1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
"""
DuckDuckGo (Web)
@website https://duckduckgo.com/
@provide-api yes (https://duckduckgo.com/api),
but not all results from search-site
@using-api no
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, content
@todo rewrite to api
"""
from lxml.html import fromstring
from json import loads
from searx.utils import extract_text, match_language, eval_xpath
# engine dependent config
categories = ['general']
paging = False
language_support = True
supported_languages_url = 'https://duckduckgo.com/util/u172.js'
time_range_support = True
language_aliases = {
'ar-SA': 'ar-XA',
'es-419': 'es-XL',
'ja': 'jp-JP',
'ko': 'kr-KR',
'sl-SI': 'sl-SL',
'zh-TW': 'tzh-TW',
'zh-HK': 'tzh-HK'
}
# search-url
url = 'https://html.duckduckgo.com/html'
time_range_dict = {'day': 'd',
'week': 'w',
'month': 'm'}
# specific xpath variables
result_xpath = '//div[@class="result results_links results_links_deep web-result "]' # noqa
url_xpath = './/a[@class="result__a"]/@href'
title_xpath = './/a[@class="result__a"]'
content_xpath = './/a[@class="result__snippet"]'
correction_xpath = '//div[@id="did_you_mean"]//a'
# match query's language to a region code that duckduckgo will accept
def get_region_code(lang, lang_list=None):
if lang == 'all':
return None
lang_code = match_language(lang, lang_list or [], language_aliases, 'wt-WT')
lang_parts = lang_code.split('-')
# country code goes first
return lang_parts[1].lower() + '-' + lang_parts[0].lower()
def request(query, params):
if params['time_range'] is not None and params['time_range'] not in time_range_dict:
return params
params['url'] = url
params['method'] = 'POST'
params['data']['b'] = ''
params['data']['q'] = query
params['data']['df'] = ''
region_code = get_region_code(params['language'], supported_languages)
if region_code:
params['data']['kl'] = region_code
params['cookies']['kl'] = region_code
if params['time_range'] in time_range_dict:
params['data']['df'] = time_range_dict[params['time_range']]
return params
# get response from search-request
def response(resp):
results = []
doc = fromstring(resp.text)
# parse results
for i, r in enumerate(eval_xpath(doc, result_xpath)):
if i >= 30:
break
try:
res_url = eval_xpath(r, url_xpath)[-1]
except:
continue
if not res_url:
continue
title = extract_text(eval_xpath(r, title_xpath))
content = extract_text(eval_xpath(r, content_xpath))
# append result
results.append({'title': title,
'content': content,
'url': res_url})
# parse correction
for correction in eval_xpath(doc, correction_xpath):
# append correction
results.append({'correction': extract_text(correction)})
# return results
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
# response is a js file with regions as an embedded object
response_page = resp.text
response_page = response_page[response_page.find('regions:{') + 8:]
response_page = response_page[:response_page.find('}') + 1]
regions_json = loads(response_page)
supported_languages = map((lambda x: x[3:] + '-' + x[:2].upper()), regions_json.keys())
return list(supported_languages)
|
