aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/safari.py
blob: 909a6ba97993f161c6c39646b073185733626d18 (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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor

from ..utils import (
    ExtractorError,
    sanitized_Request,
    std_headers,
    urlencode_postdata,
    update_url_query,
)


class SafariBaseIE(InfoExtractor):
    _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
    _NETRC_MACHINE = 'safari'

    _API_BASE = 'https://www.safaribooksonline.com/api/v1'
    _API_FORMAT = 'json'

    LOGGED_IN = False

    def _real_initialize(self):
        self._login()

    def _login(self):
        (username, password) = self._get_login_info()
        if username is None:
            return

        headers = std_headers.copy()
        if 'Referer' not in headers:
            headers['Referer'] = self._LOGIN_URL

        login_page = self._download_webpage(
            self._LOGIN_URL, None, 'Downloading login form', headers=headers)

        def is_logged(webpage):
            return any(re.search(p, webpage) for p in (
                r'href=["\']/accounts/logout/', r'>Sign Out<'))

        if is_logged(login_page):
            self.LOGGED_IN = True
            return

        csrf = self._html_search_regex(
            r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
            login_page, 'csrf token')

        login_form = {
            'csrfmiddlewaretoken': csrf,
            'email': username,
            'password1': password,
            'login': 'Sign In',
            'next': '',
        }

        request = sanitized_Request(
            self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
        login_page = self._download_webpage(
            request, None, 'Logging in as %s' % username)

        if not is_logged(login_page):
            raise ExtractorError(
                'Login failed; make sure your credentials are correct and try again.',
                expected=True)

        self.LOGGED_IN = True


class SafariIE(SafariBaseIE):
    IE_NAME = 'safari'
    IE_DESC = 'safaribooksonline.com online video'
    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'

    _TESTS = [{
        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
        'md5': 'dcc5a425e79f2564148652616af1f2a3',
        'info_dict': {
            'id': '0_qbqx90ic',
            'ext': 'mp4',
            'title': 'Introduction to Hadoop Fundamentals LiveLessons',
            'timestamp': 1437758058,
            'upload_date': '20150724',
            'uploader_id': 'stork',
        },
    }, {
        # non-digits in course id
        'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
        'only_matching': True,
    }, {
        'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))

        webpage = self._download_webpage(url, video_id)
        reference_id = self._search_regex(
            r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
            webpage, 'kaltura reference id', group='id')
        partner_id = self._search_regex(
            r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
            webpage, 'kaltura widget id', group='id')
        ui_id = self._search_regex(
            r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
            webpage, 'kaltura uiconf id', group='id')

        query = {
            'wid': '_%s' % partner_id,
            'uiconf_id': ui_id,
            'flashvars[referenceId]': reference_id,
        }

        if self.LOGGED_IN:
            kaltura_session = self._download_json(
                '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
                video_id, 'Downloading kaltura session JSON',
                'Unable to download kaltura session JSON', fatal=False)
            if kaltura_session:
                session = kaltura_session.get('session')
                if session:
                    query['flashvars[ks]'] = session

        return self.url_result(update_url_query(
            'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
            'Kaltura')


class SafariApiIE(SafariBaseIE):
    IE_NAME = 'safari:api'
    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'

    _TESTS = [{
        'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
        'only_matching': True,
    }, {
        'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        part = self._download_json(
            url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
            'Downloading part JSON')
        return self.url_result(part['web_url'], SafariIE.ie_key())


class SafariCourseIE(SafariBaseIE):
    IE_NAME = 'safari:course'
    IE_DESC = 'safaribooksonline.com online courses'

    _VALID_URL = r'''(?x)
                    https?://
                        (?:
                            (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
                            techbus\.safaribooksonline\.com
                        )
                        /(?P<id>[^/]+)/?(?:[#?]|$)
                    '''

    _TESTS = [{
        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
        'info_dict': {
            'id': '9780133392838',
            'title': 'Hadoop Fundamentals LiveLessons',
        },
        'playlist_count': 22,
        'skip': 'Requires safaribooksonline account credentials',
    }, {
        'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
        'only_matching': True,
    }, {
        'url': 'http://techbus.safaribooksonline.com/9780134426365',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        course_id = self._match_id(url)

        course_json = self._download_json(
            '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
            course_id, 'Downloading course JSON')

        if 'chapters' not in course_json:
            raise ExtractorError(
                'No chapters found for course %s' % course_id, expected=True)

        entries = [
            self.url_result(chapter, SafariApiIE.ie_key())
            for chapter in course_json['chapters']]

        course_title = course_json['title']

        return self.playlist_result(entries, course_id, course_title)