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
|
"""
Digg (News, Social media)
@website https://digg.com/
@provide-api no
@using-api no
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, content, publishedDate, thumbnail
"""
from dateutil import parser
from json import loads
from lxml import html
from searx.url_utils import quote_plus
# engine dependent config
categories = ['news', 'social media']
paging = True
# search-url
base_url = 'https://digg.com/'
search_url = base_url + 'api/search/{query}.json?position={position}&format=html'
# specific xpath variables
results_xpath = '//article'
link_xpath = './/small[@class="time"]//a'
title_xpath = './/h2//a//text()'
content_xpath = './/p//text()'
pubdate_xpath = './/time'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 10
params['url'] = search_url.format(position=offset,
query=quote_plus(query))
return params
# get response from search-request
def response(resp):
results = []
search_result = loads(resp.text)
if 'html' not in search_result or search_result['html'] == '':
return results
dom = html.fromstring(search_result['html'])
# parse results
for result in dom.xpath(results_xpath):
url = result.attrib.get('data-contenturl')
thumbnail = result.xpath('.//img')[0].attrib.get('src')
title = ''.join(result.xpath(title_xpath))
content = ''.join(result.xpath(content_xpath))
pubdate = result.xpath(pubdate_xpath)[0].attrib.get('datetime')
publishedDate = parser.parse(pubdate)
# http to https
thumbnail = thumbnail.replace("http://static.digg.com", "https://static.digg.com")
# append result
results.append({'url': url,
'title': title,
'content': content,
'template': 'videos.html',
'publishedDate': publishedDate,
'thumbnail': thumbnail})
# return results
return results
|
