < param2:
  65             param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
  66             _loc3_ += 1
  67         return param1
  68
  69     def calc_time_key(self, param1):
  70         _loc2_ = 773625421
  71         _loc3_ = self.ror(param1, _loc2_ % 13)
  72         _loc3_ = _loc3_ ^ _loc2_
  73         _loc3_ = self.ror(_loc3_, _loc2_ % 17)
  74         return _loc3_
  75
  76     def _real_extract(self, url):
  77         media_id = self._match_id(url)
  78         page = self._download_webpage(url, media_id)
  79         params = {
  80             'id': media_id,
  81             'platid': 1,
  82             'splatid': 101,
  83             'format': 1,
  84             'tkey': self.calc_time_key(int(time.time())),
  85             'domain': 'www.letv.com'
  86         }
  87         play_json_req = compat_urllib_request.Request(
  88             'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
  89         )
  90         cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
  91         if cn_verification_proxy:
  92             play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
  93
  94         play_json = self._download_json(
  95             play_json_req,
  96             media_id, 'Downloading playJson data')
  97
  98         # Check for errors
  99         playstatus = play_json['playstatus']
 100         if playstatus['status'] == 0:
 101             flag = playstatus['flag']
 102             if flag == 1:
 103                 msg = 'Country %s auth error' % playstatus['country']
 104             else:
 105                 msg = 'Generic error. flag = %d' % flag
 106             raise ExtractorError(msg, expected=True)
 107
 108         playurl = play_json['playurl']
 109
 110         formats = ['350', '1000', '1300', '720p', '1080p']
 111         dispatch = playurl['dispatch']
 112
 113         urls = []
 114         for format_id in formats:
 115             if format_id in dispatch:
 116                 media_url = playurl['domain'][0] + dispatch[format_id][0]
 117
 118                 # Mimic what flvxz.com do
 119                 url_parts = list(compat_urlparse.urlparse(media_url))
 120                 qs = dict(compat_urlparse.parse_qs(url_parts[4]))
 121                 qs.update({
 122                     'platid': '14',
 123                     'splatid': '1401',
 124                     'tss': 'no',
 125                     'retry': 1
 126                 })
 127                 url_parts[4] = compat_urllib_parse.urlencode(qs)
 128                 media_url = compat_urlparse.urlunparse(url_parts)
 129
 130                 url_info_dict = {
 131                     'url': media_url,
 132                     'ext': determine_ext(dispatch[format_id][1]),
 133                     'format_id': format_id,
 134                 }
 135
 136                 if format_id[-1:] == 'p':
 137                     url_info_dict['height'] = format_id[:-1]
 138
 139                 urls.append(url_info_dict)
 140
 141         publish_time = parse_iso8601(self._html_search_regex(
 142             r'发布时间&nbsp;([^<>]+) ', page, 'publish time', default=None),
 143             delimiter=' ', timezone=datetime.timedelta(hours=8))
 144         description = self._html_search_meta('description', page, fatal=False)
 145
 146         return {
 147             'id': media_id,
 148             'formats': urls,
 149             'title': playurl['title'],
 150             'thumbnail': playurl['pic'],
 151             'description': description,
 152             'timestamp': publish_time,
 153         }
 154
 155
 156 class LetvTvIE(InfoExtractor):
 157     _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
 158     _TESTS = [{
 159         'url': 'http://www.letv.com/tv/46177.html',
 160         'info_dict': {
 161             'id': '46177',
 162             'title': '美人天下',
 163             'description': 'md5:395666ff41b44080396e59570dbac01c'
 164         },
 165         'playlist_count': 35
 166     }]
 167
 168     def _real_extract(self, url):
 169         playlist_id = self._match_id(url)
 170         page = self._download_webpage(url, playlist_id)
 171
 172         media_urls = list(set(re.findall(
 173             r'http://www.letv.com/ptv/vplay/\d+.html', page)))
 174         entries = [self.url_result(media_url, ie='Letv')
 175                    for media_url in media_urls]
 176
 177         title = self._html_search_meta('keywords', page,
 178                                        fatal=False).split('，')[0]
 179         description = self._html_search_meta('description', page, fatal=False)
 180
 181         return self.playlist_result(entries, playlist_id, playlist_title=title,
 182                                     playlist_description=description)
 183
 184
 185 class LetvPlaylistIE(LetvTvIE):
 186     _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
 187     _TESTS = [{
 188         'url': 'http://tv.letv.com/izt/wuzetian/index.html',
 189         'info_dict': {
 190             'id': 'wuzetian',
 191             'title': '武媚娘传奇',
 192             'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
 193         },
 194         # This playlist contains some extra videos other than the drama itself
 195         'playlist_mincount': 96
 196     }, {
 197         'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
 198         'info_dict': {
 199             'id': 'lswjzzjc',
 200             # The title should be "劲舞青春", but I can't find a simple way to
 201             # determine the playlist title
 202             'title': '乐视午间自制剧场',
 203             'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
 204         },
 205         'playlist_mincount': 7
 206     }]