[enh] add raise_for_httperror

check HTTP response:
* detect some comme CAPTCHA challenge (no solving). In this case the engine is suspended for long a time.
* otherwise raise HTTPError as before

the check is done in poolrequests.py (was before in search.py).

update qwant, wikipedia, wikidata to use raise_for_httperror instead of raise_for_status

4 files changed, 25 insertions, 17 deletions

diff --git a/searx/engines/__init__.py b/searx/engines/__init__.py
index 0b77f2a95..b2a9b25a4 100644
--- a/searx/engines/__init__.py
+++ b/searx/engines/__init__.py
@@ -281,8 +281,12 @@ def initialize_engines(engine_list):
     load_engines(engine_list)
 
     def engine_init(engine_name, init_fn):
-        init_fn(get_engine_from_settings(engine_name))
-        logger.debug('%s engine: Initialized', engine_name)
+        try:
+            init_fn(get_engine_from_settings(engine_name))
+        except Exception:
+            logger.exception('%s engine: Fail to initialize', engine_name)
+        else:
+            logger.debug('%s engine: Initialized', engine_name)
 
     for engine_name, engine in engines.items():
         if hasattr(engine, 'init'):
diff --git a/searx/engines/qwant.py b/searx/engines/qwant.py
index c909ce11b..b785719d9 100644
--- a/searx/engines/qwant.py
+++ b/searx/engines/qwant.py
@@ -14,6 +14,8 @@ from datetime import datetime
 from json import loads
 from urllib.parse import urlencode
 from searx.utils import html_to_text, match_language
+from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException
+from searx.raise_for_httperror import raise_for_httperror
 
 
 # engine dependent config
@@ -24,8 +26,7 @@ supported_languages_url = 'https://qwant.com/region'
 
 category_to_keyword = {'general': 'web',
                        'images': 'images',
-                       'news': 'news',
-                       'social media': 'social'}
+                       'news': 'news'}
 
 # search-url
 url = 'https://api.qwant.com/api/search/{keyword}?count=10&offset={offset}&f=&{query}&t={keyword}&uiv=4'
@@ -51,6 +52,7 @@ def request(query, params):
         params['url'] += '&locale=' + language.replace('-', '_').lower()
 
     params['headers']['User-Agent'] = 'Mozilla/5.0 (X11; Linux x86_64; rv:69.0) Gecko/20100101 Firefox/69.0'
+    params['raise_for_httperror'] = False
     return params
 
 
@@ -58,8 +60,20 @@ def request(query, params):
 def response(resp):
     results = []
 
+    # According to https://www.qwant.com/js/app.js
+    if resp.status_code == 429:
+        raise SearxEngineCaptchaException()
+
+    # raise for other errors
+    raise_for_httperror(resp)
+
+    # load JSON result
     search_results = loads(resp.text)
 
+    # check for an API error
+    if search_results.get('status') != 'success':
+        raise SearxEngineAPIException('API error ' + str(search_results.get('error', '')))
+
     # return empty array if there are no results
     if 'data' not in search_results:
         return []
@@ -90,15 +104,6 @@ def response(resp):
                             'thumbnail_src': thumbnail_src,
                             'img_src': img_src})
 
-        elif category_to_keyword.get(categories[0], '') == 'social':
-            published_date = datetime.fromtimestamp(result['date'], None)
-            img_src = result.get('img', None)
-            results.append({'url': res_url,
-                            'title': title,
-                            'publishedDate': published_date,
-                            'content': content,
-                            'img_src': img_src})
-
         elif category_to_keyword.get(categories[0], '') == 'news':
             published_date = datetime.fromtimestamp(result['date'], None)
             media = result.get('media', [])
diff --git a/searx/engines/wikidata.py b/searx/engines/wikidata.py
index 60d0dc9a0..8d787caac 100644
--- a/searx/engines/wikidata.py
+++ b/searx/engines/wikidata.py
@@ -161,9 +161,6 @@ def request(query, params):
 
 def response(resp):
     results = []
-    if resp.status_code != 200:
-        logger.debug('SPARQL endpoint error %s', resp.content.decode())
-    resp.raise_for_status()
     jsonresponse = loads(resp.content.decode())
 
     language = resp.search_params['language'].lower()
diff --git a/searx/engines/wikipedia.py b/searx/engines/wikipedia.py
index 000e1af76..54d75108e 100644
--- a/searx/engines/wikipedia.py
+++ b/searx/engines/wikipedia.py
@@ -14,6 +14,7 @@ from urllib.parse import quote
 from json import loads
 from lxml.html import fromstring
 from searx.utils import match_language, searx_useragent
+from searx.raise_for_httperror import raise_for_httperror
 
 # search-url
 search_url = 'https://{language}.wikipedia.org/api/rest_v1/page/summary/{title}'
@@ -37,7 +38,7 @@ def request(query, params):
                                       language=url_lang(params['language']))
 
     params['headers']['User-Agent'] = searx_useragent()
-    params['raise_for_status'] = False
+    params['raise_for_httperror'] = False
     params['soft_max_redirects'] = 2
 
     return params
@@ -47,6 +48,7 @@ def request(query, params):
 def response(resp):
     if resp.status_code == 404:
         return []
+    raise_for_httperror(resp)
 
     results = []
     api_result = loads(resp.text)