Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/safari.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8
   9 from ..compat import (
  10     compat_parse_qs,
  11     compat_str,
  12     compat_urlparse,
  13 )
  14 from ..utils import (
  15     ExtractorError,
  16     update_url_query,
  17 )
  18
  19
  20 class SafariBaseIE(InfoExtractor):
  21     _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/'
  22     _NETRC_MACHINE = 'safari'
  23
  24     _API_BASE = 'https://learning.oreilly.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         username, password = self._get_login_info()
  34         if username is None:
  35             return
  36
  37         _, urlh = self._download_webpage_handle(
  38             'https://learning.oreilly.com/accounts/login-check/', None,
  39             'Downloading login page')
  40
  41         def is_logged(urlh):
  42             return 'learning.oreilly.com/home/' in compat_str(urlh.geturl())
  43
  44         if is_logged(urlh):
  45             self.LOGGED_IN = True
  46             return
  47
  48         redirect_url = compat_str(urlh.geturl())
  49         parsed_url = compat_urlparse.urlparse(redirect_url)
  50         qs = compat_parse_qs(parsed_url.query)
  51         next_uri = compat_urlparse.urljoin(
  52             'https://api.oreilly.com', qs['next'][0])
  53
  54         auth, urlh = self._download_json_handle(
  55             'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
  56             data=json.dumps({
  57                 'email': username,
  58                 'password': password,
  59                 'redirect_uri': next_uri,
  60             }).encode(), headers={
  61                 'Content-Type': 'application/json',
  62                 'Referer': redirect_url,
  63             }, expected_status=400)
  64
  65         credentials = auth.get('credentials')
  66         if (not auth.get('logged_in') and not auth.get('redirect_uri')
  67                 and credentials):
  68             raise ExtractorError(
  69                 'Unable to login: %s' % credentials, expected=True)
  70
  71         # oreilly serves two same groot_sessionid cookies in Set-Cookie header
  72         # and expects first one to be actually set
  73         self._apply_first_set_cookie_header(urlh, 'groot_sessionid')
  74
  75         _, urlh = self._download_webpage_handle(
  76             auth.get('redirect_uri') or next_uri, None, 'Completing login',)
  77
  78         if is_logged(urlh):
  79             self.LOGGED_IN = True
  80             return
  81
  82         raise ExtractorError('Unable to log in')
  83
  84
  85 class SafariIE(SafariBaseIE):
  86     IE_NAME = 'safari'
  87     IE_DESC = 'safaribooksonline.com online video'
  88     _VALID_URL = r'''(?x)
  89                         https?://
  90                             (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
  91                             (?:
  92                                 library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
  93                                 videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
  94                             )
  95                     '''
  96
  97     _TESTS = [{
  98         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
  99         'md5': 'dcc5a425e79f2564148652616af1f2a3',
 100         'info_dict': {
 101             'id': '0_qbqx90ic',
 102             'ext': 'mp4',
 103             'title': 'Introduction to Hadoop Fundamentals LiveLessons',
 104             'timestamp': 1437758058,
 105             'upload_date': '20150724',
 106             'uploader_id': 'stork',
 107         },
 108     }, {
 109         # non-digits in course id
 110         'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
 111         'only_matching': True,
 112     }, {
 113         'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
 114         'only_matching': True,
 115     }, {
 116         'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
 117         'only_matching': True,
 118     }, {
 119         'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
 120         'only_matching': True,
 121     }, {
 122         'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html',
 123         'only_matching': True,
 124     }]
 125
 126     _PARTNER_ID = '1926081'
 127     _UICONF_ID = '29375172'
 128
 129     def _real_extract(self, url):
 130         mobj = re.match(self._VALID_URL, url)
 131
 132         reference_id = mobj.group('reference_id')
 133         if reference_id:
 134             video_id = reference_id
 135             partner_id = self._PARTNER_ID
 136             ui_id = self._UICONF_ID
 137         else:
 138             video_id = '%s-%s' % (mobj.group('course_id'), mobj.group('part'))
 139
 140             webpage, urlh = self._download_webpage_handle(url, video_id)
 141
 142             mobj = re.match(self._VALID_URL, urlh.geturl())
