urls = []
url = ""
state = "start"
for b in open("big5-with-urls.txt", "rb").read():
    if state == "start" and b == "\x0A":
        state = "url"
    elif state == "url":
        if b in "\x0A\x0D":
            state = "start"
            url = ""
        elif b == "\x00":
            state = "appendurl"
        else:
            url += b
    elif state == "appendurl":
        if b == "\x00":
            state = "start"
            urls.append(url)
            url = ""
        else:
            state = "start"
            url = ""
urlfile = open("big5urls.txt", "wb")
for url in urls:
    urlfile.write(url + "\n")
