批量抽取word文档中的表格

用于抽取word文档中指定表格的指定数据
供学习交流

import pandas as pd
import docx
import os


def get_data_from_path(save_path):
    document = docx.Document(save_path)
    col_keys = [] # 获取列名
    col_values = [] # 获取列值
    i = 0  # 用来筛选指定表格（对于文档中有多个表格的情况）
    for table in document.tables:
        if i == 0:
            i += 1
            continue
        if i > 1 : break
        i += 1
        for row_index, row in enumerate(table.rows):
            for col_index, cell in enumerate(row.cells):
                if row_index > 0:
                    if col_index == 0:
                        col_keys.append(cell.text.replace('\n',''))
                    if col_index == 2:
                        col_values.append(cell.text)
    # print(f'col keys is {col_keys}')
    # print(f'col values is {col_values}')
    return  col_keys, col_values


def docx2csv(wordlist_path, csv_path):
    key, value = get_data_from_path(wordlist_path)
    res = []  # 存txt
    size = len(key)
    for i in range(size):
        txt_temp = key[i] + ',' + value[i].replace('\n', ',')
        txt_temp = txt_temp.split(',')
        res.append(txt_temp)
    df = pd.DataFrame(res)

    df.to_csv(csv_path, encoding='utf_8_sig', index=False, header = None)
    print('3Q')


wordlist_path = 'E:\\数字电子技术.docx'
csv_path = r'E:\1.csv'

docx2csv(wordlist_path, csv_path)

docxs_path = r'E:\电子系课程'  # 文件夹路径

file_list = os.listdir(docxs_path)
print(file_list)
for fl in file_list:
    if not os.path.splitext(fl)[1] == ".docx":  # 筛选文件类型,注意”.“
        continue
    docx_path = os.path.join(docxs_path, fl)  # 文件路径
    csv_name = fl.split('.')[0] + '.csv'  # csv文件名
    csv_path = os.path.join(docxs_path, csv_name)  # 文件路径
    docx2csv(docx_path, csv_path)