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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     extract_attributes,
   8     ExtractorError,
   9     get_element_by_class,
  10     js_to_json,
  11 )
  12
  13
  14 class SteamIE(InfoExtractor):
  15     _VALID_URL = r"""(?x)
  16         https?://store\.steampowered\.com/
  17             (agecheck/)?
  18             (?P<urltype>video|app)/ #If the page is only for videos or for a game
  19             (?P<gameID>\d+)/?
  20             (?P<videoID>\d*)(?P<extra>\??) # For urltype == video we sometimes get the videoID
  21         |
  22         https?://(?:www\.)?steamcommunity\.com/sharedfiles/filedetails/\?id=(?P<fileID>[0-9]+)
  23     """
  24     _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
  25     _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
  26     _TESTS = [{
  27         'url': 'http://store.steampowered.com/video/105600/',
  28         'playlist': [
  29             {
  30                 'md5': '6a294ee0c4b1f47f5bb76a65e31e3592',
  31                 'info_dict': {
  32                     'id': '2040428',
  33                     'ext': 'mp4',
  34                     'title': 'Terraria 1.3 Trailer',
  35                     'playlist_index': 1,
  36                 }
  37             },
  38             {
  39                 'md5': '911672b20064ca3263fa89650ba5a7aa',
  40                 'info_dict': {
  41                     'id': '2029566',
  42                     'ext': 'mp4',
  43                     'title': 'Terraria 1.2 Trailer',
  44                     'playlist_index': 2,
  45                 }
  46             }
  47         ],
  48         'info_dict': {
  49             'id': '105600',
  50             'title': 'Terraria',
  51         },
  52         'params': {
  53             'playlistend': 2,
  54         }
  55     }, {
  56         'url': 'http://steamcommunity.com/sharedfiles/filedetails/?id=242472205',
  57         'info_dict': {
  58             'id': 'X8kpJBlzD2E',
  59             'ext': 'mp4',
  60             'upload_date': '20140617',
  61             'title': 'FRONTIERS - Trapping',
  62             'description': 'md5:bf6f7f773def614054089e5769c12a6e',
  63             'uploader': 'AAD Productions',
  64             'uploader_id': 'AtomicAgeDogGames',
  65         }
  66     }]
  67
  68     def _real_extract(self, url):
  69         m = re.match(self._VALID_URL, url)
  70         fileID = m.group('fileID')
  71         if fileID:
  72             videourl = url
  73             playlist_id = fileID
  74         else:
  75             gameID = m.group('gameID')
  76             playlist_id = gameID
  77             videourl = self._VIDEO_PAGE_TEMPLATE % playlist_id
  78         webpage = self._download_webpage(videourl, playlist_id)
  79
  80         if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
  81             videourl = self._AGECHECK_TEMPLATE % playlist_id
  82             self.report_age_confirmation()
  83             webpage = self._download_webpage(videourl, playlist_id)
  84
  85         flash_vars = self._parse_json(self._search_regex(
  86             r'(?s)rgMovieFlashvars\s*=\s*({.+?});', webpage,
  87             'flash vars'), playlist_id, js_to_json)
  88
  89         playlist_title = None
  90         entries = []
  91         if fileID:
  92             playlist_title = get_element_by_class('workshopItemTitle', webpage)
  93             for movie in flash_vars.values():
  94                 if not movie:
  95                     continue
  96                 youtube_id = movie.get('YOUTUBE_VIDEO_ID')
  97                 if not youtube_id:
  98                     continue
  99                 entries.append({
 100                     '_type': 'url',
 101                     'url': youtube_id,
 102                     'ie_key': 'Youtube',
 103                 })
 104         else:
 105             playlist_title = get_element_by_class('apphub_AppName', webpage)
 106             for movie_id, movie in flash_vars.items():
 107                 if not movie:
 108                     continue
 109                 video_id = self._search_regex(r'movie_(\d+)', movie_id, 'video id', fatal=False)
 110                 title = movie.get('MOVIE_NAME')
 111                 if not title or not video_id:
 112                     continue
 113                 entry = {
 114                     'id': video_id,
 115                     'title': title.replace('+', ' '),
 116                 }
 117                 formats = []
 118                 flv_url = movie.get('FILENAME')
 119                 if flv_url:
 120                     formats.append({
 121                         'format_id': 'flv',
 122                         'url': flv_url,
 123                     })
 124                 highlight_element = self._search_regex(
 125                     r'(<div[^>]+id="highlight_movie_%s"[^>]+>)' % video_id,
 126                     webpage, 'highlight element', fatal=False)
 127                 if highlight_element:
 128                     highlight_attribs = extract_attributes(highlight_element)
 129                     if highlight_attribs:
 130                         entry['thumbnail'] = highlight_attribs.get('data-poster')
 131                         for quality in ('', '-hd'):
 132                             for ext in ('webm', 'mp4'):
 133                                 video_url = highlight_attribs.get('data-%s%s-source' % (ext, quality))
 134                                 if video_url:
 135                                     formats.append({
 136                                         'format_id': ext + quality,
 137                                         'url': video_url,
 138                                     })
 139                 if not formats:
 140                     continue
 141                 entry['formats'] = formats
 142                 entries.append(entry)
 143         if not entries:
 144             raise ExtractorError('Could not find any videos')
 145
 146         return self.playlist_result(entries, playlist_id, playlist_title)