yt_dlp/extractor/gdcvault.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .kaltura import KalturaIE
   7 from ..utils import (
   8     HEADRequest,
   9     remove_start,
  10     sanitized_Request,
  11     smuggle_url,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class GDCVaultIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)(?:/(?P<name>[\w-]+))?'
  18     _NETRC_MACHINE = 'gdcvault'
  19     _TESTS = [
  20         {
  21             'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
  22             'md5': '7ce8388f544c88b7ac11c7ab1b593704',
  23             'info_dict': {
  24                 'id': '201311826596_AWNY',
  25                 'display_id': 'Doki-Doki-Universe-Sweet-Simple',
  26                 'ext': 'mp4',
  27                 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
  28             }
  29         },
  30         {
  31             'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
  32             'info_dict': {
  33                 'id': '201203272_1330951438328RSXR',
  34                 'display_id': 'Embracing-the-Dark-Art-of',
  35                 'ext': 'flv',
  36                 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
  37             },
  38             'params': {
  39                 'skip_download': True,  # Requires rtmpdump
  40             }
  41         },
  42         {
  43             'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
  44             'md5': 'a5eb77996ef82118afbbe8e48731b98e',
  45             'info_dict': {
  46                 'id': '1015301',
  47                 'display_id': 'Thexder-Meets-Windows-95-or',
  48                 'ext': 'flv',
  49                 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
  50             },
  51             'skip': 'Requires login',
  52         },
  53         {
  54             'url': 'http://gdcvault.com/play/1020791/',
  55             'only_matching': True,
  56         },
  57         {
  58             # Hard-coded hostname
  59             'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface',
  60             'md5': 'a8efb6c31ed06ca8739294960b2dbabd',
  61             'info_dict': {
  62                 'id': '840376_BQRC',
  63                 'ext': 'mp4',
  64                 'display_id': 'Tenacious-Design-and-The-Interface',
  65                 'title': 'Tenacious Design and The Interface of \'Destiny\'',
  66             },
  67         },
  68         {
  69             # Multiple audios
  70             'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC',
  71             'info_dict': {
  72                 'id': '12396_1299111843500GMPX',
  73                 'ext': 'mp4',
  74                 'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man',
  75             },
  76             # 'params': {
  77             #     'skip_download': True,  # Requires rtmpdump
  78             #     'format': 'jp',  # The japanese audio
  79             # }
  80         },
  81         {
  82             # gdc-player.html
  83             'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
  84             'info_dict': {
  85                 'id': '9350_1238021887562UHXB',
  86                 'display_id': 'An-American-engine-in-Tokyo',
  87                 'ext': 'mp4',
  88                 'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
  89             },
  90         },
  91         {
  92             # Kaltura Embed
  93             'url': 'https://www.gdcvault.com/play/1026180/Mastering-the-Apex-of-Scaling',
  94             'info_dict': {
  95                 'id': '0_h1fg8j3p',
  96                 'ext': 'mp4',
  97                 'title': 'Mastering the Apex of Scaling Game Servers (Presented by Multiplay)',
  98                 'timestamp': 1554401811,
  99                 'upload_date': '20190404',
 100                 'uploader_id': 'joe@blazestreaming.com',
 101             },
 102             'params': {
 103                 'format': 'mp4-408',
 104             },
 105         },
 106         {
 107             # Kaltura embed, whitespace between quote and embedded URL in iframe's src
 108             'url': 'https://www.gdcvault.com/play/1025699',
 109             'info_dict': {
 110                 'id': '0_zagynv0a',
 111                 'ext': 'mp4',
 112                 'title': 'Tech Toolbox',
 113                 'upload_date': '20190408',
 114                 'uploader_id': 'joe@blazestreaming.com',
 115                 'timestamp': 1554764629,
 116             },
 117             'params': {
 118                 'skip_download': True,
 119             },
 120         },
 121         {
 122             # HTML5 video
 123             'url': 'http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru',
 124             'only_matching': True,
 125         },
 126     ]
 127
 128     def _login(self, webpage_url, display_id):
 129         username, password = self._get_login_info()
 130         if username is None or password is None:
 131             self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
 132             return None
 133
 134         mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
 135         login_url = mobj.group('root_url') + 'api/login.php'
 136         logout_url = mobj.group('root_url') + 'logout'
 137
 138         login_form = {
 139             'email': username,
 140             'password': password,
 141         }
 142
 143         request = sanitized_Request(login_url, urlencode_postdata(login_form))
 144         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 145         self._download_webpage(request, display_id, 'Logging in')
 146         start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
 147         self._download_webpage(logout_url, display_id, 'Logging out')
 148
 149         return start_page
 150
 151     def _real_extract(self, url):
 152         video_id, name = self._match_valid_url(url).groups()
 153         display_id = name or video_id
 154
 155         webpage_url = 'http://www.gdcvault.com/play/' + video_id
 156         start_page = self._download_webpage(webpage_url, display_id)
 157
 158         direct_url = self._search_regex(
 159             r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
 160             start_page, 'url', default=None)
 161         if direct_url:
 162             title = self._html_search_regex(
 163                 r'<td><strong>Session Name:?</strong></td>\s*<td>(.*?)</td>',
 164                 start_page, 'title')
 165             video_url = 'http://www.gdcvault.com' + direct_url
 166             # resolve the url so that we can detect the correct extension
 167             video_url = self._request_webpage(
 168                 HEADRequest(video_url), video_id).geturl()
 169
 170             return {
 171                 'id': video_id,
 172                 'display_id': display_id,
 173                 'url': video_url,
 174                 'title': title,
 175             }
 176
 177         embed_url = KalturaIE._extract_url(start_page)
 178         if embed_url:
 179             embed_url = smuggle_url(embed_url, {'source_url': url})
 180             ie_key = 'Kaltura'
 181         else:
 182             PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
 183
 184             xml_root = self._html_search_regex(
 185                 PLAYER_REGEX, start_page, 'xml root', default=None)
 186             if xml_root is None:
 187                 # Probably need to authenticate
 188                 login_res = self._login(webpage_url, display_id)
 189                 if login_res is None:
 190                     self.report_warning('Could not login.')
 191                 else:
 192                     start_page = login_res
 193                     # Grab the url from the authenticated page
 194                     xml_root = self._html_search_regex(
 195                         PLAYER_REGEX, start_page, 'xml root')
 196
 197             xml_name = self._html_search_regex(
 198                 r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
 199                 start_page, 'xml filename', default=None)
 200             if not xml_name:
 201                 info = self._parse_html5_media_entries(url, start_page, video_id)[0]
 202                 info.update({
 203                     'title': remove_start(self._search_regex(
 204                         r'>Session Name:\s*<.*?>\s*<td>(.+?)</td>', start_page,
 205                         'title', default=None) or self._og_search_title(
 206                         start_page, default=None), 'GDC Vault - '),
 207                     'id': video_id,
 208                     'display_id': display_id,
 209                 })
 210                 return info
 211             embed_url = '%s/xml/%s' % (xml_root, xml_name)
 212             ie_key = 'DigitallySpeaking'
 213
 214         return {
 215             '_type': 'url_transparent',
 216             'id': video_id,
 217             'display_id': display_id,
 218             'url': embed_url,
 219             'ie_key': ie_key,
 220         }