#read argv xml file

import sys
import xml.etree.ElementTree as ET
import mwxml

def save_to_txt(title, author, text):
    with open(title + " " + author + ".txt", "w") as f:
        f.write(text)
        
if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python wikidump2txt.py <xml file>")

    xml_file = sys.argv[1]

    dump = mwxml.Dump.from_file(open(xml_file, 'rb'))

    print("size of xml data: ", len(xml_data))

    #parse xml data
    root = ET.fromstring(xml_data)
    for page in root.findall("page"):
        title = page.find("title").text
        text = page.find("text").text
        print(title)
        print(text)
