Search in Wikivoyage history dump

wksource.py

#!/usr/bin/python

import sys, re

def check(expr, text):
    res = expr.search(text)
    if res==None:
        return None
    return res.group(1)

def main():
    re_ip = re.compile("<ip>(.*)</ip>")
    re_user = re.compile("<username>(.*)</username>")
    re_timestamp = re.compile("<timestamp>(.*)</timestamp>")
    
    fn = sys.argv[1]
    text = " ".join(sys.argv[2:]).strip()
    if len(text)==0:
        print("No text")
        return
    f = open(fn, "rt")
    ip = None
    user = None
    timestamp = None
    for line in f:
        tmp = check(re_ip, line)
        if tmp!=None:
            ip = tmp
            user = None
            continue
        #
        tmp = check(re_user, line)
        if tmp!=None:
            ip = None
            user = tmp
            continue
        #
        tmp = check(re_timestamp, line)
        if tmp!=None:
            timestamp = tmp
            continue
        #
        if line.find(text)!=-1:
            print("Found: {}, {}".format(ip or user, timestamp))
            return

main()