bin/crashreportScraper.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
New commits: commit 6b15decd0acc2c7c0622baba65b9d4c019a4183a Author: Xisco Fauli <[email protected]> AuthorDate: Tue Jun 21 15:40:33 2022 +0200 Commit: Xisco Fauli <[email protected]> CommitDate: Tue Jun 21 23:51:50 2022 +0200 crashreportScraper: encode the url Change-Id: I1f738f017966a6fe48dd9e2cf36dbdf5f50c0cef Reviewed-on: https://gerrit.libreoffice.org/c/core/+/136229 Tested-by: Xisco Fauli <[email protected]> Reviewed-by: Xisco Fauli <[email protected]> diff --git a/bin/crashreportScraper.py b/bin/crashreportScraper.py index 513f5ec7b75d..cad7feead645 100755 --- a/bin/crashreportScraper.py +++ b/bin/crashreportScraper.py @@ -17,6 +17,7 @@ import sys import os import math from datetime import datetime +import urllib.parse def convert_str_to_date(value): value = value.replace('.', '') @@ -194,11 +195,11 @@ if __name__ == '__main__': f.flush() for k, lDate in crashes.items(): - if len(k) < 254 and k not in crashesInFile and '`' not in k: + if k not in crashesInFile: print("Parsing " + k) try: crashCount, crashID, crashVersion, crashOS = parse_reports_and_get_most_recent_report_from_last_page( - "https://crashreport.libreoffice.org/stats/signature/"; + k) + "https://crashreport.libreoffice.org/stats/signature/"; + urllib.parse.quote(k)) crashReason, crashStack, codeLine = parse_details_and_get_info( "https://crashreport.libreoffice.org/stats/crash_details/"; + crashID, args.repository) line = '\t'.join([k, str(crashCount), lDate[1], lDate[2],
