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
|
#!/usr/bin/env python3
"""
Transform an unpaywall dump (JSON) into ingest requests.
"""
import sys
import json
import argparse
import urlcanon
def canon(s):
parsed = urlcanon.parse_url(s)
return str(urlcanon.whatwg(parsed))
def transform_cnki(obj):
requests = []
assert obj['cnki_id']
requests = []
requests.append({
'base_url': canon(obj['info_url']),
'ingest_type': 'pdf',
'link_source': 'cnki_covid19',
'link_source_id': obj['cnki_id'],
'ingest_request_source': 'scrape-covid19',
})
if 'read_url' in obj:
requests.append({
'base_url': canon(obj['read_url']),
'ingest_type': 'pdf', # actually HTML
'link_source': 'cnki_covid19',
'link_source_id': obj['cnki_id'],
'ingest_request_source': 'scrape-covid19',
})
return requests
def transform_wanfang(obj):
assert obj['wanfang_id']
return [{
'base_url': canon(obj['url']),
'ingest_type': 'pdf',
'link_source': 'wanfang_covid19',
'link_source_id': obj['wanfang_id'],
'ingest_request_source': 'scrape-covid19',
}]
def run(args):
for l in args.json_file:
if not l.strip():
continue
row = json.loads(l)
if 'wanfang_id' in row:
requests = transform_wanfang(row) or []
elif 'cnki_id' in row:
requests = transform_cnki(row) or []
else:
continue
for r in requests:
print("{}".format(json.dumps(r, sort_keys=True)))
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('json_file',
help="COVID-19 metadata file to use",
type=argparse.FileType('r'))
subparsers = parser.add_subparsers()
args = parser.parse_args()
run(args)
if __name__ == '__main__':
main()
|