youtube_dl/extractor/safari.py

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