Created
August 28, 2025 15:23
-
-
Save birkin/270956a8e0a09b18e1a7715b42de9869 to your computer and use it in GitHub Desktop.
warc gist experimentation for tracking downloaded warcs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"files": [ | |
{ | |
"seedId": "seed123", | |
"crawlJobId": "job456", | |
"crawlTimestamp": "20171003231334202", | |
"service": "ARCHIVEIT", | |
"collectionId": 7310, | |
"filePath": "/pairtree/73/10/warcs/20171003231334202-00000.warc.gz", | |
"serialNumber": "00000", | |
"fileFormat": "warc.gz", | |
"crawlDates": ["2017-10-03T23:13:34Z"] | |
}, | |
{ | |
"seedId": "seed123", | |
"crawlJobId": "job456", | |
"crawlTimestamp": "20171003231334202", | |
"service": "ARCHIVEIT", | |
"collectionId": 7310, | |
"filePath": "/pairtree/73/10/warcs/20171003231334202-00001.warc.gz", | |
"serialNumber": "00001", | |
"fileFormat": "warc.gz", | |
"crawlDates": ["2017-10-03T23:13:34Z"] | |
}, | |
{ | |
"seedId": "seed999", | |
"crawlJobId": "job777", | |
"crawlTimestamp": "20181205094510225", | |
"service": "ARCHIVEIT", | |
"collectionId": 10234, | |
"filePath": "/pairtree/102/34/warcs/20181205094510225-00000.warc.gz", | |
"serialNumber": "00000", | |
"fileFormat": "warc.gz", | |
"crawlDates": ["2018-12-05T09:45:10Z"] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment