代碼：

from __future__ import print_function

import logging
import os.path
import six
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))

    # check and process input arguments
    if len(sys.argv) != 3:
        print("Using: python process_wiki.py enwiki.xxx.xml.bz2 wiki.en.text")
        sys.exit(1)
    inp, outp = sys.argv[1:3]
    space = b" "
    i = 0

    output = open(outp, 'w')
    wiki = WikiCorpus(inp, lemmatize=False, dictionary={})
    for text in wiki.get_texts():
        if six.PY3:
            output.write(bytes(' '.join(text), 'utf-8').decode('utf-8') + '\n')
        #   ###another method###
        #    output.write(
        #            space.join(map(lambda x:x.decode("utf-8"), text)) + '\n')
        else:
            output.write(space.join(text) + "\n")
        i = i + 1
        if (i % 10000 == 0):
            logger.info("Saved " + str(i) + " articles")

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

報(bào)錯(cuò)信息

raceback (most recent call last):
  File "C:/Users/root/PycharmProjects/AI/super/ALP/process.py", line 28, in <module>
    for text in wiki.get_texts():
  File "C:\soft\anaconda\lib\site-packages\gensim\corpora\wikicorpus.py", line 369, in get_texts
    for group in utils.chunkize(texts, chunksize=10 * self.processes, maxsize=1):
  File "C:\soft\anaconda\lib\site-packages\gensim\utils.py", line 863, in chunkize
    for chunk in chunkize_serial(corpus, chunksize, as_numpy=as_numpy):
  File "C:\soft\anaconda\lib\site-packages\gensim\utils.py", line 816, in chunkize_serial
    wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
  File "C:\soft\anaconda\lib\site-packages\gensim\corpora\wikicorpus.py", line 361, in <genexpr>
    ((text, self.lemmatize, title, pageid, tokenization_params)
  File "C:\soft\anaconda\lib\site-packages\gensim\corpora\wikicorpus.py", line 212, in extract_pages
    elem = next(elems)
  File "C:\soft\anaconda\lib\site-packages\gensim\corpora\wikicorpus.py", line 206, in <genexpr>
    elems = (elem for _, elem in iterparse(f, events=("end",)))
  File "C:\soft\anaconda\lib\xml\etree\ElementTree.py", line 1223, in iterator
    data = source.read(16 * 1024)
  File "C:\soft\anaconda\lib\bz2.py", line 182, in read
    return self._buffer.read(size)
  File "C:\soft\anaconda\lib\_compression.py", line 68, in readinto
    data = self.read(len(byte_view))
  File "C:\soft\anaconda\lib\_compression.py", line 103, in read
    data = self._decompressor.decompress(rawblock, size)
OSError: Invalid data stream

Process finished with exit code 1