python自动化与文档处理（word, excel, html）3个小程序

python自动化办公常用库

• pandas 数据处理
• os 文件处理
• bs4 爬虫
• office 文档处理

1、将word试卷转为excel表格导入考试宝

题目长这样：

代码：

import pandas as pd
import re
from docx import Document
from collections import OrderedDict

doc = Document("1.docx")

black_char = re.compile("[\s\u3000\xa0]+")

chinese_nums_rule = re.compile("[一二三四]、(.+?)\(")
title_rule = re.compile("\d+.")
option_rule = re.compile("\([ABCDEF]\)")
option_rule_search = re.compile("\([ABCDEF]\)[^(]+")

# 保存最终的结构化数据
question_type2data = OrderedDict()
# 从word文档的“一、单项选择题”开始遍历数据
title2options = OrderedDict()
for paragraph in doc.paragraphs[1:]:
    #  去除空白字符,将全角字符转半角字符，并给括号之间调整为中间一个空格
    line = black_char.sub("", paragraph.text).replace(
        "（", "(").replace("）", ")").replace("．", ".").replace("()", "(  )")
    # 对于空白行就直接跳过
    if not line:
        continue
    if title_rule.match(line):
        print("题目", line)
        options = title2options.setdefault(line, [])
    elif option_rule.match(line):
        print("选项", option_rule_search.findall(line))
        options.extend(option_rule_search.findall(line))
    else:
        chinese_nums_match = chinese_nums_rule.match(line)
        if chinese_nums_match:
            # print("题型", chinese_nums_match.group(1))
            question_type = chinese_nums_match.group(1)
            title2options = question_type2data.setdefault(
                question_type, OrderedDict())


result = []
max_options_len = 0
for question_type, title2options in question_type2data.items():
    for title, options in title2options.items():
        result.append([question_type, title, *options])
        options_len = len(options)
        if options_len > max_options_len:
            max_options_len = options_len
            

# print(result)

df = pd.DataFrame(result, columns=["题型", "题目"]+[f"选项{
      
      i}" for i in range(1, max_options_len+1)])
# 题型可以简化下，去掉选择两个字
df['题型'] = df['题型'].str.replace("选择", "")
df.to_excel("result.xlsx", index=False)

运行结果：

附：手动word复制粘贴到txt，替换规则

替换操作（全词匹配）：

正确答案:^p
答案：

答案：C、
答案：C^p解析：

2、bs4处理下载的html文本

from bs4 import BeautifulSoup
import pandas as pd

html = open('activity_show.html',encoding='utf-8')
soup = BeautifulSoup(html,'html.parser')

# 获取所有题目
lst = soup.find_all('div',
    class_= ["testpaper-question", "testpaper-question-choice", "js-testpaper-question"]
)
all = []
for timu in lst :
    tt = []
    
    name = timu.find_all('div', class_ = ["testpaper-question-stem","test001"])
    name = name[0].find('p').contents[0]
    tt.append(name)
    # print(name)
    
    choice = timu.find_all('ul', class_ = ["testpaper-question-choices","js-testpaper-question-list"])[0]
    choice = choice.find_all('li')
    choice2 = []
    for ch in choice:
        tt.append(ch.find('p').contents[0])
        choice2.append(ch.contents[0])
    # print(choice2)
    
    ans = timu.find('strong',class_=["color-success"])
    ans = ans.contents[0]
    tt.append(ans)
    # print(ans)
    all.append(tt)
    print(tt)

# print(all)

df = pd.DataFrame(all, columns=['timu', 'A', 'B', 'C', 'D', 'ans'])
print(df.head())
df.to_excel('benci.xlsx',index=False)


# -i http://pypi.douban.com/simple --trusted-host pypi.douban.com  
# conda activate pytorch
# python html_deal.py

结果如下：

3、将大量word表格导出为excel

1、先新建bat得到当前目录所有文件名

dir /b > rename.txt

2、excel处理后得到重命名.bat，运行即可重命名

3、将word表格导出到excel

import docx
import pandas as pd
import os
# from win32com import client as wc
# 安装 python-docx, docx
# conda activate pytorch
# cd C:/XXX/例子/测试/
# python To_excel.py


def Todocx():
    # word = wc.Dispatch('Word.Application')
    path_list = os.listdir(path)
    doc_list = [os.path.join(path,str(i)) for i in path_list if str(i).endswith('doc')]
    word = wc.Dispatch('Word.Application')
    print(doc_list)
    for path in doc_list:
        print(path)
        save_path = str(path).replace('doc','docx')
        doc = word.Documents.Open(path)
        doc.SaveAs(save_path,12, False, "", True, "", False, False, False, False)
        doc.Close()
        print('{} Save sucessfully '.format(save_path))
    word.Quit()


word_paths = "C:/XXX/例子/测试/"

# convertdoc_docx(word_paths)
wordlist_path = [os.path.join(word_paths,i) for i in os.listdir(word_paths) if str(i).endswith('.docx')]

def GetData_frompath(doc_path):
    '''
     Generate Data form doc_path of word path
    :param doc_path:
    :return: col_keys 列键；
            col_values 列名；
    '''
    document = docx.Document(doc_path)
    col_keys = [] # 获取列名
    col_values = [] # 获取列值
    index_num = 0
    # 添加一个去重机制
    fore_str = ''
    for table in document.tables:
        for row_index,row in enumerate(table.rows):
            for col_index,cell in enumerate(row.cells):
                if fore_str != cell.text:
                    if index_num % 2==0:
                        col_keys.append(cell.text)
                    else:
                        col_values.append(cell.text)
                    fore_str = cell.text
                    index_num +=1
    # col_values[7] = '\t'+col_values[7]
    # col_values[8] = '\t'+col_values[8]
    print(f'col keys is {
      
      col_keys}')
    print(f'col values is {
      
      col_values}')
    return col_keys,col_values


pd_data = []
for index,single_path in enumerate(wordlist_path):
    try:
        col_names,col_values = GetData_frompath(single_path)
    except:
        pass
    if index == 0:
        pd_data.append(col_names)
        pd_data.append(col_values)
    else:
        pd_data.append(col_values)


df = pd.DataFrame(pd_data)
df.to_csv(word_paths+'/result.csv', encoding='utf_8_sig',index=False)