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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import hashlib
   5 import time
   6 import uuid
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_str,
  11     compat_urllib_parse_urlencode,
  12 )
  13 from ..utils import (
  14     ExtractorError,
  15     unescapeHTML,
  16 )
  17
  18
  19 class DouyuTVIE(InfoExtractor):
  20     IE_DESC = '斗鱼'
  21     _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)'
  22     _TESTS = [{
  23         'url': 'http://www.douyutv.com/iseven',
  24         'info_dict': {
  25             'id': '17732',
  26             'display_id': 'iseven',
  27             'ext': 'flv',
  28             'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  29             'description': r're:.*m7show@163\.com.*',
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31             'uploader': '7师傅',
  32             'is_live': True,
  33         },
  34         'params': {
  35             'skip_download': True,
  36         },
  37     }, {
  38         'url': 'http://www.douyutv.com/85982',
  39         'info_dict': {
  40             'id': '85982',
  41             'display_id': '85982',
  42             'ext': 'flv',
  43             'title': 're:^小漠从零单排记！——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  44             'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
  45             'thumbnail': r're:^https?://.*\.jpg$',
  46             'uploader': 'douyu小漠',
  47             'is_live': True,
  48         },
  49         'params': {
  50             'skip_download': True,
  51         },
  52         'skip': 'Room not found',
  53     }, {
  54         'url': 'http://www.douyutv.com/17732',
  55         'info_dict': {
  56             'id': '17732',
  57             'display_id': '17732',
  58             'ext': 'flv',
  59             'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  60             'description': r're:.*m7show@163\.com.*',
  61             'thumbnail': r're:^https?://.*\.jpg$',
  62             'uploader': '7师傅',
  63             'is_live': True,
  64         },
  65         'params': {
  66             'skip_download': True,
  67         },
  68     }, {
  69         'url': 'http://www.douyu.com/xiaocang',
  70         'only_matching': True,
  71     }, {
  72         # \"room_id\"
  73         'url': 'http://www.douyu.com/t/lpl',
  74         'only_matching': True,
  75     }]
  76
  77     # Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
  78     # is encrypted originally, but ffdec can dump memory to get the decrypted one.
  79     _API_KEY = 'A12Svb&%1UUmf@hC'
  80
  81     def _real_extract(self, url):
  82         video_id = self._match_id(url)
  83
  84         if video_id.isdigit():
  85             room_id = video_id
  86         else:
  87             page = self._download_webpage(url, video_id)
  88             room_id = self._html_search_regex(
  89                 r'"room_id\\?"\s*:\s*(\d+),', page, 'room id')
  90
  91         room = self._download_json(
  92             'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
  93             note='Downloading room info')['data']
  94
  95         # 1 = live, 2 = offline
  96         if room.get('show_status') == '2':
  97             raise ExtractorError('Live stream is offline', expected=True)
  98
  99         tt = compat_str(int(time.time() / 60))
 100         did = uuid.uuid4().hex.upper()
 101
 102         sign_content = ''.join((room_id, did, self._API_KEY, tt))
 103         sign = hashlib.md5((sign_content).encode('utf-8')).hexdigest()
 104
 105         flv_data = compat_urllib_parse_urlencode({
 106             'cdn': 'ws',
 107             'rate': '0',
 108             'tt': tt,
 109             'did': did,
 110             'sign': sign,
 111         })
 112
 113         video_info = self._download_json(
 114             'http://www.douyu.com/lapi/live/getPlay/%s' % room_id, video_id,
 115             data=flv_data, note='Downloading video info',
 116             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 117
 118         error_code = video_info.get('error', 0)
 119         if error_code is not 0:
 120             raise ExtractorError(
 121                 '%s reported error %i' % (self.IE_NAME, error_code),
 122                 expected=True)
 123
 124         base_url = video_info['data']['rtmp_url']
 125         live_path = video_info['data']['rtmp_live']
 126
 127         video_url = '%s/%s' % (base_url, live_path)
 128
 129         title = self._live_title(unescapeHTML(room['room_name']))
 130         description = room.get('notice')
 131         thumbnail = room.get('room_src')
 132         uploader = room.get('nickname')
 133
 134         return {
 135             'id': room_id,
 136             'display_id': video_id,
 137             'url': video_url,
 138             'title': title,
 139             'description': description,
 140             'thumbnail': thumbnail,
 141             'uploader': uploader,
 142             'is_live': True,
 143         }