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