[bbc.co.uk:article] Add new extractor (#7257)

youtube_dl/extractor/bbc.py

@@ -20,7 +20,7 @@ from ..compat import compat_HTTPError
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
 
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
@@ -652,7 +652,7 @@ class BBCIE(BBCCoUkIE):
 
     @classmethod
     def suitable(cls, url):
-        return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
+        return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
 
     def _extract_from_media_meta(self, media_meta, video_id):
         # Direct links to media in media metadata (e.g.
@@ -903,3 +903,33 @@ class BBCIE(BBCCoUkIE):
             })
 
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
+
+
+class BBCCoUkArticleIE(InfoExtractor):
+    _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    IE_NAME = 'bbc.co.uk:article'
+    IE_DESC = 'BBC articles'
+
+    _TEST = {
+        'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
+        'info_dict': {
+            'id': '3jNQLTMrPlYGTBn0WV6M2MS',
+            'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
+            'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
+        },
+        'playlist_count': 4,
+        'add_ie': ['BBCCoUk'],
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage).strip()
+
+        entries = [self.url_result(programme_url) for programme_url in re.findall(
+            r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
+
+        return self.playlist_result(entries, playlist_id, title, description)