diff options
author | Markus Heiser <markus.heiser@darmarIT.de> | 2019-12-24 17:45:13 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2019-12-24 17:45:13 +0100 |
commit | ecb054a7a058a1f62a536e5cac88eed8926b107d (patch) | |
tree | 925594876f18580732d2c8a438ff8f3bea8d9092 /searx/engines/duckduckgo.py | |
parent | cc8d4b958e274eb9e154db5c319d2e50da561d61 (diff) | |
parent | 5a0a66e9bc34af2b6404231efc7cf02f389bdfcb (diff) | |
download | searxng-ecb054a7a058a1f62a536e5cac88eed8926b107d.tar.gz searxng-ecb054a7a058a1f62a536e5cac88eed8926b107d.zip |
Merge branch 'master' into patch-1
Diffstat (limited to 'searx/engines/duckduckgo.py')
-rw-r--r-- | searx/engines/duckduckgo.py | 43 |
1 files changed, 30 insertions, 13 deletions
diff --git a/searx/engines/duckduckgo.py b/searx/engines/duckduckgo.py index fb8f523ac..0d2c0af2d 100644 --- a/searx/engines/duckduckgo.py +++ b/searx/engines/duckduckgo.py @@ -18,7 +18,7 @@ from json import loads from searx.engines.xpath import extract_text from searx.poolrequests import get from searx.url_utils import urlencode -from searx.utils import match_language +from searx.utils import match_language, eval_xpath # engine dependent config categories = ['general'] @@ -65,21 +65,36 @@ def get_region_code(lang, lang_list=[]): def request(query, params): - if params['time_range'] and params['time_range'] not in time_range_dict: + if params['time_range'] not in (None, 'None', '') and params['time_range'] not in time_range_dict: return params offset = (params['pageno'] - 1) * 30 region_code = get_region_code(params['language'], supported_languages) - if region_code: - params['url'] = url.format( - query=urlencode({'q': query, 'kl': region_code}), offset=offset, dc_param=offset) + params['url'] = 'https://duckduckgo.com/html/' + if params['pageno'] > 1: + params['method'] = 'POST' + params['data']['q'] = query + params['data']['s'] = offset + params['data']['dc'] = 30 + params['data']['nextParams'] = '' + params['data']['v'] = 'l' + params['data']['o'] = 'json' + params['data']['api'] = '/d.js' + if params['time_range'] in time_range_dict: + params['data']['df'] = time_range_dict[params['time_range']] + if region_code: + params['data']['kl'] = region_code else: - params['url'] = url.format( - query=urlencode({'q': query}), offset=offset, dc_param=offset) + if region_code: + params['url'] = url.format( + query=urlencode({'q': query, 'kl': region_code}), offset=offset, dc_param=offset) + else: + params['url'] = url.format( + query=urlencode({'q': query}), offset=offset, dc_param=offset) - if params['time_range'] in time_range_dict: - params['url'] += time_range_url.format(range=time_range_dict[params['time_range']]) + if params['time_range'] in time_range_dict: + params['url'] += time_range_url.format(range=time_range_dict[params['time_range']]) return params @@ -91,17 +106,19 @@ def response(resp): doc = fromstring(resp.text) # parse results - for r in doc.xpath(result_xpath): + for i, r in enumerate(eval_xpath(doc, result_xpath)): + if i >= 30: + break try: - res_url = r.xpath(url_xpath)[-1] + res_url = eval_xpath(r, url_xpath)[-1] except: continue if not res_url: continue - title = extract_text(r.xpath(title_xpath)) - content = extract_text(r.xpath(content_xpath)) + title = extract_text(eval_xpath(r, title_xpath)) + content = extract_text(eval_xpath(r, content_xpath)) # append result results.append({'title': title, |