Merge branch 'benbusby:main' into bypass_captcha

README.md

@@ -642,7 +642,7 @@ A lot of the app currently piggybacks on Google's existing support for fetching
 | [https://gowogle.voring.me](https://gowogle.voring.me) | 🇺🇸 US | Multi-choice | |
 | [https://whoogle.privacydev.net](https://whoogle.privacydev.net) | 🇺🇸 US | English | |
 | [https://wg.vern.cc](https://wg.vern.cc) | 🇺🇸 US | English |  |
-| [https://www.indexia.gq](https://www.indexia.gq) | 🇨🇦 CA | Multi-choice | ✅ |
+| [https://whoogle.hxvy0.gq](https://whoogle.hxvy0.gq) | 🇨🇦 CA | Turkish Only | ✅ |
 | [https://whoogle.hostux.net](https://whoogle.hostux.net) | 🇫🇷 FR | Multi-choice | |
 | [https://whoogle.lunar.icu](https://whoogle.lunar.icu) | 🇩🇪 DE | Multi-choice | ✅ |
 | [https://whoogle.rhyshl.live](https://whoogle.rhyshl.live) | 🇬🇧 GB | Multi-choice | ✅ |

app/filter.py

@@ -459,7 +459,7 @@ class Filter:
         if any(url in link_netloc for url in unsupported_g_pages):
             # FIXME: The "Shopping" tab requires further filtering (see #136)
             # Temporarily removing all links to that tab for now.
-            
+
             # Replaces the /url google unsupported link to the direct url
             link['href'] = link_netloc
             parent = link.parent
@@ -588,10 +588,9 @@ class Filter:
                 # replaced (i.e. 'philomedium.com' should stay as it is).
                 if 'medium.com' in link_str:
                     if link_str.startswith('medium.com') or '.medium.com' in link_str:
-                        new_desc.string = link_str.replace(
-                            'medium.com', 'farside.link/scribe')
-                    else:
-                        new_desc.string = link_str
+                        link_str = 'farside.link/scribe' + link_str[
+                            link_str.find('medium.com') + len('medium.com'):]
+                    new_desc.string = link_str
                 else:
                     new_desc.string = link_str.replace(site, alt)
 

app/utils/results.py

@@ -186,6 +186,8 @@ def get_site_alt(link: str) -> str:
         if 'wikipedia' in hostname and len(subdomain) == 2:
             hostname = f'{subdomain}.{hostname}'
             params = f'?lang={subdomain}'
+        elif 'medium' in hostname and len(subdomain) > 0:
+            hostname = f'{subdomain}.{hostname}'
 
         parsed_alt = urlparse.urlparse(SITE_ALTS[site_key])
         link = link.replace(hostname, SITE_ALTS[site_key]) + params

misc/instances.txt

@@ -11,7 +11,7 @@ https://gowogle.voring.me
 https://whoogle.privacydev.net
 https://whoogle.hostux.net
 https://wg.vern.cc
-https://www.indexia.gq
+https://whoogle.hxvy0.gq
 https://whoogle.ungovernable.men
 https://whoogle2.ungovernable.men
 https://whoogle3.ungovernable.men