aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/gdcvault.py
blob: 01e1ceec8e212c13e7f86a15ba7a161755ff8ad2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    HEADRequest,
    sanitized_Request,
    urlencode_postdata,
)


class GDCVaultIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?'
    _NETRC_MACHINE = 'gdcvault'
    _TESTS = [
        {
            'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
            'md5': '7ce8388f544c88b7ac11c7ab1b593704',
            'info_dict': {
                'id': '1019721',
                'display_id': 'Doki-Doki-Universe-Sweet-Simple',
                'ext': 'mp4',
                'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
            }
        },
        {
            'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
            'info_dict': {
                'id': '1015683',
                'display_id': 'Embracing-the-Dark-Art-of',
                'ext': 'flv',
                'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
            },
            'params': {
                'skip_download': True,  # Requires rtmpdump
            }
        },
        {
            'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
            'md5': 'a5eb77996ef82118afbbe8e48731b98e',
            'info_dict': {
                'id': '1015301',
                'display_id': 'Thexder-Meets-Windows-95-or',
                'ext': 'flv',
                'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
            },
            'skip': 'Requires login',
        },
        {
            'url': 'http://gdcvault.com/play/1020791/',
            'only_matching': True,
        },
        {
            'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface',
            'md5': 'a8efb6c31ed06ca8739294960b2dbabd',
            'info_dict': {
                'id': '1023460',
                'ext': 'mp4',
                'display_id': 'Tenacious-Design-and-The-Interface',
                'title': 'Tenacious Design and The Interface of \'Destiny\'',
            },
        },
    ]

    def _login(self, webpage_url, display_id):
        (username, password) = self._get_login_info()
        if username is None or password is None:
            self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
            return None

        mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
        login_url = mobj.group('root_url') + 'api/login.php'
        logout_url = mobj.group('root_url') + 'logout'

        login_form = {
            'email': username,
            'password': password,
        }

        request = sanitized_Request(login_url, urlencode_postdata(login_form))
        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
        self._download_webpage(request, display_id, 'Logging in')
        start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
        self._download_webpage(logout_url, display_id, 'Logging out')

        return start_page

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)

        video_id = mobj.group('id')
        display_id = mobj.group('name') or video_id

        webpage_url = 'http://www.gdcvault.com/play/' + video_id
        start_page = self._download_webpage(webpage_url, display_id)

        direct_url = self._search_regex(
            r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
            start_page, 'url', default=None)
        if direct_url:
            title = self._html_search_regex(
                r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
                start_page, 'title')
            video_url = 'http://www.gdcvault.com' + direct_url
            # resolve the url so that we can detect the correct extension
            head = self._request_webpage(HEADRequest(video_url), video_id)
            video_url = head.geturl()

            return {
                'id': video_id,
                'display_id': display_id,
                'url': video_url,
                'title': title,
            }

        PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/player.*?\.html.*?".*?</iframe>'

        xml_root = self._html_search_regex(
            PLAYER_REGEX, start_page, 'xml root', default=None)
        if xml_root is None:
            # Probably need to authenticate
            login_res = self._login(webpage_url, display_id)
            if login_res is None:
                self.report_warning('Could not login.')
            else:
                start_page = login_res
                # Grab the url from the authenticated page
                xml_root = self._html_search_regex(
                    PLAYER_REGEX, start_page, 'xml root')

        xml_name = self._html_search_regex(
            r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
            start_page, 'xml filename', default=None)
        if xml_name is None:
            # Fallback to the older format
            xml_name = self._html_search_regex(
                r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>',
                start_page, 'xml filename')

        return {
            '_type': 'url_transparent',
            'id': video_id,
            'display_id': display_id,
            'url': '%s/xml/%s' % (xml_root, xml_name),
            'ie': 'DigitalSpeaking',
        }