 143             reference_id = mobj.group('reference_id')
 144             if not reference_id:
 145                 reference_id = self._search_regex(
 146                     r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
 147                     webpage, 'kaltura reference id', group='id')
 148             partner_id = self._search_regex(
 149                 r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
 150                 webpage, 'kaltura widget id', default=self._PARTNER_ID,
 151                 group='id')
 152             ui_id = self._search_regex(
 153                 r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
 154                 webpage, 'kaltura uiconf id', default=self._UICONF_ID,
 155                 group='id')
 156
 157         query = {
 158             'wid': '_%s' % partner_id,
 159             'uiconf_id': ui_id,
 160             'flashvars[referenceId]': reference_id,
 161         }
 162
 163         if self.LOGGED_IN:
 164             kaltura_session = self._download_json(
 165                 '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
 166                 video_id, 'Downloading kaltura session JSON',
 167                 'Unable to download kaltura session JSON', fatal=False)
 168             if kaltura_session:
 169                 session = kaltura_session.get('session')
 170                 if session:
 171                     query['flashvars[ks]'] = session
 172
 173         return self.url_result(update_url_query(
 174             'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
 175             'Kaltura')
 176
 177
 178 class SafariApiIE(SafariBaseIE):
 179     IE_NAME = 'safari:api'
 180     _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
 181
 182     _TESTS = [{
 183         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
 184         'only_matching': True,
 185     }, {
 186         'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
 187         'only_matching': True,
 188     }]
 189
 190     def _real_extract(self, url):
 191         mobj = re.match(self._VALID_URL, url)
 192         part = self._download_json(
 193             url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
 194             'Downloading part JSON')
 195         return self.url_result(part['web_url'], SafariIE.ie_key())
 196
 197
 198 class SafariCourseIE(SafariBaseIE):
 199     IE_NAME = 'safari:course'
 200     IE_DESC = 'safaribooksonline.com online courses'
 201
 202     _VALID_URL = r'''(?x)
 203                     https?://
 204                         (?:
 205                             (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
 206                             (?:
 207                                 library/view/[^/]+|
 208                                 api/v1/book|
 209                                 videos/[^/]+
 210                             )|
 211                             techbus\.safaribooksonline\.com
 212                         )
 213                         /(?P<id>[^/]+)
 214                     '''
 215
 216     _TESTS = [{
 217         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 218         'info_dict': {
 219             'id': '9780133392838',
 220             'title': 'Hadoop Fundamentals LiveLessons',
 221         },
 222         'playlist_count': 22,
 223         'skip': 'Requires safaribooksonline account credentials',
 224     }, {
 225         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
 226         'only_matching': True,
 227     }, {
 228         'url': 'http://techbus.safaribooksonline.com/9780134426365',
 229         'only_matching': True,
 230     }, {
 231         'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
 232         'only_matching': True,
 233     }, {
 234         'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
 235         'only_matching': True,
 236     }, {
 237         'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 238         'only_matching': True,
 239     }]
 240
 241     @classmethod
 242     def suitable(cls, url):
 243         return (False if SafariIE.suitable(url) or SafariApiIE.suitable(url)
 244                 else super(SafariCourseIE, cls).suitable(url))
 245
 246     def _real_extract(self, url):
 247         course_id = self._match_id(url)
 248
 249         course_json = self._download_json(
 250             '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 251             course_id, 'Downloading course JSON')
 252
 253         if 'chapters' not in course_json:
 254             raise ExtractorError(
 255                 'No chapters found for course %s' % course_id, expected=True)
 256
 257         entries = [
 258             self.url_result(chapter, SafariApiIE.ie_key())
 259             for chapter in course_json['chapters']]
 260
 261         course_title = course_json['title']
 262
 263         return self.playlist_result(entries, course_id, course_title)