require 'extension' data for each URL (#382)

gallery_dl/extractor/artstation.py

@@ -41,6 +41,7 @@ class ArtstationExtractor(Extractor):
                     player = adict["player_embedded"]
                     url = text.extract(player, 'src="', '"')[0]
                     if not url.startswith(self.root):
+                        asset["extension"] = None
                         yield Message.Url, "ytdl:" + url, asset
                         continue
 

gallery_dl/extractor/instagram.py

@@ -40,6 +40,7 @@ class InstagramExtractor(Extractor):
                 yield Message.Url, data['display_url'], \
                     text.nameext_from_url(data['display_url'], data)
             elif data['typename'] == 'GraphVideo':
+                data["extension"] = None
                 yield Message.Url, \
                     'ytdl:{}/p/{}/'.format(self.root, data['shortcode']), data
 

gallery_dl/extractor/sexcom.py

@@ -78,6 +78,7 @@ class SexcomExtractor(Extractor):
                     path += "/hd"
                 data["url"] = self.root + path
             else:
+                data["extension"] = None
                 data["url"] = "ytdl:" + text.extract(
                     extr('<iframe', '>'), ' src="', '"')[0]
         else:

gallery_dl/extractor/twitter.py

@@ -54,6 +54,7 @@ class TwitterExtractor(Extractor):
 
             if self.videos and "-videoContainer" in tweet:
                 data["num"] = 1
+                data["extension"] = None
                 url = "ytdl:{}/{}/status/{}".format(
                     self.root, data["user"], data["tweet_id"])
                 yield Message.Url, url, data

test/test_results.py

@@ -87,13 +87,17 @@ class TestExtractorResults(unittest.TestCase):
         # test archive-id uniqueness
         self.assertEqual(len(set(tjob.list_archive)), len(tjob.list_archive))
 
-        # test '_extractor' entries
         if tjob.queue:
+            # test '_extractor' entries
             for url, kwdict in zip(tjob.list_url, tjob.list_keyword):
                 if "_extractor" in kwdict:
                     extr = kwdict["_extractor"].from_url(url)
                     self.assertIsInstance(extr, kwdict["_extractor"])
                     self.assertEqual(extr.url, url)
+        else:
+            # test 'extension' entries
+            for kwdict in tjob.list_keyword:
+                self.assertIn("extension", kwdict)
 
         # test extraction results
         if "url" in result: