[instagram] let's go

soimort · Dec 10, 2018 · c90a44c · c90a44c
1 parent 8454f87
commit c90a44c
Showing 1 changed file with 16 additions and 6 deletions.
diff --git a/src/you_get/extractors/instagram.py b/src/you_get/extractors/instagram.py
@@ -29,9 +29,14 @@ def instagram_download(url, output_dir='.', merge=True, info_only=False, **kwarg
                 image_url = edge['node']['display_url']
                 if 'video_url' in edge['node']:
                     image_url = edge['node']['video_url']
-                image_url = image_url.split('?')[0] # (not here: '?_nc_ht=instagram.fcph1-1.fna.fbcdn.net')
-                ext = image_url.split('.')[-1]
-                size = int(get_head(image_url)['Content-Length'])
+                try:
+                    image_url = image_url.split('?')[0]
+                    ext = image_url.split('.')[-1]
+                    size = int(get_head(image_url)['Content-Length'])
+                except:
+                    image_url = image_url.split('?')[0] + '?_nc_ht=instagram.fcph1-1.fna.fbcdn.net'
+                    ext = image_url.split('.')[-1]
+                    size = int(get_head(image_url)['Content-Length'])
                 print_info(site_info, title, ext, size)
                 if not info_only:
                     download_urls(urls=[image_url],
@@ -44,9 +49,14 @@ def instagram_download(url, output_dir='.', merge=True, info_only=False, **kwarg
             image_url = info['entry_data']['PostPage'][0]['graphql']['shortcode_media']['display_url']
             if 'video_url' in info['entry_data']['PostPage'][0]['graphql']['shortcode_media']:
                 image_url =info['entry_data']['PostPage'][0]['graphql']['shortcode_media']['video_url']
-            image_url = image_url.split('?')[0] + '?_nc_ht=instagram.fcph1-1.fna.fbcdn.net'
-            ext = image_url.split('.')[-1]
-            size = int(get_head(image_url)['Content-Length'])
+            try:
+                image_url = image_url.split('?')[0]
+                ext = image_url.split('.')[-1]
+                size = int(get_head(image_url)['Content-Length'])
+            except:
+                image_url = image_url.split('?')[0] + '?_nc_ht=instagram.fcph1-1.fna.fbcdn.net'
+                ext = image_url.split('.')[-1]
+                size = int(get_head(image_url)['Content-Length'])
             print_info(site_info, title, ext, size)
             if not info_only:
                 download_urls(urls=[image_url],