aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_harvest.py
blob: 4c4f34a182311921b6822d2257681cc4f7cc3de9 (plain)
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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
#!/usr/bin/env python3

import sys
import argparse
import datetime
import raven
from fatcat_tools.harvest import HarvestCrossrefWorker, HarvestDataciteWorker,\
    HarvestArxivWorker, HarvestPubmedWorker, HarvestDoajArticleWorker,\
    HarvestDoajJournalWorker, PubmedFTPWorker

# Yep, a global. Gets DSN from `SENTRY_DSN` environment variable
sentry_client = raven.Client()


def run_crossref(args):
    worker = HarvestCrossrefWorker(
        kafka_hosts=args.kafka_hosts,
        produce_topic="fatcat-{}.api-crossref".format(args.env),
        state_topic="fatcat-{}.api-crossref-state".format(args.env),
        contact_email=args.contact_email,
        start_date=args.start_date,
        end_date=args.end_date)
    worker.run(continuous=args.continuous)

def run_datacite(args):
    worker = HarvestDataciteWorker(
        kafka_hosts=args.kafka_hosts,
        produce_topic="fatcat-{}.api-datacite".format(args.env),
        state_topic="fatcat-{}.api-datacite-state".format(args.env),
        contact_email=args.contact_email,
        start_date=args.start_date,
        end_date=args.end_date)
    worker.run(continuous=args.continuous)

def run_arxiv(args):
    worker = HarvestArxivWorker(
        kafka_hosts=args.kafka_hosts,
        produce_topic="fatcat-{}.oaipmh-arxiv".format(args.env),
        state_topic="fatcat-{}.oaipmh-arxiv-state".format(args.env),
        start_date=args.start_date,
        end_date=args.end_date)
    worker.run(continuous=args.continuous)

def run_pubmed(args):
    # worker = HarvestPubmedWorker(
    #     kafka_hosts=args.kafka_hosts,
    #     produce_topic="fatcat-{}.oaipmh-pubmed".format(args.env),
    #     state_topic="fatcat-{}.oaipmh-pubmed-state".format(args.env),
    #     start_date=args.start_date,
    #     end_date=args.end_date)
    # worker.run(continuous=args.continuous)
    worker = PubmedFTPWorker(
        kafka_hosts=args.kafka_hosts,
        produce_topic="fatcat-{}.ftp-pubmed".format(args.env),
        state_topic="fatcat-{}.ftp-pubmed-state".format(args.env),
        start_date=args.start_date,
        end_date=args.end_date)
    worker.run(continuous=args.continuous)

def run_doaj_article(args):
    worker = HarvestDoajArticleWorker(
        kafka_hosts=args.kafka_hosts,
        produce_topic="fatcat-{}.oaipmh-doaj-article".format(args.env),
        state_topic="fatcat-{}.oaipmh-doaj-article-state".format(args.env),
        start_date=args.start_date,
        end_date=args.end_date)
    worker.run(continuous=args.continuous)

def run_doaj_journal(args):
    worker = HarvestDoajJournalWorker(
        kafka_hosts=args.kafka_hosts,
        produce_topic="fatcat-{}.oaipmh-doaj-journal".format(args.env),
        state_topic="fatcat-{}.oaipmh-doaj-journal-state".format(args.env),
        start_date=args.start_date,
        end_date=args.end_date)
    worker.run(continuous=args.continuous)


def mkdate(raw):
    return datetime.datetime.strptime(raw, "%Y-%m-%d").date()

def main():
    parser = argparse.ArgumentParser(
        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--kafka-hosts',
        default="localhost:9092",
        help="list of Kafka brokers (host/port) to use")
    parser.add_argument('--env',
        default="dev",
        help="Kafka topic namespace to use (eg, prod, qa, dev)")
    parser.add_argument('--start-date',
        default=None, type=mkdate,
        help="begining of harvest period")
    parser.add_argument('--end-date',
        default=None, type=mkdate,
        help="end of harvest period")
    parser.add_argument('--contact-email',
        default="undefined",    # better?
        help="contact email to use in API header")
    parser.add_argument('--continuous',
        action='store_true',
        help="continue harvesting indefinitely in a loop?")
    subparsers = parser.add_subparsers()

    sub_crossref = subparsers.add_parser('crossref',
        help="harvest DOI metadata from Crossref API (JSON)")
    sub_crossref.set_defaults(func=run_crossref)

    sub_datacite = subparsers.add_parser('datacite',
        help="harvest DOI metadata from Datacite API (JSON)")
    sub_datacite.set_defaults(func=run_datacite)

    sub_arxiv = subparsers.add_parser('arxiv',
        help="harvest metadata from arxiv.org OAI-PMH endpoint (XML)")
    sub_arxiv.set_defaults(func=run_arxiv)

    sub_pubmed = subparsers.add_parser('pubmed',
        help="harvest MEDLINE/PubMed metadata from daily FTP updates (XML)")
    sub_pubmed.set_defaults(func=run_pubmed)

    # DOAJ stuff disabled because API range-requests are broken
    #sub_doaj_article = subparsers.add_parser('doaj-article')
    #sub_doaj_article.set_defaults(func=run_doaj_article)
    #sub_doaj_journal = subparsers.add_parser('doaj-journal')
    #sub_doaj_journal.set_defaults(func=run_doaj_journal)

    args = parser.parse_args()
    if not args.__dict__.get("func"):
        print("tell me what to do!")
        sys.exit(-1)
    args.func(args)

if __name__ == '__main__':
    main()