debian/control: Mark package compliant with Policy 4.3.0 (no changes needed).

[youtubedl] / youtube_dl / extractor / aenetworks.py

diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py
index dd96a47cecd787de1dd3b071fd5dd49f7306560f..85ec6392daf807b18253b815c0165afc07badbc0 100644 (file)
--- a/youtube_dl/extractor/aenetworks.py
+++ b/youtube_dl/extractor/aenetworks.py
@@ -22,8 +22,21 @@ class AENetworksBaseIE(ThePlatformIE):
 
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
 
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'

-    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime|lifetimemovieclub)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?)'
+    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?P<domain>
+                            (?: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|
+                            collections/[^/]+/(?P<collection_display_id>[^/]+)
+                        )
+                    '''

     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',


@@ -65,6 +78,12 @@ class AENetworksIE(AENetworksBaseIE):
     }, {
         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
         'only_matching': True
     }, {
         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
         'only_matching': True

+    }, {
+        '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',
     }]
     _DOMAIN_TO_REQUESTOR_ID = {
         'history.com': 'HISTORY',


@@ -75,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

-        domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
-        display_id = show_path or movie_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)
         if show_path:
             url_parts = show_path.split('/')
             url_parts_len = len(url_parts)


@@ -86,10 +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'))
                 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)
                 entries = []
                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
                     episode_attributes = extract_attributes(episode_item)


@@ -97,19 +120,23 @@ class AENetworksIE(AENetworksBaseIE):
                         url, episode_attributes['data-canonical'])
                     entries.append(self.url_result(
                         episode_url, 'AENetworks',
                         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',
                 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(
         }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(

-            r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
+            [r"media_url\s*=\s*'(?P<url>[^']+)'",
+             r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
+             r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
+            webpage, 'video url', group='url')

         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
         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$isBehindWall'):
             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
         info = self._parse_theplatform_metadata(theplatform_metadata)
         if theplatform_metadata.get('AETN$isBehindWall'):
             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]