]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/safari.py
New upstream version 2017.09.24
[youtubedl] / youtube_dl / extractor / safari.py
index 91970426103c0384a4998407443907182d7976b5..909a6ba97993f161c6c39646b073185733626d18 100644 (file)
@@ -1,48 +1,50 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from .brightcove import BrightcoveLegacyIE
 
-from ..compat import compat_urllib_parse
 from ..utils import (
     ExtractorError,
     sanitized_Request,
-    smuggle_url,
     std_headers,
+    urlencode_postdata,
+    update_url_query,
 )
 
 
 class SafariBaseIE(InfoExtractor):
     _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
-    _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
     _NETRC_MACHINE = 'safari'
 
-    _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
+    _API_BASE = 'https://www.safaribooksonline.com/api/v1'
     _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):
         (username, password) = self._get_login_info()
         if username is None:
-            self.raise_login_required('safaribooksonline.com account is required')
+            return
 
-        headers = std_headers
+        headers = std_headers.copy()
         if 'Referer' not in headers:
             headers['Referer'] = self._LOGIN_URL
 
         login_page = self._download_webpage(
-            self._LOGIN_URL, None,
-            'Downloading login form')
+            self._LOGIN_URL, None, 'Downloading login form', headers=headers)
+
+        def is_logged(webpage):
+            return any(re.search(p, webpage) for p in (
+                r'href=["\']/accounts/logout/', r'>Sign Out<'))
+
+        if is_logged(login_page):
+            self.LOGGED_IN = True
+            return
 
         csrf = self._html_search_regex(
             r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
@@ -57,71 +59,111 @@ class SafariBaseIE(InfoExtractor):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
+            self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
-        if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
+        if not is_logged(login_page):
             raise ExtractorError(
                 'Login failed; make sure your credentials are correct and try again.',
                 expected=True)
 
-        self.to_screen('Login successful')
+        self.LOGGED_IN = True
 
 
 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>[^/]+)/
-                                    (?:chapter(?:-content)?/)?
-                                (?P<part>part\d+)\.html
-    '''
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
-        'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
+        'md5': 'dcc5a425e79f2564148652616af1f2a3',
         'info_dict': {
-            'id': '2842601850001',
+            'id': '0_qbqx90ic',
             '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',
-        'only_matching': True,
     }, {
         # 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,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        course_id = mobj.group('course_id')
-        part = mobj.group('part')
+        video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))
+
+        webpage = self._download_webpage(url, video_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', group='id')
+        ui_id = self._search_regex(
+            r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+            webpage, 'kaltura 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)
+            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')
 
-        webpage = self._download_webpage(
-            '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
-            part)
 
-        bc_url = BrightcoveLegacyIE._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\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
 
-        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy')
+    _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'
 
-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
+                            techbus\.safaribooksonline\.com
+                        )
+                        /(?P<id>[^/]+)/?(?:[#?]|$)
+                    '''
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
@@ -134,13 +176,16 @@ class SafariCourseIE(SafariBaseIE):
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
         'only_matching': True,
+    }, {
+        'url': 'http://techbus.safaribooksonline.com/9780134426365',
+        'only_matching': True,
     }]
 
     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:
@@ -148,7 +193,7 @@ class SafariCourseIE(SafariBaseIE):
                 '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']