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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""pypi.org
"""
from urllib.parse import urlencode
from dateutil import parser
from lxml import html
from searx.utils import (
eval_xpath_getindex,
eval_xpath_list,
extract_text,
)
# about
about = {
"website": "https://pypi.org",
"wikidata_id": "Q2984686",
"official_api_documentation": "https://warehouse.readthedocs.io/api-reference/index.html",
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
categories = ['it', 'packages']
# engine dependent config
first_page_num = 1
base_url = "https://pypi.org"
search_url = base_url + '/search/?{query}'
def request(query, params):
args = {
"q": query,
"page": params['pageno'],
}
params['url'] = search_url.format(query=urlencode(args))
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
for entry in eval_xpath_list(dom, '/html/body/main/div/div/div/form/div/ul/li/a[@class="package-snippet"]'):
url = base_url + extract_text(eval_xpath_getindex(entry, './@href', 0)) # type: ignore
title = extract_text(eval_xpath_getindex(entry, './h3/span[@class="package-snippet__name"]', 0))
version = extract_text(eval_xpath_getindex(entry, './h3/span[@class="package-snippet__version"]', 0))
created_at = extract_text(
eval_xpath_getindex(entry, './h3/span[@class="package-snippet__created"]/time/@datetime', 0)
)
content = extract_text(eval_xpath_getindex(entry, './p', 0))
results.append(
{
"template": "packages.html",
"url": url,
"title": title,
'package_name': title,
"content": content,
"version": version,
'publishedDate': parser.parse(created_at), # type: ignore
}
)
return results
|
