diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-10-19 16:30:20 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-10-19 16:30:20 -0700 |
commit | e5c7645010ed1315a43f9cc0cd20ca192b5e8008 (patch) | |
tree | cf50c444d70010154c97db5714f29d0db4b7657a /python | |
parent | b388be5aff1b074b82a5382c5267a8ab4c9e615b (diff) | |
download | sandcrawler-e5c7645010ed1315a43f9cc0cd20ca192b5e8008.tar.gz sandcrawler-e5c7645010ed1315a43f9cc0cd20ca192b5e8008.zip |
SPN: more verbose status logging
Diffstat (limited to 'python')
-rw-r--r-- | python/sandcrawler/ia.py | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/python/sandcrawler/ia.py b/python/sandcrawler/ia.py index 30ebc77..2d0d068 100644 --- a/python/sandcrawler/ia.py +++ b/python/sandcrawler/ia.py @@ -4,6 +4,7 @@ # pylint: skip-file import os, sys, time +import json import requests import datetime from collections import namedtuple @@ -861,6 +862,7 @@ class SavePageNowClient: # if there was a recent crawl of same URL, fetch the status of that # crawl to get correct datetime if final_json.get('original_job_id'): + print(f" SPN recent capture: {job_id} -> {final_json['original_job_id']}", file=sys.stderr) resp = self.v2_session.get("{}/status/{}".format(self.v2endpoint, final_json['original_job_id'])) try: resp.raise_for_status() @@ -871,6 +873,8 @@ class SavePageNowClient: #print(final_json, file=sys.stderr) if final_json['status'] == "success": + if final_json.get('original_url').startswith('/'): + print(f" truncateded URL in JSON: {request_url} {json.dumps(final_json)}", file=sys.stderr) return SavePageNowResult( True, "success", |