From e7a604d428752c33ae47ab9d4ec3eca01a37907d Mon Sep 17 00:00:00 2001
From: Ben Busby <benbusby@protonmail.com>
Date: Fri, 4 Jun 2021 15:30:21 -0400
Subject: [PATCH] Fix handling of http (vs https) proxy creation

The requests library requires both 'http' and 'https' values in any
included proxy dict, and whoogle was previously copying the http proxy
to https for simplicity. The assumption was that if the underlying
request wasn't able to connect via https, it would default to http
(otherwise why have the requirement to specify both?)

This led to connectivity issues for users with http only proxies as of
the latest urllib and requests package versions, which are a lot more
strict with connections over https. With the latest versions, if an
https connection cannot be made, the library returns an error.

As a result, the new proxy dict must look something like this for plain
http proxies:

{'http': 'http://domain.tld:port', 'https': 'http://domain.tld:port'}

where both http and https are identical, but both are still required.
---
 README.md          |  2 +-
 app/request.py     | 25 +++++++++++++++++--------
 docker-compose.yml |  2 +-
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index b2112d0..07a58a6 100644
--- a/README.md
+++ b/README.md
@@ -183,7 +183,7 @@ Description=Whoogle
 # Proxy configuration, uncomment to enable
 #Environment=WHOOGLE_PROXY_USER=<proxy username>
 #Environment=WHOOGLE_PROXY_PASS=<proxy password>
-#Environment=WHOOGLE_PROXY_TYPE=<proxy type (http|proxy4|proxy5)
+#Environment=WHOOGLE_PROXY_TYPE=<proxy type (http|https|proxy4|proxy5)
 #Environment=WHOOGLE_PROXY_LOC=<proxy host/ip>
 # Site alternative configurations, uncomment to enable
 # Note: If not set, the feature will still be available
diff --git a/app/request.py b/app/request.py
index 4458c54..f324a4b 100644
--- a/app/request.py
+++ b/app/request.py
@@ -166,17 +166,26 @@ class Request:
             self.modified_user_agent_mobile = gen_user_agent(True)
 
         # Set up proxy, if previously configured
-        if os.environ.get('WHOOGLE_PROXY_LOC'):
+        proxy_path = os.environ.get('WHOOGLE_PROXY_LOC', '')
+        if proxy_path:
+            proxy_type = os.environ.get('WHOOGLE_PROXY_TYPE', '')
+            proxy_user = os.environ.get('WHOOGLE_PROXY_USER', '')
+            proxy_pass = os.environ.get('WHOOGLE_PROXY_PASS', '')
             auth_str = ''
-            if os.environ.get('WHOOGLE_PROXY_USER', ''):
-                auth_str = os.environ.get('WHOOGLE_PROXY_USER', '') + \
-                           ':' + os.environ.get('WHOOGLE_PROXY_PASS', '')
+            if proxy_user:
+                auth_str = proxy_user + ':' + proxy_pass
             self.proxies = {
-                'http': os.environ.get('WHOOGLE_PROXY_TYPE', '') + '://' +
-                auth_str + '@' + os.environ.get('WHOOGLE_PROXY_LOC', ''),
+                'https': proxy_type + '://' +
+                ((auth_str + '@') if auth_str else '') + proxy_path,
             }
-            self.proxies['https'] = self.proxies['http'].replace('http',
-                                                                 'https')
+
+            # Need to ensure both HTTP and HTTPS are in the proxy dict,
+            # regardless of underlying protocol
+            if proxy_type == 'https':
+                self.proxies['http'] = self.proxies['https'].replace(
+                    'https', 'http')
+            else:
+                self.proxies['http'] = self.proxies['https']
         else:
             self.proxies = {
                 'http': 'socks5://127.0.0.1:9050',
diff --git a/docker-compose.yml b/docker-compose.yml
index f29586c..1e45980 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -28,7 +28,7 @@ services:
       # Proxy configuration, uncomment to enable
       #- WHOOGLE_PROXY_USER=<proxy username>
       #- WHOOGLE_PROXY_PASS=<proxy password>
-      #- WHOOGLE_PROXY_TYPE=<proxy type (http|socks4|socks5)
+      #- WHOOGLE_PROXY_TYPE=<proxy type (http|https|socks4|socks5)
       #- WHOOGLE_PROXY_LOC=<proxy host/ip>
       # Site alternative configurations, uncomment to enable
       # Note: If not set, the feature will still be available