aboutsummaryrefslogtreecommitdiffstats
path: root/python/sandcrawler_worker.py
blob: 26735ce269b10ef46dfd10cc75803131c1c24525 (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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
#!/usr/bin/env python3

"""
These are generally for continuously running workers that consume from Kafka.
Outputs might either be pushed back into Kafka, or directly into sandcrawler-db
or minio.
"""

import os
import sys
import argparse
import datetime
import raven

from sandcrawler import *

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


def run_grobid_extract(args):
    consume_topic = "sandcrawler-{}.ungrobided-pg".format(args.env)
    produce_topic = "sandcrawler-{}.grobid-output-pg".format(args.env)
    sink = KafkaSink(
        kafka_hosts=args.kafka_hosts,
        produce_topic=produce_topic,
    )
    grobid_client = GrobidClient(
        host_url=args.grobid_host,
    )
    wayback_client = WaybackClient(
        host_url=args.grobid_host,
    )
    worker = GrobidWorker(
        grobid_client=grobid_client,
        wayback_client=wayback_client,
        sink=sink,
    )
    pusher = KafkaJsonPusher(
        worker=worker,
        kafka_hosts=args.kafka_hosts,
        consume_topic=consume_topic,
        group="grobid-extract",
    )
    pusher.run()

def run_persist_grobid(args):
    consume_topic = "sandcrawler-{}.grobid-output-pg".format(args.env)
    worker = PersistGrobidWorker(
        db_url=args.db_url,
        s3_url=args.s3_url,
        s3_bucket=args.s3_bucket,
        s3_access_key=args.s3_access_key,
        s3_secret_key=args.s3_secret_key,
        s3_only=args.s3_only,
    )
    pusher = KafkaJsonPusher(
        worker=worker,
        kafka_hosts=args.kafka_hosts,
        consume_topic=consume_topic,
        group="persist-grobid",
        push_batches=True,
        batch_size=25,
    )
    pusher.run()

def run_ingest_file(args):
    consume_topic = "sandcrawler-{}.ingest-file-requests".format(args.env)
    produce_topic = "sandcrawler-{}.ingest-file-results".format(args.env)
    sink = KafkaSink(
        kafka_hosts=args.kafka_hosts,
        produce_topic=produce_topic,
    )
    grobid_client = GrobidClient(
        host_url=args.grobid_host,
    )
    worker = IngestFileWorker(
        grobid_client=grobid_client,
        sink=sink,
    )
    pusher = KafkaJsonPusher(
        worker=worker,
        kafka_hosts=args.kafka_hosts,
        consume_topic=consume_topic,
        group="ingest-file",
        batch_size=1,
    )
    pusher.run()

def run_persist_ingest_file(args):
    consume_topic = "sandcrawler-{}.ingest-file-results".format(args.env)
    worker = PersistIngestFileResultWorker(
        db_url=args.db_url,
    )
    pusher = KafkaJsonPusher(
        worker=worker,
        kafka_hosts=args.kafka_hosts,
        consume_topic=consume_topic,
        group="persist-ingest",
        push_batches=True,
        batch_size=100,
    )
    pusher.run()

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('--grobid-host',
        default="http://grobid.qa.fatcat.wiki",
        help="GROBID API host/port")
    parser.add_argument('--db-url',
        help="postgresql database connection string",
        default="postgres:///sandcrawler")
    parser.add_argument('--s3-url',
        help="S3 (minio) backend URL",
        default="localhost:9000")
    parser.add_argument('--s3-access-key',
        help="S3 (minio) credential",
        default=os.environ.get('MINIO_ACCESS_KEY'))
    parser.add_argument('--s3-secret-key',
        help="S3 (minio) credential",
        default=os.environ.get('MINIO_SECRET_KEY'))
    parser.add_argument('--s3-bucket',
        help="S3 (minio) bucket to persist into",
        default="sandcrawler-dev")
    subparsers = parser.add_subparsers()

    sub_grobid_extract = subparsers.add_parser('grobid-extract',
        help="daemon that consumes CDX JSON objects from Kafka, extracts, pushes to Kafka")
    sub_grobid_extract.set_defaults(func=run_grobid_extract)

    sub_persist_grobid = subparsers.add_parser('persist-grobid',
        help="daemon that consumes GROBID output from Kafka and pushes to minio and postgres")
    sub_persist_grobid.add_argument('--s3-only',
        action='store_true',
        help="only upload TEI-XML to S3 (don't write to database)")
    sub_persist_grobid.set_defaults(func=run_persist_grobid)

    sub_ingest_file = subparsers.add_parser('ingest-file',
        help="daemon that consumes requests from Kafka, ingests, pushes results to Kafka")
    sub_ingest_file.set_defaults(func=run_ingest_file)

    sub_persist_ingest_file = subparsers.add_parser('persist-ingest-file',
        help="daemon that consumes ingest-file output from Kafka and pushes to postgres")
    sub_persist_ingest_file.set_defaults(func=run_persist_ingest_file)

    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()