批量统计文档指定高频词

一、背景和功能

 统计2012-2016年间各地级市政府的工作报告中在政治、经济、文化等领域的已指定高频词汇（etc.指定经济类的词汇有发展、经济建设、GDP等）

 其中economy文件打开后如下，

二、存储格式

地级市分年份（不分月份了，没有删掉）

三、数据处理

如果是txt格式文档，可以直接使用，如果是docx格式文档，可以查看我的上一篇文章，有docx批量转txt的代码，转换后就可以直接使用下面的代码。

四、代码

import jieba
import os
import openpyxl

def save_city_year(city_filename, year_num):
    # 打开另一个存储的Excel文件
    outfile = "finaldata.xlsx"
    save_wb = openpyxl.load_workbook(outfile)
    save_sheet = save_wb.active
    # 存储
    year = int(year_num[0:4])
    save_sheet.cell(row=year-2010+5*(city_num-1), column=1, value=city_filename)
    save_sheet.cell(row=year-2010+5*(city_num-1), column=3, value=year)
    # 保存新的Excel文件
    save_wb.save(outfile)

def jiebafenci(txt, year_num, city_num):
    type_num = 0;  # 记录类型数量
    for type_path in os.listdir(r'E:\high_frequency_words'):
        if type_path.endswith('.txt'):
            type_num = type_num+1;
            need_words = open(type_path, encoding="utf-8").read()  # 这个是要查找的词的txt文件 每个词一行
            wordslist = need_words.split()

            jieba.load_userdict(type_path)
            words = jieba.lcut(txt)#要查找的词
            counts = {}
            for word in words:
                counts[word] = counts.get(word, 0) + 1
            lst = []

            # 打开另一个存储的Excel文件
            outfile = "finaldata.xlsx"
            save_wb = openpyxl.load_workbook(outfile)
            save_sheet = save_wb.active

            type_word_num = 0;  # 该类型的词数
            for i in range(len(wordslist)):
                try:
                    # print(wordslist[i], counts[wordslist[i]])
                    type_word_num=type_word_num+counts[wordslist[i]]
                except:
                    lst.append(wordslist[i])
            # print('不存在的词:', lst)
            #存储
            year = int(year_num[0:4])
            save_sheet.cell(row=year-2010+5*(city_num-1), column=type_num+4, value=type_word_num)
            # 保存新的Excel文件
            save_wb.save(outfile)


if __name__ == '__main__':
    root_folder = r'E:\high_frequency_words\地级市政府工作报告'
    city_num=0;
    # 确保指定的文件夹存在
    if not os.path.exists(root_folder):
        print("指定的文件夹不存在。")
    else:
        # 遍历Word文档文件夹中的所有Word文档
        for province_filename in os.listdir(root_folder):
            print(province_filename)
            if province_filename.endswith("省") or province_filename.endswith("市") or province_filename.endswith("区"):
                province_folder = os.path.join(root_folder, province_filename)
                for city_filename in os.listdir(province_folder):
                    if city_filename.endswith("市"):
                        city_num=city_num+1;
                        city_folder = os.path.join(province_folder, city_filename)
                        for txt_name in os.listdir(city_folder):
                            # print(txt_name)
                            if txt_name.endswith('2012.txt') or txt_name.endswith('2013.txt') or txt_name.endswith('2014.txt') or txt_name.endswith('2015.txt') or txt_name.endswith('2016.txt'):
                                txt_path = os.path.join(city_folder, txt_name)
                                # print(txt_path)
                                txt = open(txt_path, encoding="utf-8").read()  # 'wuxi.txt' 更换你的文件（txt格式）
                                jiebafenci(txt, txt_name, city_num)
                                save_city_year(city_filename, txt_name)