[youtube] Unescape HTML for series (closes #18641)

[youtube-dl] / youtube_dl / extractor / aenetworks.py

diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py
index c01c6730358f28356dc1bf62ef72bc0af81299c4..85ec6392daf807b18253b815c0165afc07badbc0 100644 (file)
--- a/youtube_dl/extractor/aenetworks.py
+++ b/youtube_dl/extractor/aenetworks.py
@@ -22,18 +22,19 @@ class AENetworksBaseIE(ThePlatformIE):
 
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
-    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
+    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?
                         (?P<domain>
-                            (?:history|aetv|mylifetime|lifetimemovieclub)\.com|
+                            (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
                             fyi\.tv
                         )/
                         (?:
                             shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
                             movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
-                            specials/(?P<special_display_id>[^/]+)/full-special
+                            specials/(?P<special_display_id>[^/]+)/full-special|
+                            collections/[^/]+/(?P<collection_display_id>[^/]+)
                         )
                     '''
     _TESTS = [{
@@ -80,6 +81,9 @@ class AENetworksIE(AENetworksBaseIE):
     }, {
         'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
         'only_matching': True
+    }, {
+        'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
+        'only_matching': True
     }]
     _DOMAIN_TO_REQUESTOR_ID = {
         'history.com': 'HISTORY',
@@ -90,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE):
     }
 
     def _real_extract(self, url):
-        domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups()
-        display_id = show_path or movie_display_id or special_display_id
-        webpage = self._download_webpage(url, display_id)
+        domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
+        display_id = show_path or movie_display_id or special_display_id or collection_display_id
+        webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
         if show_path:
             url_parts = show_path.split('/')
             url_parts_len = len(url_parts)
@@ -101,10 +105,14 @@ class AENetworksIE(AENetworksBaseIE):
                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
                     entries.append(self.url_result(
                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
-                return self.playlist_result(
-                    entries, self._html_search_meta('aetn:SeriesId', webpage),
-                    self._html_search_meta('aetn:SeriesTitle', webpage))
-            elif url_parts_len == 2:
+                if entries:
+                    return self.playlist_result(
+                        entries, self._html_search_meta('aetn:SeriesId', webpage),
+                        self._html_search_meta('aetn:SeriesTitle', webpage))
+                else:
+                    # single season
+                    url_parts_len = 2
+            if url_parts_len == 2:
                 entries = []
                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
                     episode_attributes = extract_attributes(episode_item)
@@ -112,13 +120,14 @@ class AENetworksIE(AENetworksBaseIE):
                         url, episode_attributes['data-canonical'])
                     entries.append(self.url_result(
                         episode_url, 'AENetworks',
-                        episode_attributes['data-videoid']))
+                        episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
                 return self.playlist_result(
                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 
         query = {
             'mbr': 'true',
-            'assetTypes': 'high_video_s3'
+            'assetTypes': 'high_video_ak',
+            'switch': 'hls_high_ak',
         }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(
@@ -127,7 +136,7 @@ class AENetworksIE(AENetworksBaseIE):
              r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
             webpage, 'video url', group='url')
         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
-            r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
+            r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)
         if theplatform_metadata.get('AETN$isBehindWall'):
             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]