[mod] add option max_page to bing, brave, qwant, startpage & mojeek

[1] searxng#2982 (comment) Reported-by: @Damaj301damaj-lol [1] Signed-off-by: Markus Heiser <[email protected]>
tiekoetter · Dec 3, 2023 · 3829c25 · 3829c25
1 parent 2274d55
commit 3829c25
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 4 deletions.
diff --git a/searx/engines/bing.py b/searx/engines/bing.py
@@ -59,6 +59,9 @@
 # engine dependent config
 categories = ['general', 'web']
 paging = True
+max_page = 200
+"""200 pages maximum (``&first=1991``)"""
+
 time_range_support = True
 safesearch = True
 """Bing results are always SFW.  To get NSFW links from bing some age

diff --git a/searx/engines/brave.py b/searx/engines/brave.py
@@ -152,6 +152,10 @@
 paging = False
 """Brave only supports paging in :py:obj:`brave_category` ``search`` (UI
 category All)."""
+max_page = 10
+"""Tested 9 pages maximum (``&offset=8``), to be save max is set to 10.  Trying
+to do more won't return any result and you will most likely be flagged as a bot.
+"""
 
 safesearch = True
 safesearch_map = {2: 'strict', 1: 'moderate', 0: 'off'}  # cookie: safesearch=off

diff --git a/searx/engines/qwant.py b/searx/engines/qwant.py
@@ -75,6 +75,10 @@
 # engine dependent config
 categories = []
 paging = True
+max_page = 5
+"""5 pages maximum (``&p=5``): Trying to do more just results in an improper
+redirect"""
+
 qwant_categ = None
 """One of ``web-lite`` (or ``web``), ``news``, ``images`` or ``videos``"""
 
@@ -112,10 +116,6 @@ def request(query, params):
     args = {'q': query}
     params['raise_for_httperror'] = False
 
-    # all qwant engines (incl qwant-lite) delivers only 5 pages maximum
-    if params['pageno'] > 5:
-        return None
-
     if qwant_categ == 'web-lite':
 
         url = web_lite_url + '?'

diff --git a/searx/engines/startpage.py b/searx/engines/startpage.py
@@ -127,6 +127,9 @@
 # engine dependent config
 categories = ['general', 'web']
 paging = True
+max_page = 18
+"""Tested 18 pages maximum (argument ``page``), to be save max is set to 20."""
+
 time_range_support = True
 safesearch = True
 

diff --git a/searx/settings.yml b/searx/settings.yml
@@ -1871,6 +1871,7 @@ engines:
     suggestion_xpath: //div[@class="top-info"]/p[@class="top-info spell"]/em/a
     first_page_num: 0
     page_size: 10
+    max_page: 100
     disabled: true
     about:
       website: https://www.mojeek.com/