From 7dc382519187e32856f494af76248fa93aef7770 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 3 Nov 2020 19:28:21 -0800
Subject: persist: XML and HTML persist workers

---
 python/sandcrawler_worker.py | 47 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

(limited to 'python/sandcrawler_worker.py')

diff --git a/python/sandcrawler_worker.py b/python/sandcrawler_worker.py
index b62fa80..24dbdd0 100755
--- a/python/sandcrawler_worker.py
+++ b/python/sandcrawler_worker.py
@@ -13,6 +13,7 @@ import datetime
 import raven
 
 from sandcrawler import *
+from sandcrawler.persist import PersistXmlDocWorker, PersistHtmlTeiXmlWorker
 
 # Yep, a global. Gets DSN from `SENTRY_DSN` environment variable
 try:
@@ -148,6 +149,44 @@ def run_persist_thumbnail(args):
     )
     pusher.run()
 
+def run_persist_xml_doc(args: argparse.Namespace) -> None:
+    consume_topic = f"sandcrawler-{args.env}.xml-doc"
+    worker = PersistXmlDocWorker(
+        s3_url=args.s3_url,
+        s3_bucket=args.s3_bucket,
+        s3_access_key=args.s3_access_key,
+        s3_secret_key=args.s3_secret_key,
+    )
+    pusher = KafkaJsonPusher(
+        worker=worker,
+        kafka_hosts=args.kafka_hosts,
+        consume_topic=consume_topic,
+        group="persist-xml-doc",
+        push_batches=False,
+        raw_records=True,
+        batch_size=25,
+    )
+    pusher.run()
+
+def run_persist_html_teixml(args: argparse.Namespace) -> None:
+    consume_topic = f"sandcrawler-{args.env}.html-teixml"
+    worker = PersistHtmlTeiXmlWorker(
+        s3_url=args.s3_url,
+        s3_bucket=args.s3_bucket,
+        s3_access_key=args.s3_access_key,
+        s3_secret_key=args.s3_secret_key,
+    )
+    pusher = KafkaJsonPusher(
+        worker=worker,
+        kafka_hosts=args.kafka_hosts,
+        consume_topic=consume_topic,
+        group="persist-html-teixml",
+        push_batches=False,
+        raw_records=True,
+        batch_size=25,
+    )
+    pusher.run()
+
 def run_persist_pdftrio(args):
     consume_topic = "sandcrawler-{}.pdftrio-output".format(args.env)
     worker = PersistPdfTrioWorker(
@@ -293,6 +332,14 @@ def main():
         help="daemon that consumes thumbnail output from Kafka and pushes to S3 (seaweedfs) and postgres")
     sub_persist_thumbnail.set_defaults(func=run_persist_thumbnail)
 
+    sub_persist_xml_doc = subparsers.add_parser('persist-xml-doc',
+        help="daemon that consumes xml-doc output from Kafka and pushes to S3 (seaweedfs) bucket")
+    sub_persist_xml_doc.set_defaults(func=run_persist_xml_doc)
+
+    sub_persist_html_teixml = subparsers.add_parser('persist-html-teixml',
+        help="daemon that consumes html-teixml output from Kafka and pushes to S3 (seaweedfs) bucket")
+    sub_persist_html_teixml.set_defaults(func=run_persist_html_teixml)
+
     sub_persist_pdftrio = subparsers.add_parser('persist-pdftrio',
         help="daemon that consumes pdftrio output from Kafka and pushes to postgres")
     sub_persist_pdftrio.set_defaults(func=run_persist_pdftrio)
-- 
cgit v1.2.3