]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/mediasite.py
debian/changelog: Wrap long line.
[youtubedl] / youtube_dl / extractor / mediasite.py
index 0e2645c55072a3401e95d6308d9296ef13280694..d6eb1574065dece67e28a4b36fa43478dd48dfa3 100644 (file)
@@ -13,14 +13,20 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     mimetype2ext,
+    str_or_none,
+    try_get,
     unescapeHTML,
     unsmuggle_url,
+    url_or_none,
     urljoin,
 )
 
 
+_ID_RE = r'(?:[0-9a-f]{32,34}|[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12,14})'
+
+
 class MediasiteIE(InfoExtractor):
-    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?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',
@@ -83,6 +89,19 @@ class MediasiteIE(InfoExtractor):
                 'timestamp': 1333983600,
                 'duration': 7794,
             }
+        },
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d',
+            'only_matching': True,
+        },
+        {
+            # dashed id
+            'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271-681e-4f19-9af3-c60d1f82869b1d',
+            'only_matching': True,
         }
     ]
 
@@ -100,7 +119,7 @@ class MediasiteIE(InfoExtractor):
         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):
@@ -110,7 +129,7 @@ class MediasiteIE(InfoExtractor):
         query = mobj.group('query')
 
         webpage, urlh = self._download_webpage_handle(url, resource_id)  # XXX: add UrlReferrer?
-        redirect_url = compat_str(urlh.geturl())
+        redirect_url = urlh.geturl()
 
         # XXX: might have also extracted UrlReferrer and QueryString from the html
         service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex(
@@ -156,8 +175,8 @@ class MediasiteIE(InfoExtractor):
 
             stream_formats = []
             for unum, VideoUrl in enumerate(video_urls):
-                video_url = VideoUrl.get('Location')
-                if not video_url or not isinstance(video_url, compat_str):
+                video_url = url_or_none(VideoUrl.get('Location'))
+                if not video_url:
                     continue
                 # XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS
 
@@ -212,3 +231,136 @@ class MediasiteIE(InfoExtractor):
             '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,
+    }, {
+        # dashed id
+        'url': 'http://events7.mediasite.com/Mediasite/Catalog/Full/631f9e48-530d-4543-8154-9f955d08c75e',
+        '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,)
+
+
+class MediasiteNamedCatalogIE(InfoExtractor):
+    _VALID_URL = r'(?xi)(?P<url>https?://[^/]+/Mediasite)/Catalog/catalogs/(?P<catalog_name>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://msite.misis.ru/Mediasite/Catalog/catalogs/2016-industrial-management-skriabin-o-o',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mediasite_url = mobj.group('url')
+        catalog_name = mobj.group('catalog_name')
+
+        webpage = self._download_webpage(url, catalog_name)
+
+        catalog_id = self._search_regex(
+            r'CatalogId\s*:\s*["\'](%s)' % _ID_RE, webpage, 'catalog id')
+
+        return self.url_result(
+            '%s/Catalog/Full/%s' % (mediasite_url, catalog_id),
+            ie=MediasiteCatalogIE.ie_key(), video_id=catalog_id)