kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-22 12:10:11 +01:00
Code

[fix] duckduckgo paging - closes #1677

Browse Source
This commit is contained in:
Adam Tauber 2019-10-14 13:52:15 +02:00
parent 8e62f7600f
commit 94ea9d6622
1 changed files with 26 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
searx/engines/duckduckgo.py
View File

@ -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
@ -91,7 +106,9 @@ def response(resp):
doc = fromstring(resp.text)
# parse results
for r in doc.xpath(result_xpath):
for i,r in enumerate(doc.xpath(result_xpath)):
if i >= 30:
break
try:
res_url = r.xpath(url_xpath)[-1]
except: