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}$',
  29             'description': 're:.*m7show@163\.com.*',
  30             'thumbnail': 're:^https?://.*\.jpg$',
  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}$',
  44             'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
  45             'thumbnail': 're:^https?://.*\.jpg$',
  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}$',
  60             'description': 're:.*m7show@163\.com.*',
  61             'thumbnail': 're:^https?://.*\.jpg$',
  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
  73     # Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
  74     # is encrypted originally, but ffdec can dump memory to get the decrypted one.
  75     _API_KEY = 'A12Svb&%1UUmf@hC'
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79
  80         if video_id.isdigit():
  81             room_id = video_id
  82         else:
  83             page = self._download_webpage(url, video_id)
  84             room_id = self._html_search_regex(
  85                 r'"room_id"\s*:\s*(\d+),', page, 'room id')
  86
  87         room = self._download_json(
  88             'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
  89             note='Downloading room info')['data']
  90
  91         # 1 = live, 2 = offline
  92         if room.get('show_status') == '2':
  93             raise ExtractorError('Live stream is offline', expected=True)
  94
  95         tt = compat_str(int(time.time() / 60))
  96         did = uuid.uuid4().hex.upper()
  97
  98         sign_content = ''.join((room_id, did, self._API_KEY, tt))
  99         sign = hashlib.md5((sign_content).encode('utf-8')).hexdigest()
 100
 101         flv_data = compat_urllib_parse_urlencode({
 102             'cdn': 'ws',
 103             'rate': '0',
 104             'tt': tt,
 105             'did': did,
 106             'sign': sign,
 107         })
 108
 109         video_info = self._download_json(
 110             'http://www.douyu.com/lapi/live/getPlay/%s' % room_id, video_id,
 111             data=flv_data, note='Downloading video info',
 112             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 113
 114         error_code = video_info.get('error', 0)
 115         if error_code is not 0:
 116             raise ExtractorError(
 117                 '%s reported error %i' % (self.IE_NAME, error_code),
 118                 expected=True)
 119
 120         base_url = video_info['data']['rtmp_url']
 121         live_path = video_info['data']['rtmp_live']
 122
 123         video_url = '%s/%s' % (base_url, live_path)
 124
 125         title = self._live_title(unescapeHTML(room['room_name']))
 126         description = room.get('notice')
 127         thumbnail = room.get('room_src')
 128         uploader = room.get('nickname')
 129
 130         return {
 131             'id': room_id,
 132             'display_id': video_id,
 133             'url': video_url,
 134             'title': title,
 135             'description': description,
 136             'thumbnail': thumbnail,
 137             'uploader': uploader,
 138             'is_live': True,
 139         }