_ Git - youtube-dl/blob - youtube_dl/extractor/douyutv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     unescapeHTML,
   8 )
   9
  10
  11 class DouyuTVIE(InfoExtractor):
  12     IE_DESC = '斗鱼'
  13     _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)'
  14     _TESTS = [{
  15         'url': 'http://www.douyutv.com/iseven',
  16         'info_dict': {
  17             'id': '17732',
  18             'display_id': 'iseven',
  19             'ext': 'mp4',
  20             '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}$',
  21             'description': r're:.*m7show@163\.com.*',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'uploader': '7师傅',
  24             'is_live': True,
  25         },
  26         'params': {
  27             'skip_download': True,
  28         },
  29     }, {
  30         'url': 'http://www.douyutv.com/85982',
  31         'info_dict': {
  32             'id': '85982',
  33             'display_id': '85982',
  34             'ext': 'mp4',
  35             '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}$',
  36             'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
  37             'thumbnail': r're:^https?://.*\.jpg$',
  38             'uploader': 'douyu小漠',
  39             'is_live': True,
  40         },
  41         'params': {
  42             'skip_download': True,
  43         },
  44         'skip': 'Room not found',
  45     }, {
  46         'url': 'http://www.douyutv.com/17732',
  47         'info_dict': {
  48             'id': '17732',
  49             'display_id': '17732',
  50             'ext': 'mp4',
  51             '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}$',
  52             'description': r're:.*m7show@163\.com.*',
  53             'thumbnail': r're:^https?://.*\.jpg$',
  54             'uploader': '7师傅',
  55             'is_live': True,
  56         },
  57         'params': {
  58             'skip_download': True,
  59         },
  60     }, {
  61         'url': 'http://www.douyu.com/xiaocang',
  62         'only_matching': True,
  63     }, {
  64         # \"room_id\"
  65         'url': 'http://www.douyu.com/t/lpl',
  66         'only_matching': True,
  67     }]
  68
  69     # Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
  70     # is encrypted originally, but ffdec can dump memory to get the decrypted one.
  71     _API_KEY = 'A12Svb&%1UUmf@hC'
  72
  73     def _real_extract(self, url):
  74         video_id = self._match_id(url)
  75
  76         if video_id.isdigit():
  77             room_id = video_id
  78         else:
  79             page = self._download_webpage(url, video_id)
  80             room_id = self._html_search_regex(
  81                 r'"room_id\\?"\s*:\s*(\d+),', page, 'room id')
  82
  83         room = self._download_json(
  84             'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
  85             note='Downloading room info')['data']
  86
  87         # 1 = live, 2 = offline
  88         if room.get('show_status') == '2':
  89             raise ExtractorError('Live stream is offline', expected=True)
  90
  91         formats = self._extract_m3u8_formats(
  92             room['hls_url'], video_id, ext='mp4')
  93
  94         title = self._live_title(unescapeHTML(room['room_name']))
  95         description = room.get('show_details')
  96         thumbnail = room.get('room_src')
  97         uploader = room.get('nickname')
  98
  99         return {
 100             'id': room_id,
 101             'display_id': video_id,
 102             'formats': formats,
 103             'title': title,
 104             'description': description,
 105             'thumbnail': thumbnail,
 106             'uploader': uploader,
 107             'is_live': True,
 108         }