From fd9d6b58d5b0fe6c21168f039678b5721b41fcea Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?No=C3=A9mi=20V=C3=A1nyi?= <sitbackandwait@gmail.com>
Date: Sat, 22 Jan 2022 11:59:21 +0100
Subject: [PATCH] Add scheme to img_src and thumbnail_url if missing from URL

Closes #3092
---
 searx/results.py | 10 ++++++++--
 searx/utils.py   | 12 +++++++++++-
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/searx/results.py b/searx/results.py
index 6502ddcd..1b1eccbe 100644
--- a/searx/results.py
+++ b/searx/results.py
@@ -6,6 +6,7 @@ from urllib.parse import urlparse, unquote
 from searx import logger
 from searx.engines import engines
 from searx.metrology.error_recorder import record_error
+from searx.utils import add_scheme_to_url
 from searx import settings
 
 
@@ -240,10 +241,15 @@ class ResultContainer:
         result['parsed_url'] = urlparse(result['url'])
 
         # if the result has no scheme, use http as default
-        if not result['parsed_url'].scheme:
-            result['parsed_url'] = result['parsed_url']._replace(scheme="http")
+        if not result['parsed_url'].scheme or result['parsed_url'].scheme == '':
+            result['parsed_url'] = result['parsed_url']._replace(scheme='http')
             result['url'] = result['parsed_url'].geturl()
 
+        if 'thumbnail_src' in result:
+            result['thumbnail_src'] = add_scheme_to_url(result['thumbnail_src'])
+        if 'img_src' in result:
+            result['img_src'] = add_scheme_to_url(result['img_src'])
+
         result['engines'] = set([result['engine']])
 
         # strip multiple spaces and cariage returns from content
diff --git a/searx/utils.py b/searx/utils.py
index 55a386bd..9aea9bb0 100644
--- a/searx/utils.py
+++ b/searx/utils.py
@@ -7,7 +7,7 @@ from numbers import Number
 from os.path import splitext, join
 from random import choice
 from html.parser import HTMLParser
-from urllib.parse import urljoin, urlparse
+from urllib.parse import urljoin, urlparse, urlunparse
 
 from lxml import html
 from lxml.etree import ElementBase, XPath, XPathError, XPathSyntaxError, _ElementStringResult, _ElementUnicodeResult
@@ -214,6 +214,16 @@ def normalize_url(url, base_url):
     return url
 
 
+def add_scheme_to_url(url, scheme="https"):
+    """Add schema to URL: if scheme is missing from the URL, then add it."""
+
+    parsed = urlparse(url)
+    if parsed.scheme == '':
+        parsed_with_scheme = parsed._replace(scheme=scheme)
+        return urlunparse(parsed_with_scheme)
+    return url
+
+
 def extract_url(xpath_results, base_url):
     """Extract and normalize URL from lxml Element