python语词分析_shell：使用python脚本分析文本关键词密度

需要一个Python脚本

import syssys.path.append('../')import jiebaimport jieba.analysefrom optparse import OptionParserUSAGE = "usage:    python extract_tags_with_weight.py [file name] -k [top k] -w [with weight=1 or 0]"parser = OptionParser(USAGE)parser.add_option("-k", dest="topK")parser.add_option("-w", dest="withWeight")opt, args = parser.parse_args()if len(args) < 1:    print(USAGE)    sys.exit(1)file_name = args[0]if opt.topK is None:    topK = 10else:    topK = int(opt.topK)if opt.withWeight is None:    withWeight = Falseelse:    if int(opt.withWeight) is 1:        withWeight = True    else:        withWeight = Falsecontent = open(file_name, 'rb').read()tags = jieba.analyse.extract_tags(content, topK=topK, withWeight=withWeight)if withWeight is True:    for tag in tags:        print("tag: %s\t\t weight: %f" % (tag[0],tag[1]))else:    print(",".join(tags))

自己去复制，保存.py格式。如：extract_tags.py