diff options
Diffstat (limited to 'searx/engines/qwant.py')
| -rw-r--r-- | searx/engines/qwant.py | 27 |
1 files changed, 16 insertions, 11 deletions
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', []) |