New upstream version 2020.06.16.1

[youtubedl] / youtube_dl / extractor / safari.py

diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index 10251f29e033ef241618ed7985e214dc0e76cd51..2cc66512241dbc6f65589e52d842cf70b7250ccb 100644 (file)
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -1,128 +1,218 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import json

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from .brightcove import BrightcoveIE

 
 from ..compat import (
 
 from ..compat import (

-    compat_urllib_parse,
-    compat_urllib_request,
+    compat_parse_qs,
+    compat_urlparse,

 )
 from ..utils import (
     ExtractorError,
 )
 from ..utils import (
     ExtractorError,

-    smuggle_url,
-    std_headers,
+    update_url_query,

 )
 
 
 class SafariBaseIE(InfoExtractor):
 )
 
 
 class SafariBaseIE(InfoExtractor):

-    _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
-    _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
-    _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'
+    _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/'

     _NETRC_MACHINE = 'safari'
 
     _NETRC_MACHINE = 'safari'
 

-    _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
+    _API_BASE = 'https://learning.oreilly.com/api/v1'

     _API_FORMAT = 'json'
 
     LOGGED_IN = False
 
     def _real_initialize(self):
     _API_FORMAT = 'json'
 
     LOGGED_IN = False
 
     def _real_initialize(self):

-        # We only need to log in once for courses or individual videos
-        if not self.LOGGED_IN:
-            self._login()
-            SafariBaseIE.LOGGED_IN = True
+        self._login()

 
     def _login(self):
 
     def _login(self):

-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()

         if username is None:
         if username is None:

+            return
+
+        _, urlh = self._download_webpage_handle(
+            'https://learning.oreilly.com/accounts/login-check/', None,
+            'Downloading login page')
+
+        def is_logged(urlh):
+            return 'learning.oreilly.com/home/' in urlh.geturl()
+
+        if is_logged(urlh):
+            self.LOGGED_IN = True
+            return
+
+        redirect_url = urlh.geturl()
+        parsed_url = compat_urlparse.urlparse(redirect_url)
+        qs = compat_parse_qs(parsed_url.query)
+        next_uri = compat_urlparse.urljoin(
+            'https://api.oreilly.com', qs['next'][0])
+
+        auth, urlh = self._download_json_handle(
+            'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
+            data=json.dumps({
+                'email': username,
+                'password': password,
+                'redirect_uri': next_uri,
+            }).encode(), headers={
+                'Content-Type': 'application/json',
+                'Referer': redirect_url,
+            }, expected_status=400)
+
+        credentials = auth.get('credentials')
+        if (not auth.get('logged_in') and not auth.get('redirect_uri')
+                and credentials):

             raise ExtractorError(
             raise ExtractorError(

-                self._ACCOUNT_CREDENTIALS_HINT,
-                expected=True)
-
-        headers = std_headers
-        if 'Referer' not in headers:
-            headers['Referer'] = self._LOGIN_URL
-
-        login_page = self._download_webpage(
-            self._LOGIN_URL, None,
-            'Downloading login form')
-
-        csrf = self._html_search_regex(
-            r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
-            login_page, 'csrf token')
-
-        login_form = {
-            'csrfmiddlewaretoken': csrf,
-            'email': username,
-            'password1': password,
-            'login': 'Sign In',
-            'next': '',
-        }
+                'Unable to login: %s' % credentials, expected=True)

 
 

-        request = compat_urllib_request.Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
-        login_page = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+        # oreilly serves two same instances of the following cookies
+        # in Set-Cookie header and expects first one to be actually set
+        for cookie in ('groot_sessionid', 'orm-jwt', 'orm-rt'):
+            self._apply_first_set_cookie_header(urlh, cookie)

 
 

-        if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
-            raise ExtractorError(
-                'Login failed; make sure your credentials are correct and try again.',
-                expected=True)
+        _, urlh = self._download_webpage_handle(
+            auth.get('redirect_uri') or next_uri, None, 'Completing login',)
+
+        if is_logged(urlh):
+            self.LOGGED_IN = True
+            return

 
 

-        self.to_screen('Login successful')
+        raise ExtractorError('Unable to log in')

 
 
 class SafariIE(SafariBaseIE):
     IE_NAME = 'safari'
     IE_DESC = 'safaribooksonline.com online video'
 
 
 class SafariIE(SafariBaseIE):
     IE_NAME = 'safari'
     IE_DESC = 'safaribooksonline.com online video'

-    _VALID_URL = r'''(?x)https?://
-                            (?:www\.)?safaribooksonline\.com/
-                                (?:
-                                    library/view/[^/]+|
-                                    api/v1/book
-                                )/
-                                (?P<course_id>\d+)/
-                                    (?:chapter(?:-content)?/)?
-                                (?P<part>part\d+)\.html
-    '''
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
+                            (?:
+                                library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
+                                videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
+                            )
+                    '''

