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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import hmac
   5 from hashlib import sha1
   6 from base64 import b64encode
   7 from time import time
   8
   9 from .common import InfoExtractor
  10 from ..utils import (
  11     ExtractorError,
  12     determine_ext
  13 )
  14 from ..compat import compat_urllib_parse
  15
  16
  17 class VLiveIE(InfoExtractor):
  18     IE_NAME = 'vlive'
  19     # www.vlive.tv/video/ links redirect to m.vlive.tv/video/ for mobile devices
  20     _VALID_URL = r'https?://(?:(www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
  21     _TEST = {
  22         'url': 'http://m.vlive.tv/video/1326',
  23         'md5': 'cc7314812855ce56de70a06a27314983',
  24         'info_dict': {
  25             'id': '1326',
  26             'ext': 'mp4',
  27             'title': '[V] Girl\'s Day\'s Broadcast',
  28             'creator': 'Girl\'s Day',
  29         },
  30     }
  31     _SECRET = 'rFkwZet6pqk1vQt6SxxUkAHX7YL3lmqzUMrU4IDusTo4jEBdtOhNfT4BYYAdArwH'
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(
  37             'http://m.vlive.tv/video/%s' % video_id,
  38             video_id, note='Download video page')
  39
  40         title = self._og_search_title(webpage)
  41         thumbnail = self._og_search_thumbnail(webpage)
  42         creator = self._html_search_regex(
  43             r'<span[^>]+class="name">([^<>]+)</span>', webpage, 'creator')
  44
  45         url = 'http://global.apis.naver.com/globalV/globalV/vod/%s/playinfo?' % video_id
  46         msgpad = '%.0f' % (time() * 1000)
  47         md = b64encode(
  48             hmac.new(self._SECRET.encode('ascii'),
  49                      (url[:255] + msgpad).encode('ascii'), sha1).digest()
  50         )
  51         url += '&' + compat_urllib_parse.urlencode({'msgpad': msgpad, 'md': md})
  52         playinfo = self._download_json(url, video_id, 'Downloading video json')
  53
  54         if playinfo.get('message', '') != 'success':
  55             raise ExtractorError(playinfo.get('message', 'JSON request unsuccessful'))
  56
  57         if not playinfo.get('result'):
  58             raise ExtractorError('No videos found.')
  59
  60         formats = []
  61         for vid in playinfo['result'].get('videos', {}).get('list', []):
  62             formats.append({
  63                 'url': vid['source'],
  64                 'ext': 'mp4',
  65                 'abr': vid.get('bitrate', {}).get('audio'),
  66                 'vbr': vid.get('bitrate', {}).get('video'),
  67                 'format_id': vid['encodingOption']['name'],
  68                 'height': vid.get('height'),
  69                 'width': vid.get('width'),
  70             })
  71         self._sort_formats(formats)
  72
  73         subtitles = {}
  74         for caption in playinfo['result'].get('captions', {}).get('list', []):
  75             subtitles[caption['language']] = [
  76                 {'ext': determine_ext(caption['source'], default_ext='vtt'),
  77                  'url': caption['source']}]
  78
  79         return {
  80             'id': video_id,
  81             'title': title,
  82             'creator': creator,
  83             'thumbnail': thumbnail,
  84             'formats': formats,
  85             'subtitles': subtitles,
  86         }