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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""BPB refers to ``Bundeszentrale für poltische Bildung``, which is a German
governmental institution aiming to reduce misinformation by providing resources
about politics and history.
"""
from datetime import datetime
from urllib.parse import urlencode
about = {
'website': "https://www.bpb.de",
'official_api_documentation': None,
'use_official_api': False,
'require_api_key': False,
'results': 'JSON',
'language': 'de',
}
paging = True
categories = ['general']
base_url = "https://www.bpb.de"
def request(query, params):
args = {
'query[term]': query,
'page': params['pageno'] - 1,
'sort[direction]': 'descending',
'payload[nid]': 65350,
}
params['url'] = f"{base_url}/bpbapi/filter/search?{urlencode(args)}"
return params
def response(resp):
results = []
json_resp = resp.json()
for result in json_resp['teaser']:
img_src = None
if result['teaser']['image']:
img_src = base_url + result['teaser']['image']['sources'][-1]['url']
metadata = result['extension']['overline']
authors = ', '.join(author['name'] for author in result['extension'].get('authors', []))
if authors:
metadata += f" | {authors}"
publishedDate = None
if result['extension'].get('publishingDate'):
publishedDate = datetime.utcfromtimestamp(result['extension']['publishingDate'])
results.append(
{
'url': base_url + result['teaser']['link']['url'],
'title': result['teaser']['title'],
'content': result['teaser']['text'],
'img_src': img_src,
'publishedDate': publishedDate,
'metadata': metadata,
}
)
return results
|
