aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/safari.py
blob: a65fc8ed706efa02e4d008494ea8269c10ad8b3a (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
# encoding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from .brightcove import BrightcoveLegacyIE

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


class SafariBaseIE(InfoExtractor):
    _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
    _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
    _NETRC_MACHINE = 'safari'

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

    LOGGED_IN = False

    def _real_initialize(self):
        # We only need to log in once for courses or individual videos
        if not self.LOGGED_IN:
            self._login()
            SafariBaseIE.LOGGED_IN = True

    def _login(self):
        (username, password) = self._get_login_info()
        if username is None:
            self.raise_login_required('safaribooksonline.com account is required')

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

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

        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 re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
            raise ExtractorError(
                'Login failed; make sure your credentials are correct and try again.',
                expected=True)

        self.to_screen('Login successful')


class SafariIE(SafariBaseIE):
    IE_NAME = 'safari'
    IE_DESC = 'safaribooksonline.com online video'
    _VALID_URL = r'''(?x)https?://
                            (?:www\.)?safaribooksonline\.com/
                                (?:
                                    library/view/[^/]+|
                                    api/v1/book
                                )/
                                (?P<course_id>[^/]+)/
                                    (?:chapter(?:-content)?/)?
                                (?P<part>part\d+)\.html
    '''

    _TESTS = [{
        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
        'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
        'info_dict': {
            'id': '2842601850001',
            'ext': 'mp4',
            'title': 'Introduction',
        },
        'skip': 'Requires safaribooksonline account credentials',
    }, {
        'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
        'only_matching': True,
    }, {
        # non-digits in course id
        'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(
            '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
            part)

        bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
        if not bc_url:
            raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)

        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy')


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

    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?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,
    }]

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

        course_json = self._download_json(
            '%s/%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, 'Safari')
            for chapter in course_json['chapters']]

        course_title = course_json['title']

        return self.playlist_result(entries, course_id, course_title)