 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',

-        'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
+        'md5': 'dcc5a425e79f2564148652616af1f2a3',

         'info_dict': {
         'info_dict': {

-            'id': '2842601850001',
+            'id': '0_qbqx90ic',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Introduction',
+            'title': 'Introduction to Hadoop Fundamentals LiveLessons',
+            'timestamp': 1437758058,
+            'upload_date': '20150724',
+            'uploader_id': 'stork',

         },
         },

-        'skip': 'Requires safaribooksonline account credentials',

     }, {
     }, {

-        'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
+        # non-digits in course id
+        'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
+        'only_matching': True,
+    }, {
+        'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html',

         'only_matching': True,
     }]
 
         'only_matching': True,
     }]
 

+    _PARTNER_ID = '1926081'
+    _UICONF_ID = '29375172'
+

     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        course_id = mobj.group('course_id')
-        part = mobj.group('part')

 
 

-        webpage = self._download_webpage(
-            '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
-            part)
+        reference_id = mobj.group('reference_id')
+        if reference_id:
+            video_id = reference_id
+            partner_id = self._PARTNER_ID
+            ui_id = self._UICONF_ID
+        else:
+            video_id = '%s-%s' % (mobj.group('course_id'), mobj.group('part'))
+
+            webpage, urlh = self._download_webpage_handle(url, video_id)
+
+            mobj = re.match(self._VALID_URL, urlh.geturl())
+            reference_id = mobj.group('reference_id')
+            if not reference_id:
+                reference_id = self._search_regex(
+                    r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                    webpage, 'kaltura reference id', group='id')
+            partner_id = self._search_regex(
+                r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura widget id', default=self._PARTNER_ID,
+                group='id')
+            ui_id = self._search_regex(
+                r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura uiconf id', default=self._UICONF_ID,
+                group='id')
+
+        query = {
+            'wid': '_%s' % partner_id,
+            'uiconf_id': ui_id,
+            'flashvars[referenceId]': reference_id,
+        }
+
+        if self.LOGGED_IN:
+            kaltura_session = self._download_json(
+                '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
+                video_id, 'Downloading kaltura session JSON',
+                'Unable to download kaltura session JSON', fatal=False,
+                headers={'Accept': 'application/json'})
+            if kaltura_session:
+                session = kaltura_session.get('session')
+                if session:
+                    query['flashvars[ks]'] = session
+
+        return self.url_result(update_url_query(
+            'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
+            'Kaltura')
+

 
 

-        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
-        if not bc_url:
-            raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
+class SafariApiIE(SafariBaseIE):
+    IE_NAME = 'safari:api'
+    _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'

 
 

-        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
+    _TESTS = [{
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        part = self._download_json(
+            url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
+            'Downloading part JSON')
+        return self.url_result(part['web_url'], SafariIE.ie_key())

 
 
 class SafariCourseIE(SafariBaseIE):
     IE_NAME = 'safari:course'
     IE_DESC = 'safaribooksonline.com online courses'
 
 
 
 class SafariCourseIE(SafariBaseIE):
     IE_NAME = 'safari:course'
     IE_DESC = 'safaribooksonline.com online courses'
 

-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
+                            (?:
+                                library/view/[^/]+|
+                                api/v1/book|
+                                videos/[^/]+
+                            )|
+                            techbus\.safaribooksonline\.com
+                        )
+                        /(?P<id>[^/]+)
+                    '''

 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',


@@ -135,13 +225,30 @@ class SafariCourseIE(SafariBaseIE):
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
         'only_matching': True,
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
         'only_matching': True,

+    }, {
+        'url': 'http://techbus.safaribooksonline.com/9780134426365',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
+        'only_matching': True,
+    }, {
+        'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
+        'only_matching': True,

     }]
 
     }]
 

+    @classmethod
+    def suitable(cls, url):
+        return (False if SafariIE.suitable(url) or SafariApiIE.suitable(url)
+                else super(SafariCourseIE, cls).suitable(url))
+

     def _real_extract(self, url):
         course_id = self._match_id(url)
 
         course_json = self._download_json(
     def _real_extract(self, url):
         course_id = self._match_id(url)
 
         course_json = self._download_json(

-            '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
+            '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),

             course_id, 'Downloading course JSON')
 
         if 'chapters' not in course_json:
             course_id, 'Downloading course JSON')
 
         if 'chapters' not in course_json:


@@ -149,7 +256,7 @@ class SafariCourseIE(SafariBaseIE):
                 'No chapters found for course %s' % course_id, expected=True)
 
         entries = [
                 'No chapters found for course %s' % course_id, expected=True)
 
         entries = [

-            self.url_result(chapter, 'Safari')
+            self.url_result(chapter, SafariApiIE.ie_key())

             for chapter in course_json['chapters']]
 
         course_title = course_json['title']
             for chapter in course_json['chapters']]
 
         course_title = course_json['title']