youtube_dl/extractor/safari.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     ExtractorError,
  10     sanitized_Request,
  11     std_headers,
  12     urlencode_postdata,
  13     update_url_query,
  14 )
  15
  16
  17 class SafariBaseIE(InfoExtractor):
  18     _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
  19     _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
  20     _NETRC_MACHINE = 'safari'
  21
  22     _API_BASE = 'https://www.safaribooksonline.com/api/v1'
  23     _API_FORMAT = 'json'
  24
  25     LOGGED_IN = False
  26
  27     def _real_initialize(self):
  28         self._login()
  29
  30     def _login(self):
  31         # We only need to log in once for courses or individual videos
  32         if self.LOGGED_IN:
  33             return
  34
  35         (username, password) = self._get_login_info()
  36         if username is None:
  37             return
  38
  39         headers = std_headers.copy()
  40         if 'Referer' not in headers:
  41             headers['Referer'] = self._LOGIN_URL
  42         login_page_request = sanitized_Request(self._LOGIN_URL, headers=headers)
  43
  44         login_page = self._download_webpage(
  45             login_page_request, None,
  46             'Downloading login form')
  47
  48         csrf = self._html_search_regex(
  49             r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
  50             login_page, 'csrf token')
  51
  52         login_form = {
  53             'csrfmiddlewaretoken': csrf,
  54             'email': username,
  55             'password1': password,
  56             'login': 'Sign In',
  57             'next': '',
  58         }
  59
  60         request = sanitized_Request(
  61             self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
  62         login_page = self._download_webpage(
  63             request, None, 'Logging in as %s' % username)
  64
  65         if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
  66             raise ExtractorError(
  67                 'Login failed; make sure your credentials are correct and try again.',
  68                 expected=True)
  69
  70         SafariBaseIE.LOGGED_IN = True
  71
  72         self.to_screen('Login successful')
  73
  74
  75 class SafariIE(SafariBaseIE):
  76     IE_NAME = 'safari'
  77     IE_DESC = 'safaribooksonline.com online video'
  78     _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
  79
  80     _TESTS = [{
  81         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
  82         'md5': 'dcc5a425e79f2564148652616af1f2a3',
  83         'info_dict': {
  84             'id': '0_qbqx90ic',
  85             'ext': 'mp4',
  86             'title': 'Introduction to Hadoop Fundamentals LiveLessons',
  87             'timestamp': 1437758058,
  88             'upload_date': '20150724',
  89             'uploader_id': 'stork',
  90         },
  91     }, {
  92         # non-digits in course id
  93         'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
  94         'only_matching': True,
  95     }, {
  96         'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
  97         'only_matching': True,
  98     }]
  99
 100     def _real_extract(self, url):
 101         mobj = re.match(self._VALID_URL, url)
 102         video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))
 103
 104         webpage = self._download_webpage(url, video_id)
 105         reference_id = self._search_regex(
 106             r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
 107             webpage, 'kaltura reference id', group='id')
 108         partner_id = self._search_regex(
 109             r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
 110             webpage, 'kaltura widget id', group='id')
 111         ui_id = self._search_regex(
 112             r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
 113             webpage, 'kaltura uiconf id', group='id')
 114
 115         query = {
 116             'wid': '_%s' % partner_id,
 117             'uiconf_id': ui_id,
 118             'flashvars[referenceId]': reference_id,
 119         }
 120
 121         if self.LOGGED_IN:
 122             kaltura_session = self._download_json(
 123                 '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
 124                 video_id, 'Downloading kaltura session JSON',
 125                 'Unable to download kaltura session JSON', fatal=False)
 126             if kaltura_session:
 127                 session = kaltura_session.get('session')
 128                 if session:
 129                     query['flashvars[ks]'] = session
 130
 131         return self.url_result(update_url_query(
 132             'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
 133             'Kaltura')
 134
 135
 136 class SafariApiIE(SafariBaseIE):
 137     IE_NAME = 'safari:api'
 138     _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
 139
 140     _TESTS = [{
 141         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
 142         'only_matching': True,
 143     }, {
 144         'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
 145         'only_matching': True,
 146     }]
 147
 148     def _real_extract(self, url):
 149         mobj = re.match(self._VALID_URL, url)
 150         part = self._download_json(
 151             url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
 152             'Downloading part JSON')
 153         return self.url_result(part['web_url'], SafariIE.ie_key())
 154
 155
 156 class SafariCourseIE(SafariBaseIE):
 157     IE_NAME = 'safari:course'
 158     IE_DESC = 'safaribooksonline.com online courses'
 159
 160     _VALID_URL = r'''(?x)
 161                     https?://
 162                         (?:
 163                             (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
 164                             techbus\.safaribooksonline\.com
 165                         )
 166                         /(?P<id>[^/]+)/?(?:[#?]|$)
 167                     '''
 168
 169     _TESTS = [{
 170         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 171         'info_dict': {
 172             'id': '9780133392838',
 173             'title': 'Hadoop Fundamentals LiveLessons',
 174         },
 175         'playlist_count': 22,
 176         'skip': 'Requires safaribooksonline account credentials',
 177     }, {
 178         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
 179         'only_matching': True,
 180     }, {
 181         'url': 'http://techbus.safaribooksonline.com/9780134426365',
 182         'only_matching': True,
 183     }]
 184
 185     def _real_extract(self, url):
 186         course_id = self._match_id(url)
 187
 188         course_json = self._download_json(
 189             '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 190             course_id, 'Downloading course JSON')
 191
 192         if 'chapters' not in course_json:
 193             raise ExtractorError(
 194                 'No chapters found for course %s' % course_id, expected=True)
 195
 196         entries = [
 197             self.url_result(chapter, SafariApiIE.ie_key())
 198             for chapter in course_json['chapters']]
 199
 200         course_title = course_json['title']
 201
 202         return self.playlist_result(entries, course_id, course_title)