[mediasite:catalog] Add extractor (closes #20507)

youtube_dl/extractor/extractors.py

@@ -632,7 +632,10 @@
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
-from .mediasite import MediasiteIE
+from .mediasite import (
+    MediasiteIE,
+    MediasiteCatalogIE,
+)
 from .medici import MediciIE
 from .megaphone import MegaphoneIE
 from .meipai import MeipaiIE

youtube_dl/extractor/mediasite.py

@@ -13,6 +13,8 @@
     ExtractorError,
     float_or_none,
     mimetype2ext,
+    str_or_none,
+    try_get,
     unescapeHTML,
     unsmuggle_url,
     url_or_none,
@@ -20,8 +22,11 @@
 )
 
 
+_ID_RE = r'[0-9a-f]{32,34}'
+
+
 class MediasiteIE(InfoExtractor):
-    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
+    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>%s)(?P<query>\?[^#]+|)' % _ID_RE
     _TESTS = [
         {
             'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
@@ -109,7 +114,7 @@ def _extract_urls(webpage):
         return [
             unescapeHTML(mobj.group('url'))
             for mobj in re.finditer(
-                r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/[0-9a-f]{32,34}(?:\?.*?)?)\1',
+                r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/%s(?:\?.*?)?)\1' % _ID_RE,
                 webpage)]
 
     def _real_extract(self, url):
@@ -221,3 +226,110 @@ def _real_extract(self, url):
             'formats': formats,
             'thumbnails': thumbnails,
         }
+
+
+class MediasiteCatalogIE(InfoExtractor):
+    _VALID_URL = r'''(?xi)
+                        (?P<url>https?://[^/]+/Mediasite)
+                        /Catalog/Full/
+                        (?P<catalog_id>{0})
+                        (?:
+                            /(?P<current_folder_id>{0})
+                            /(?P<root_dynamic_folder_id>{0})
+                        )?
+                    '''.format(_ID_RE)
+    _TESTS = [{
+        'url': 'http://events7.mediasite.com/Mediasite/Catalog/Full/631f9e48530d454381549f955d08c75e21',
+        'info_dict': {
+            'id': '631f9e48530d454381549f955d08c75e21',
+            'title': 'WCET Summit: Adaptive Learning in Higher Ed: Improving Outcomes Dynamically',
+        },
+        'playlist_count': 6,
+        'expected_warnings': ['is not a supported codec'],
+    }, {
+        # with CurrentFolderId and RootDynamicFolderId
+        'url': 'https://medaudio.medicine.iu.edu/Mediasite/Catalog/Full/9518c4a6c5cf4993b21cbd53e828a92521/97a9db45f7ab47428c77cd2ed74bb98f14/9518c4a6c5cf4993b21cbd53e828a92521',
+        'info_dict': {
+            'id': '9518c4a6c5cf4993b21cbd53e828a92521',
+            'title': 'IUSM Family and Friends Sessions',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'http://uipsyc.mediasite.com/mediasite/Catalog/Full/d5d79287c75243c58c50fef50174ec1b21',
+        'only_matching': True,
+    }, {
+        # no AntiForgeryToken
+        'url': 'https://live.libraries.psu.edu/Mediasite/Catalog/Full/8376d4b24dd1457ea3bfe4cf9163feda21',
+        'only_matching': True,
+    }, {
+        'url': 'https://medaudio.medicine.iu.edu/Mediasite/Catalog/Full/9518c4a6c5cf4993b21cbd53e828a92521/97a9db45f7ab47428c77cd2ed74bb98f14/9518c4a6c5cf4993b21cbd53e828a92521',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mediasite_url = mobj.group('url')
+        catalog_id = mobj.group('catalog_id')
+        current_folder_id = mobj.group('current_folder_id') or catalog_id
+        root_dynamic_folder_id = mobj.group('root_dynamic_folder_id')
+
+        webpage = self._download_webpage(url, catalog_id)
+
+        # AntiForgeryToken is optional (e.g. [1])
+        # 1. https://live.libraries.psu.edu/Mediasite/Catalog/Full/8376d4b24dd1457ea3bfe4cf9163feda21
+        anti_forgery_token = self._search_regex(
+            r'AntiForgeryToken\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+            webpage, 'anti forgery token', default=None, group='value')
+        if anti_forgery_token:
+            anti_forgery_header = self._search_regex(
+                r'AntiForgeryHeaderName\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'anti forgery header name',
+                default='X-SOFO-AntiForgeryHeader', group='value')
+
+        data = {
+            'IsViewPage': True,
+            'IsNewFolder': True,
+            'AuthTicket': None,
+            'CatalogId': catalog_id,
+            'CurrentFolderId': current_folder_id,
+            'RootDynamicFolderId': root_dynamic_folder_id,
+            'ItemsPerPage': 1000,
+            'PageIndex': 0,
+            'PermissionMask': 'Execute',
+            'CatalogSearchType': 'SearchInFolder',
+            'SortBy': 'Date',
+            'SortDirection': 'Descending',
+            'StartDate': None,
+            'EndDate': None,
+            'StatusFilterList': None,
+            'PreviewKey': None,
+            'Tags': [],
+        }
+
+        headers = {
+            'Content-Type': 'application/json; charset=UTF-8',
+            'Referer': url,
+            'X-Requested-With': 'XMLHttpRequest',
+        }
+        if anti_forgery_token:
+            headers[anti_forgery_header] = anti_forgery_token
+
+        catalog = self._download_json(
+            '%s/Catalog/Data/GetPresentationsForFolder' % mediasite_url,
+            catalog_id, data=json.dumps(data).encode(), headers=headers)
+
+        entries = []
+        for video in catalog['PresentationDetailsList']:
+            if not isinstance(video, dict):
+                continue
+            video_id = str_or_none(video.get('Id'))
+            if not video_id:
+                continue
+            entries.append(self.url_result(
+                '%s/Play/%s' % (mediasite_url, video_id),
+                ie=MediasiteIE.ie_key(), video_id=video_id))
+
+        title = try_get(
+            catalog, lambda x: x['CurrentFolder']['Name'], compat_str)
+
+        return self.playlist_result(entries, catalog_id, title,)