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
|
#!/usr/bin/env python
"""
BASE (Scholar publications)
@website https://base-search.net
@provide-api yes with authorization (https://api.base-search.net/)
@using-api yes
@results XML
@stable ?
@parse url, title, publishedDate, content
More info on api: http://base-search.net/about/download/base_interface.pdf
"""
from urllib.parse import urlencode
from lxml import etree
from datetime import datetime
import re
from searx.utils import searx_useragent
categories = ['science']
base_url = 'https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi'\
+ '?func=PerformSearch&{query}&boost=oa&hits={hits}&offset={offset}'
# engine dependent config
paging = True
number_of_results = 10
# shortcuts for advanced search
shorcut_dict = {
# user-friendly keywords
'format:': 'dcformat:',
'author:': 'dccreator:',
'collection:': 'dccollection:',
'hdate:': 'dchdate:',
'contributor:': 'dccontributor:',
'coverage:': 'dccoverage:',
'date:': 'dcdate:',
'abstract:': 'dcdescription:',
'urls:': 'dcidentifier:',
'language:': 'dclanguage:',
'publisher:': 'dcpublisher:',
'relation:': 'dcrelation:',
'rights:': 'dcrights:',
'source:': 'dcsource:',
'subject:': 'dcsubject:',
'title:': 'dctitle:',
'type:': 'dcdctype:'
}
def request(query, params):
# replace shortcuts with API advanced search keywords
for key in shorcut_dict.keys():
query = re.sub(key, shorcut_dict[key], query)
# basic search
offset = (params['pageno'] - 1) * number_of_results
string_args = dict(query=urlencode({'query': query}),
offset=offset,
hits=number_of_results)
params['url'] = base_url.format(**string_args)
params['headers']['User-Agent'] = searx_useragent()
return params
def response(resp):
results = []
search_results = etree.XML(resp.content)
for entry in search_results.xpath('./result/doc'):
content = "No description available"
date = datetime.now() # needed in case no dcdate is available for an item
for item in entry:
if item.attrib["name"] == "dchdate":
harvestDate = item.text
elif item.attrib["name"] == "dcdate":
date = item.text
elif item.attrib["name"] == "dctitle":
title = item.text
elif item.attrib["name"] == "dclink":
url = item.text
elif item.attrib["name"] == "dcdescription":
content = item.text[:300]
if len(item.text) > 300:
content += "..."
# dates returned by the BASE API are not several formats
publishedDate = None
for date_format in ['%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%d', '%Y-%m', '%Y']:
try:
publishedDate = datetime.strptime(date, date_format)
break
except:
pass
if publishedDate is not None:
res_dict = {'url': url,
'title': title,
'publishedDate': publishedDate,
'content': content}
else:
res_dict = {'url': url,
'title': title,
'content': content}
results.append(res_dict)
return results
|
