_ 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/book'
  25     _API_FORMAT = 'json'
  26
  27     LOGGED_IN = False
  28
  29     def _real_initialize(self):
  30         return
  31         # We only need to log in once for courses or individual videos
  32         if not self.LOGGED_IN:
  33             self._login()
  34             SafariBaseIE.LOGGED_IN = True
  35
  36     def _login(self):
  37         (username, password) = self._get_login_info()
  38         if username is None:
  39             self.raise_login_required('safaribooksonline.com account is required')
  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         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'''(?x)https?://
  79                             (?:www\.)?safaribooksonline\.com/
  80                                 (?:
  81                                     library/view/[^/]+|
  82                                     api/v1/book
  83                                 )/
  84                                 (?P<course_id>[^/]+)/
  85                                     (?:chapter(?:-content)?/)?
  86                                 (?P<part>part\d+)\.html
  87     '''
  88
  89     _TESTS = [{
  90         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
  91         'md5': 'dcc5a425e79f2564148652616af1f2a3',
  92         'info_dict': {
  93             'id': '0_qbqx90ic',
  94             'ext': 'mp4',
  95             'title': 'Introduction to Hadoop Fundamentals LiveLessons',
  96             'timestamp': 1437758058,
  97             'upload_date': '20150724',
  98             'uploader_id': 'stork',
  99         },
 100     }, {
 101         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
 102         'only_matching': True,
 103     }, {
 104         # non-digits in course id
 105         'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
 106         'only_matching': True,
 107     }]
 108
 109     def _real_extract(self, url):
 110         mobj = re.match(self._VALID_URL, url)
 111         course_id = mobj.group('course_id')
 112         part = mobj.group('part')
 113
 114         webpage = self._download_webpage(url, '%s/%s' % (course_id, part))
 115         reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id')
 116         partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id')
 117         ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id')
 118
 119         return self.url_result(update_url_query('https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', {
 120             'wid': '_%s' % partner_id,
 121             'uiconf_id': ui_id,
 122             'flashvars[referenceId]': reference_id,
 123         }), 'Kaltura')
 124
 125
 126 class SafariCourseIE(SafariBaseIE):
 127     IE_NAME = 'safari:course'
 128     IE_DESC = 'safaribooksonline.com online courses'
 129
 130     _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
 131
 132     _TESTS = [{
 133         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 134         'info_dict': {
 135             'id': '9780133392838',
 136             'title': 'Hadoop Fundamentals LiveLessons',
 137         },
 138         'playlist_count': 22,
 139         'skip': 'Requires safaribooksonline account credentials',
 140     }, {
 141         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
 142         'only_matching': True,
 143     }]
 144
 145     def _real_extract(self, url):
 146         course_id = self._match_id(url)
 147
 148         course_json = self._download_json(
 149             '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 150             course_id, 'Downloading course JSON')
 151
 152         if 'chapters' not in course_json:
 153             raise ExtractorError(
 154                 'No chapters found for course %s' % course_id, expected=True)
 155
 156         entries = [
 157             self.url_result(chapter, 'Safari')
 158             for chapter in course_json['chapters']]
 159
 160         course_title = course_json['title']
 161
 162         return self.playlist_result(entries, course_id, course_title)