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_urlparse,
  12 )
  13 from ..utils import (
  14     ExtractorError,
  15     update_url_query,
  16 )
  17
  18
  19 class SafariBaseIE(InfoExtractor):
  20     _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/'
  21     _NETRC_MACHINE = 'safari'
  22
  23     _API_BASE = 'https://learning.oreilly.com/api/v1'
  24     _API_FORMAT = 'json'
  25
  26     LOGGED_IN = False
  27
  28     def _real_initialize(self):
  29         self._login()
  30
  31     def _login(self):
  32         username, password = self._get_login_info()
  33         if username is None:
  34             return
  35
  36         _, urlh = self._download_webpage_handle(
  37             'https://learning.oreilly.com/accounts/login-check/', None,
  38             'Downloading login page')
  39
  40         def is_logged(urlh):
  41             return 'learning.oreilly.com/home/' in urlh.geturl()
  42
  43         if is_logged(urlh):
  44             self.LOGGED_IN = True
  45             return
  46
  47         redirect_url = urlh.geturl()
  48         parsed_url = compat_urlparse.urlparse(redirect_url)
  49         qs = compat_parse_qs(parsed_url.query)
  50         next_uri = compat_urlparse.urljoin(
  51             'https://api.oreilly.com', qs['next'][0])
  52
  53         auth, urlh = self._download_json_handle(
  54             'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
  55             data=json.dumps({
  56                 'email': username,
  57                 'password': password,
  58                 'redirect_uri': next_uri,
  59             }).encode(), headers={
  60                 'Content-Type': 'application/json',
  61                 'Referer': redirect_url,
  62             }, expected_status=400)
  63
  64         credentials = auth.get('credentials')
  65         if (not auth.get('logged_in') and not auth.get('redirect_uri')
  66                 and credentials):
  67             raise ExtractorError(
  68                 'Unable to login: %s' % credentials, expected=True)
  69
  70         # oreilly serves two same instances of the following cookies
  71         # in Set-Cookie header and expects first one to be actually set
  72         for cookie in ('groot_sessionid', 'orm-jwt', 'orm-rt'):
  73             self._apply_first_set_cookie_header(urlh, cookie)
  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                 headers={'Accept': 'application/json'})
 169             if kaltura_session:
 170                 session = kaltura_session.get('session')
 171                 if session:
 172                     query['flashvars[ks]'] = session
 173
 174         return self.url_result(update_url_query(
 175             'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
 176             'Kaltura')
 177
 178
 179 class SafariApiIE(SafariBaseIE):
 180     IE_NAME = 'safari:api'
 181     _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
 182
 183     _TESTS = [{
 184         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
 185         'only_matching': True,
 186     }, {
 187         'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
 188         'only_matching': True,
 189     }]
 190
 191     def _real_extract(self, url):
 192         mobj = re.match(self._VALID_URL, url)
 193         part = self._download_json(
 194             url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
 195             'Downloading part JSON')
 196         return self.url_result(part['web_url'], SafariIE.ie_key())
 197
 198
 199 class SafariCourseIE(SafariBaseIE):
 200     IE_NAME = 'safari:course'
 201     IE_DESC = 'safaribooksonline.com online courses'
 202
 203     _VALID_URL = r'''(?x)
 204                     https?://
 205                         (?:
 206                             (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
 207                             (?:
 208                                 library/view/[^/]+|
 209                                 api/v1/book|
 210                                 videos/[^/]+
 211                             )|
 212                             techbus\.safaribooksonline\.com
 213                         )
 214                         /(?P<id>[^/]+)
 215                     '''
 216
 217     _TESTS = [{
 218         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 219         'info_dict': {
 220             'id': '9780133392838',
 221             'title': 'Hadoop Fundamentals LiveLessons',
 222         },
 223         'playlist_count': 22,
 224         'skip': 'Requires safaribooksonline account credentials',
 225     }, {
 226         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
 227         'only_matching': True,
 228     }, {
 229         'url': 'http://techbus.safaribooksonline.com/9780134426365',
 230         'only_matching': True,
 231     }, {
 232         'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
 233         'only_matching': True,
 234     }, {
 235         'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
 236         'only_matching': True,
 237     }, {
 238         'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 239         'only_matching': True,
 240     }]
 241
 242     @classmethod
 243     def suitable(cls, url):
 244         return (False if SafariIE.suitable(url) or SafariApiIE.suitable(url)
 245                 else super(SafariCourseIE, cls).suitable(url))
 246
 247     def _real_extract(self, url):
 248         course_id = self._match_id(url)
 249
 250         course_json = self._download_json(
 251             '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 252             course_id, 'Downloading course JSON')
 253
 254         if 'chapters' not in course_json:
 255             raise ExtractorError(
 256                 'No chapters found for course %s' % course_id, expected=True)
 257
 258         entries = [
 259             self.url_result(chapter, SafariApiIE.ie_key())
 260             for chapter in course_json['chapters']]
 261
 262         course_title = course_json['title']
 263
 264         return self.playlist_result(entries, course_id, course_title)