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
|
# Doku Wiki
#
# @website https://www.dokuwiki.org/
# @provide-api yes
# (https://www.dokuwiki.org/devel:xmlrpc)
#
# @using-api no
# @results HTML
# @stable yes
# @parse (general) url, title, content
from urllib import urlencode
from lxml.html import fromstring
from searx.engines.xpath import extract_text
from datetime import datetime
# engine dependent config
categories = ['general'] # TODO , 'images', 'music', 'videos', 'files'
paging = False
language_support = False
number_of_results = 5
# search-url
# Doku is OpenSearch compatible
base_url = 'http://dev.ryzom.com'
search_url = '/search?wiki_pages=1&{query}'
#search_url = '/wikhan/?do=search'\
# '&{query}'
# TODO '&startRecord={offset}'\
# TODO '&maximumRecords={limit}'\
# do search-request
def request(query, params):
params['url'] = base_url +\
search_url.format(query=urlencode({'q': query}))
return params
# get response from search-request
def response(resp):
results = []
doc = fromstring(resp.text)
# parse results
# Quickhits
i = 0
for r in doc.xpath('//dl[@id="search-results"]/dt'):
try:
res_url = r.xpath('.//a/@href')[-1]
except:
continue
if not res_url:
continue
title = extract_text(r.xpath('.//a'))
i = i + 1
y = 0
for s in doc.xpath('//dl[@id="search-results"]/dd'):
y = y + 1
if y == i:
content = extract_text(s.xpath('.//span[@class="description"]'))
dataBrut = extract_text(s.xpath('.//span[@class="author"]'))
data = dataBrut.split(' ')
date = data[0].split('/')
# append result
results.append({'title': title,
'content': content,
'url': base_url + res_url,
'publishedDate': datetime(int(date[2]), int(date[0]), int(date[1]), 0, 0, 0)})
# append result
#results.append({'content': content})
# Search results
#for r in doc.xpath('//dl[@class="search_results"]/*'):
# try:
# if r.tag == "dt":
# res_url = r.xpath('.//a[@class="wikilink1"]/@href')[-1]
# title = extract_text(r.xpath('.//a[@class="wikilink1"]/@title'))
# elif r.tag == "dd":
# content = extract_text(r.xpath('.'))
# append result
# results.append({'title': title,
# 'content': content,
# 'url': base_url + res_url})
# except:
# continue
# if not res_url:
# continue
# return results
return results
|
