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
|
"""
Bing (Images)
@website https://www.bing.com/images
@provide-api yes (http://datamarket.azure.com/dataset/bing/search),
max. 5000 query/month
@using-api no (because of query limit)
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, img_src
"""
from lxml import html
from json import loads
import re
from searx.url_utils import urlencode
from searx.utils import match_language
# engine dependent config
categories = ['images']
paging = True
safesearch = True
time_range_support = True
language_support = True
supported_languages_url = 'https://www.bing.com/account/general'
number_of_results = 28
# search-url
base_url = 'https://www.bing.com/'
search_string = 'images/search'\
'?{query}'\
'&count={count}'\
'&first={first}'\
'&FORM=IBASEP'
time_range_string = '&qft=+filterui:age-lt{interval}'
time_range_dict = {'day': '1440',
'week': '10080',
'month': '43200',
'year': '525600'}
# safesearch definitions
safesearch_types = {2: 'STRICT',
1: 'DEMOTE',
0: 'OFF'}
# do search-request
def request(query, params):
offset = ((params['pageno'] - 1) * number_of_results) + 1
search_path = search_string.format(
query=urlencode({'q': query}),
count=number_of_results,
first=offset)
language = match_language(params['language'], supported_languages, language_aliases).lower()
params['cookies']['SRCHHPGUSR'] = \
'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
params['cookies']['_EDGE_S'] = 'mkt=' + language +\
'&ui=' + language + '&F=1'
params['url'] = base_url + search_path
if params['time_range'] in time_range_dict:
params['url'] += time_range_string.format(interval=time_range_dict[params['time_range']])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath('//div[@class="imgpt"]'):
img_format = result.xpath('./div[contains(@class, "img_info")]/span/text()')[0]
# Microsoft seems to experiment with this code so don't make the path too specific,
# just catch the text section for the first anchor in img_info assuming this to be
# the originating site.
source = result.xpath('./div[contains(@class, "img_info")]//a/text()')[0]
try:
m = loads(result.xpath('./a/@m')[0])
# strip 'Unicode private use area' highlighting, they render to Tux
# the Linux penguin and a standing diamond on my machine...
title = m.get('t', '').replace(u'\ue000', '').replace(u'\ue001', '')
results.append({'template': 'images.html',
'url': m['purl'],
'thumbnail_src': m['turl'],
'img_src': m['murl'],
'content': '',
'title': title,
'source': source,
'img_format': img_format})
except:
continue
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
supported_languages = []
dom = html.fromstring(resp.text)
regions_xpath = '//div[@id="region-section-content"]' \
+ '//ul[@class="b_vList"]/li/a/@href'
regions = dom.xpath(regions_xpath)
for region in regions:
code = re.search('setmkt=[^\&]+', region).group()[7:]
if code == 'nb-NO':
code = 'no-NO'
supported_languages.append(code)
return supported_languages
|
