1 from __future__ import unicode_literals
5 from .common import InfoExtractor
10 from ..utils import remove_end
13 class GDCVaultIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
17 'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
18 'md5': '7ce8388f544c88b7ac11c7ab1b593704',
22 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
26 'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
30 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
33 'skip_download': True, # Requires rtmpdump
37 'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
38 'md5': 'a5eb77996ef82118afbbe8e48731b98e',
42 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
44 'skip': 'Requires login',
48 def _parse_mp4(self, xml_description):
50 mp4_video = xml_description.find('./metadata/mp4video')
54 mobj = re.match(r'(?P<root>https?://.*?/).*', mp4_video.text)
55 video_root = mobj.group('root')
56 formats = xml_description.findall('./metadata/MBRVideos/MBRVideo')
57 for format in formats:
58 mobj = re.match(r'mp4\:(?P<path>.*)', format.find('streamName').text)
59 url = video_root + mobj.group('path')
60 vbr = format.find('bitrate').text
61 video_formats.append({
67 def _parse_flv(self, xml_description):
69 slide_video_path = xml_description.find('./metadata/slideVideo').text
70 video_formats.append({
71 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % 'fms.digitallyspeaking.com/cfx/st',
72 'play_path': remove_end(slide_video_path, '.flv'),
74 'format_note': 'slide deck video',
77 'format_id': 'slides',
79 speaker_video_path = xml_description.find('./metadata/speakerVideo').text
80 video_formats.append({
81 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % 'fms.digitallyspeaking.com/cfx/st',
82 'play_path': remove_end(speaker_video_path, '.flv'),
84 'format_note': 'speaker video',
87 'format_id': 'speaker',
91 def _login(self, webpage_url, video_id):
92 (username, password) = self._get_login_info()
93 if username is None or password is None:
94 self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
97 mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
98 login_url = mobj.group('root_url') + 'api/login.php'
99 logout_url = mobj.group('root_url') + 'logout'
103 'password': password,
106 request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
107 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
108 self._download_webpage(request, video_id, 'Logging in')
109 start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page')
110 self._download_webpage(logout_url, video_id, 'Logging out')
114 def _real_extract(self, url):
115 mobj = re.match(self._VALID_URL, url)
117 video_id = mobj.group('id')
118 webpage_url = 'http://www.gdcvault.com/play/' + video_id
119 start_page = self._download_webpage(webpage_url, video_id)
121 direct_url = self._search_regex(
122 r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
123 start_page, 'url', default=None)
125 video_url = 'http://www.gdcvault.com/' + direct_url
126 title = self._html_search_regex(
127 r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
137 xml_root = self._html_search_regex(
138 r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>',
139 start_page, 'xml root', default=None)
141 # Probably need to authenticate
142 login_res = self._login(webpage_url, video_id)
143 if login_res is None:
144 self.report_warning('Could not login.')
146 start_page = login_res
147 # Grab the url from the authenticated page
148 xml_root = self._html_search_regex(
149 r'<iframe src="(.*?)player.html.*?".*?</iframe>',
150 start_page, 'xml root')
152 xml_name = self._html_search_regex(
153 r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
154 start_page, 'xml filename', default=None)
156 # Fallback to the older format
157 xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
159 xml_decription_url = xml_root + 'xml/' + xml_name
160 xml_description = self._download_xml(xml_decription_url, video_id)
162 video_title = xml_description.find('./metadata/title').text
163 video_formats = self._parse_mp4(xml_description)
164 if video_formats is None:
165 video_formats = self._parse_flv(xml_description)
169 'title': video_title,
170 'formats': video_formats,