]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gdcvault.py
Update changelog.
[youtubedl] / youtube_dl / extractor / gdcvault.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 HEADRequest,
8 sanitized_Request,
9 urlencode_postdata,
10 )
11
12
13 class GDCVaultIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?'
15 _NETRC_MACHINE = 'gdcvault'
16 _TESTS = [
17 {
18 'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
19 'md5': '7ce8388f544c88b7ac11c7ab1b593704',
20 'info_dict': {
21 'id': '1019721',
22 'display_id': 'Doki-Doki-Universe-Sweet-Simple',
23 'ext': 'mp4',
24 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
25 }
26 },
27 {
28 'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
29 'info_dict': {
30 'id': '1015683',
31 'display_id': 'Embracing-the-Dark-Art-of',
32 'ext': 'flv',
33 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
34 },
35 'params': {
36 'skip_download': True, # Requires rtmpdump
37 }
38 },
39 {
40 'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
41 'md5': 'a5eb77996ef82118afbbe8e48731b98e',
42 'info_dict': {
43 'id': '1015301',
44 'display_id': 'Thexder-Meets-Windows-95-or',
45 'ext': 'flv',
46 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
47 },
48 'skip': 'Requires login',
49 },
50 {
51 'url': 'http://gdcvault.com/play/1020791/',
52 'only_matching': True,
53 },
54 {
55 # Hard-coded hostname
56 'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface',
57 'md5': 'a8efb6c31ed06ca8739294960b2dbabd',
58 'info_dict': {
59 'id': '1023460',
60 'ext': 'mp4',
61 'display_id': 'Tenacious-Design-and-The-Interface',
62 'title': 'Tenacious Design and The Interface of \'Destiny\'',
63 },
64 },
65 {
66 # Multiple audios
67 'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC',
68 'info_dict': {
69 'id': '1014631',
70 'ext': 'flv',
71 'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man',
72 },
73 'params': {
74 'skip_download': True, # Requires rtmpdump
75 'format': 'jp', # The japanese audio
76 }
77 },
78 {
79 # gdc-player.html
80 'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
81 'info_dict': {
82 'id': '1435',
83 'display_id': 'An-American-engine-in-Tokyo',
84 'ext': 'flv',
85 'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
86 },
87 'params': {
88 'skip_download': True, # Requires rtmpdump
89 },
90 },
91 ]
92
93 def _login(self, webpage_url, display_id):
94 username, password = self._get_login_info()
95 if username is None or password is None:
96 self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
97 return None
98
99 mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
100 login_url = mobj.group('root_url') + 'api/login.php'
101 logout_url = mobj.group('root_url') + 'logout'
102
103 login_form = {
104 'email': username,
105 'password': password,
106 }
107
108 request = sanitized_Request(login_url, urlencode_postdata(login_form))
109 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
110 self._download_webpage(request, display_id, 'Logging in')
111 start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
112 self._download_webpage(logout_url, display_id, 'Logging out')
113
114 return start_page
115
116 def _real_extract(self, url):
117 mobj = re.match(self._VALID_URL, url)
118
119 video_id = mobj.group('id')
120 display_id = mobj.group('name') or video_id
121
122 webpage_url = 'http://www.gdcvault.com/play/' + video_id
123 start_page = self._download_webpage(webpage_url, display_id)
124
125 direct_url = self._search_regex(
126 r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
127 start_page, 'url', default=None)
128 if direct_url:
129 title = self._html_search_regex(
130 r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
131 start_page, 'title')
132 video_url = 'http://www.gdcvault.com' + direct_url
133 # resolve the url so that we can detect the correct extension
134 head = self._request_webpage(HEADRequest(video_url), video_id)
135 video_url = head.geturl()
136
137 return {
138 'id': video_id,
139 'display_id': display_id,
140 'url': video_url,
141 'title': title,
142 }
143
144 PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
145
146 xml_root = self._html_search_regex(
147 PLAYER_REGEX, start_page, 'xml root', default=None)
148 if xml_root is None:
149 # Probably need to authenticate
150 login_res = self._login(webpage_url, display_id)
151 if login_res is None:
152 self.report_warning('Could not login.')
153 else:
154 start_page = login_res
155 # Grab the url from the authenticated page
156 xml_root = self._html_search_regex(
157 PLAYER_REGEX, start_page, 'xml root')
158
159 xml_name = self._html_search_regex(
160 r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
161 start_page, 'xml filename', default=None)
162 if xml_name is None:
163 # Fallback to the older format
164 xml_name = self._html_search_regex(
165 r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>',
166 start_page, 'xml filename')
167
168 return {
169 '_type': 'url_transparent',
170 'id': video_id,
171 'display_id': display_id,
172 'url': '%s/xml/%s' % (xml_root, xml_name),
173 'ie_key': 'DigitallySpeaking',
174 }