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
|
#!/usr/bin/env python3
"""
This script takes a "Paper" MAG TSV file which has been joined with (at most) a
single "PaperExtendedAttributes", parses it into JSON, and does fatcat fetches
to "enrich" the output. Outputs a single JSON object per line with attributes:
mag_id
mag_paper
release_id
fatcat_release
Input columns:
"""
import sys
import json
import argparse
import datetime
import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry # pylint: disable=import-error
def requests_retry_session(retries=10, backoff_factor=3,
status_forcelist=(500, 502, 504), session=None):
"""
From: https://www.peterbe.com/plog/best-practice-with-retries-with-requests
"""
session = session or requests.Session()
retry = Retry(
total=retries,
read=retries,
connect=retries,
backoff_factor=backoff_factor,
status_forcelist=status_forcelist,
)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)
return session
def do_line(row, args):
pubmed_id = row.get('pubmed_id') or None
pmcid = row.get('pmcid') or None
doi = row.get('doi') or None
fatcat_release = None
if not fatcat_release and pmcid:
resp = args.session.get('https://api.fatcat.wiki/v0/release/lookup',
params={
'pmcid': pmcid,
'expand': 'container,files,filesets,webcaptures',
'hide': 'abstracts,references',
})
if resp.status_code == 200:
fatcat_release = resp.json()
if not fatcat_release and doi:
resp = args.session.get('https://api.fatcat.wiki/v0/release/lookup',
params={
'doi': doi,
'expand': 'container,files,filesets,webcaptures',
'hide': 'abstracts,references',
})
if resp.status_code == 200:
fatcat_release = resp.json()
if not fatcat_release and pubmed_id:
resp = args.session.get('https://api.fatcat.wiki/v0/release/lookup',
params={
'pmid': pubmed_id,
'expand': 'container,files,filesets,webcaptures',
'hide': 'abstracts,references',
})
if resp.status_code == 200:
fatcat_release = resp.json()
obj = dict(
who_paper=row,
)
if fatcat_release:
obj['fatcat_release'] = fatcat_release
obj['release_id'] = fatcat_release['ident']
obj['fatcat_url'] = "https://fatcat.wiki/release/{}".format(obj['release_id'])
print(json.dumps(obj, sort_keys=True))
def run(args):
for l in sys.stdin:
l = json.loads(l)
do_line(l, args)
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('json_file',
help="WHO/S2 parsed JSON file",
type=argparse.FileType('r'))
subparsers = parser.add_subparsers()
args = parser.parse_args()
args.session = requests_retry_session()
run(args)
if __name__ == '__main__':
main()
|
