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
130
131
132
133
134
135
136
137
138
139
140
|
# Google (Web)
#
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/custom-search/)
#
# @using-api no
# @results HTML
# @stable no (HTML can change)
# @parse url, title, content, suggestion
from urllib import urlencode
from urlparse import urlparse, parse_qsl
from lxml import html
from searx.poolrequests import get
from searx.engines.xpath import extract_text, extract_url
# engine dependent config
categories = ['general']
paging = True
language_support = True
# search-url
google_hostname = 'www.google.com'
search_path = '/search'
redirect_path = '/url'
images_path = '/images'
search_url = ('https://' +
google_hostname +
search_path +
'?{query}&start={offset}&gbv=1')
# specific xpath variables
results_xpath = '//li[@class="g"]'
url_xpath = './/h3/a/@href'
title_xpath = './/h3'
content_xpath = './/span[@class="st"]'
suggestion_xpath = '//p[@class="_Bmc"]'
images_xpath = './/div/a'
image_url_xpath = './@href'
image_img_src_xpath = './img/@src'
pref_cookie = ''
# see https://support.google.com/websearch/answer/873?hl=en
def get_google_pref_cookie():
global pref_cookie
if pref_cookie == '':
resp = get('https://www.google.com/ncr', allow_redirects=False)
pref_cookie = resp.cookies["PREF"]
return pref_cookie
# remove google-specific tracking-url
def parse_url(url_string):
parsed_url = urlparse(url_string)
if (parsed_url.netloc in [google_hostname, '']
and parsed_url.path == redirect_path):
query = dict(parse_qsl(parsed_url.query))
return query['q']
else:
return url_string
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 10
if params['language'] == 'all':
language = 'en'
else:
language = params['language'].replace('_', '-').lower()
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}))
params['headers']['Accept-Language'] = language
params['cookies']['PREF'] = get_google_pref_cookie()
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
title = extract_text(result.xpath(title_xpath)[0])
try:
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
parsed_url = urlparse(url)
if (parsed_url.netloc == google_hostname
and parsed_url.path == search_path):
# remove the link to google news
continue
# images result
if (parsed_url.netloc == google_hostname
and parsed_url.path == images_path):
# only thumbnail image provided,
# so skipping image results
# results = results + parse_images(result)
pass
else:
# normal result
content = extract_text(result.xpath(content_xpath)[0])
# append result
results.append({'url': url,
'title': title,
'content': content})
except:
continue
# parse suggestion
for suggestion in dom.xpath(suggestion_xpath):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
# return results
return results
def parse_images(result):
results = []
for image in result.xpath(images_xpath):
url = parse_url(extract_text(image.xpath(image_url_xpath)[0]))
img_src = extract_text(image.xpath(image_img_src_xpath)[0])
# append result
results.append({'url': url,
'title': '',
'content': '',
'img_src': img_src,
'template': 'images.html'})
return results
|
