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
  79         self._set_cookie('steampowered.com', 'mature_content', '1')
  80
  81         webpage = self._download_webpage(videourl, playlist_id)
  82
  83         if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
  84             videourl = self._AGECHECK_TEMPLATE % playlist_id
  85             self.report_age_confirmation()
  86             webpage = self._download_webpage(videourl, playlist_id)
  87
  88         flash_vars = self._parse_json(self._search_regex(
  89             r'(?s)rgMovieFlashvars\s*=\s*({.+?});', webpage,
  90             'flash vars'), playlist_id, js_to_json)
  91
  92         playlist_title = None
  93         entries = []
  94         if fileID:
  95             playlist_title = get_element_by_class('workshopItemTitle', webpage)
  96             for movie in flash_vars.values():
  97                 if not movie:
  98                     continue
  99                 youtube_id = movie.get('YOUTUBE_VIDEO_ID')
 100                 if not youtube_id:
 101                     continue
 102                 entries.append({
 103                     '_type': 'url',
 104                     'url': youtube_id,
 105                     'ie_key': 'Youtube',
 106                 })
 107         else:
 108             playlist_title = get_element_by_class('apphub_AppName', webpage)
 109             for movie_id, movie in flash_vars.items():
 110                 if not movie:
 111                     continue
 112                 video_id = self._search_regex(r'movie_(\d+)', movie_id, 'video id', fatal=False)
 113                 title = movie.get('MOVIE_NAME')
 114                 if not title or not video_id:
 115                     continue
 116                 entry = {
 117                     'id': video_id,
 118                     'title': title.replace('+', ' '),
 119                 }
 120                 formats = []
 121                 flv_url = movie.get('FILENAME')
 122                 if flv_url:
 123                     formats.append({
 124                         'format_id': 'flv',
 125                         'url': flv_url,
 126                     })
 127                 highlight_element = self._search_regex(
 128                     r'(<div[^>]+id="highlight_movie_%s"[^>]+>)' % video_id,
 129                     webpage, 'highlight element', fatal=False)
 130                 if highlight_element:
 131                     highlight_attribs = extract_attributes(highlight_element)
 132                     if highlight_attribs:
 133                         entry['thumbnail'] = highlight_attribs.get('data-poster')
 134                         for quality in ('', '-hd'):
 135                             for ext in ('webm', 'mp4'):
 136                                 video_url = highlight_attribs.get('data-%s%s-source' % (ext, quality))
 137                                 if video_url:
 138                                     formats.append({
 139                                         'format_id': ext + quality,
 140                                         'url': video_url,
 141                                     })
 142                 if not formats:
 143                     continue
 144                 entry['formats'] = formats
 145                 entries.append(entry)
 146         if not entries:
 147             raise ExtractorError('Could not find any videos')
 148
 149         return self.playlist_result(entries, playlist_id, playlist_title)