Use fetch.sh to grab the WARCC-file (https://archive.org/download/yahoo-groups-2017-09-03T05-35-21Z-4c3880/macromediadirector_group.RmKlqJY.warc.gz)
Run repair-mbox.py with new outputed as argument to fix the mailbox to useable mailbox for importing into Thunderbird:
python3 repair-mbox.py macromediadirector_group.RmKlqJY.mbox| #!/bin/sh | |
| url=$1 | |
| basename=${url##*/} | |
| newname=${basename%.*}.mbox | |
| curl -sL $1 | | |
| zcat | grep '^\{' | jq -c 'select(.rawEmail)' | jq -r .rawEmail | | |
| perl -MHTML::Entities -pe ' | |
| s/\r//; | |
| decode_entities $_; | |
| /^([-\w]+): \S/; | |
| ' > $newname |
| #!/usr/bin/env python3 | |
| import time | |
| import sys | |
| import re | |
| from pathlib import Path | |
| def main(input, output): | |
| file = open(input, "rb+") | |
| s = file.read() | |
| file.close() | |
| fixed = re.sub( | |
| rb"Return-Path:.*", | |
| b"From MAILER-DAEMON " + time.asctime(time.gmtime()).encode(), | |
| s, | |
| ) | |
| file = open(output, "wb+") | |
| file.write(fixed) | |
| file.close() | |
| if __name__ == "__main__": | |
| output_file = Path(sys.argv[1]).stem + "-fixed.mbox" | |
| # takes file.mbox as input and outputs file-fixed.mbox | |
| main(sys.argv[1], output_file) |