[syfy] fix the extraction logic and make the test pass

youtube_dl/extractor/syfy.py

@@ -1,46 +1,31 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class SyfyIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))'
+    _VALID_URL = r'https?://www\.syfy\.com/[^/]+/videos/(?:\d+-)?(?P<id>[A-Za-z0-9-]+)'
 
     _TESTS = [{
-        'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
+        'url': 'http://www.syfy.com/sharknado3/videos/sharknado-3-trailer',
         'info_dict': {
-            'id': 'NmqMrGnXvmO1',
-            'ext': 'flv',
-            'title': 'George Lucas has Advice for his Daughter',
-            'description': 'Listen to what insights George Lucas give his daughter Amanda.',
-        },
-        'add_ie': ['ThePlatform'],
-    }, {
-        'url': 'http://www.syfy.com/wilwheaton',
-        'md5': '94dfa54ee3ccb63295b276da08c415f6',
-        'info_dict': {
-            'id': '4yoffOOXC767',
-            'ext': 'flv',
-            'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.',
-            'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.',
+            'id': 'Sueh0V5Eh6L6',
+            'ext': 'm3u8',
+            'title': 'Sharknado 3: Trailer',
+            'description': 'This time, the entire east coast isn\'t safe. Sharknado 3 premieres July 22 at 9/8c on Syfy.',
         },
         'add_ie': ['ThePlatform'],
         'skip': 'Blocked outside the US',
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_name = mobj.group('video_name')
-        if video_name:
-            generic_webpage = self._download_webpage(url, video_name)
-            video_id = self._search_regex(
-                r'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">',
-                generic_webpage, 'video ID')
-            url = 'http://www.syfy.com/videos/%s/%s/vid:%s' % (
-                video_name, video_name, video_id)
-        else:
-            video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        return self.url_result(self._og_search_video_url(webpage))
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        releaseURL = self._parse_json(self._html_search_regex(
+            r'"syfy_mpx"\s*:\s*({[^}]+?})',
+            webpage, 'syfy_mpx'), display_id)['releaseURL']
+        return self.url_result(releaseURL)