unwrap wiki

unwrapwiki.py

#-- this script is not my own, I modified it from a Gensim tutorial --#

import logging
import os.path
import sys

from gensim.corpora import WikiCorpus

if __name__ == '__main__':
    program = os.path.basename(sys.argv[0])
    logger = logging.getLogger(program)

    logging.basicConfig(format='%(asctime)s: %(levelname)s: %(message)s')
    logging.root.setLevel(level=logging.INFO)
    logger.info("running %s" % ' '.join(sys.argv))

    inp, outp = sys.argv[1:3]
    space = " "
    i = 0

    output = open(outp, 'w')
    wiki = WikiCorpus(inp, lemmatize=False, dictionary={})
    for text in wiki.get_texts():
        output.write(' '.join(map(lambda t: t.decode('utf-8'), text)) + "\n")
        i = i + 1
        if (i % 10000 == 0):
            logger.info("Saved " + str(i) + " articles")

    output.close()
    logger.info("Finished Saved " + str(i) + " articles")