import json import jieba.analyse as anl import xlwt # 获取待统计的文本内容 # 打开文件 f = open('zhilian.json', 'r', encoding='utf-8') ans_data = '' for index in range(1867): data = f.readline().replace('},', '}') dict = json.loads(data) ans_data += dict['job_content'] # 关闭文件 f.close() # xls的相关操作 # 新建文件,后面save workbook=xlwt.Workbook(encoding='ascii') # 新建sheet表 worksheet=workbook.add_sheet('python招聘分词') # jieba分词统计ans_data文本中,分词后的频率 seg = anl.extract_tags(ans_data, topK=150, withWeight=True) index = 0 for tag, weight in seg: print("%-20s:%3s %-8s" % (weight, index, tag)) # 写入xls的单元格 worksheet.write(index, 0, label=index + 1) worksheet.write(index, 1, label=tag) worksheet.write(index, 2, label=weight) index += 1 # 保存xls文件 workbook.save('python招聘分词统计.xls')