searching_for_books.py

# Object for handling xml
handler = WikiXmlHandler()
# Parsing object
parser = xml.sax.make_parser()
parser.setContentHandler(handler)
start = timer()
# Parse the entire file
for line in subprocess.Popen(['bzcat'], 
                             stdin = open(data_path), 
                             stdout = subprocess.PIPE).stdout:
    try:
        parser.feed(line)
    except StopIteration:
        break
    
end = timer()
books = handler._books

print(f'\nSearched through {handler._article_count} articles.')
print(f'\nFound {len(books)} books in {round(end - start)} seconds.')