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
141
142
143
144
145
146
|
# -*- coding: utf-8 -*-
# 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 = 'https://khaganat.net'
search_url = '/forum/index.php?action=search2&{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({'search': query}))
return params
# get response from search-request
def response(resp):
results = []
doc = fromstring(resp.text)
# parse results
# Quickhits
for r in doc.xpath('//div[@id="main_content_section"]/div/div/div'):
try:
res_url = r.xpath('.//div[@class="topic_details floatleft"]/h5/a/@href')[-1]
except:
continue
if not res_url:
continue
try:
title = extract_text(r.xpath('.//div[@class="topic_details floatleft"]/h5'))
except:
continue
try:
content = extract_text(r.xpath('.//div[@class="list_posts double_height"]'))
except:
content = ""
try:
dateBrut = extract_text(r.xpath('.//div[@class="topic_details floatleft"]/span/em')).encode('utf-8')
except:
dateBrut = "01 janvier 1970 à 01:01:01".encode('utf-8')
date = dateBrut.split(' ')
year = date[2]
day = date[0]
french_text_month = date[1]
time = date[4]
#dataBrut = extract_text(r.xpath('.//span[@class="date"]'))
#data = dataBrut.split('-')
#date = '-'.join(dataS)
#adatetime = data[1]
#data = adatetime.split(',')
#date = data[1]
#Thedate = dataBrut.split(' ')
#TheDay = Thedate[1].split(',')
if french_text_month == "janvier":
Month = 1
elif french_text_month.decode('utf-8') == "février".decode('utf-8'):
Month = 2
elif french_text_month == "mars":
Month = 3
elif french_text_month == "avril":
Month = 4
elif french_text_month == "mai":
Month = 5
elif french_text_month == "juin":
Month = 6
elif french_text_month == "juillet":
Month = 7
elif french_text_month.decode('utf-8') == "août".decode('utf-8'):
Month = 8
elif french_text_month == "septembre":
Month = 9
elif french_text_month == "octobre":
Month = 10
elif french_text_month == "novembre":
Month = 11
else:
Month = 12
# append result
results.append({'title': title,
'content': content,
'url': res_url,
'publishedDate': datetime(int(year), Month, int(day), 3, 1, 42)})
# 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
|
