关于文档处理的各种脚本

  暂时记录,改天再整理

import re
import os
import pandas as pd
from requests import get
from docx import Document
import win32com.client as win
import subprocess

# dir2 = 'C:/Users/User/Documents/gzzw/'
# names = os.listdir(dir2)
# data = {}
# word = win.Dispatch('Word.Application')
# for (i, n) in enumerate(names):
    # subprocess.call(['soffice', '--headless', '--convert-to', 'docx', '--outdir', dir2 + str(i) + '.docx', dir + n])
    # doc = Document(docx=dir2 + n)
    # table = doc.tables[1]
    # row = table.rows[0]
    # row1 = table.rows[1]
    # for k, v in zip(row.cells, row1.cells):
    #     if i == 0:
    #         data[k.text] = [v.text]
    #     else:
    #         data[k.text].append(v.text)
    # gs = re.match(r'.*_(.*)_.*', n)
    # dn.append(gs.group(1))
    # os.rename(dir + n, dir + str(i) + '.doc')
    # doc = word.Documents.Open(dir + n)
    # doc.SaveAs(dir2 + str(i) + '.docx', FileFormat=12)
    # table = doc.Tables(2)
    # for j in range(table.Columns.Count):
        # print(table.Cell(Row=1, Column=i + 1).Range.Text)
        # label.append(table.Cell(Row=1, Column=i + 1).Range.Text.encode('utf8'))
        # dn.append(table.Cell(Row=2, Column=i + 1).Range.Text.encode('utf8'))

# word.Quit()

# sheel = pd.DataFrame(data)
# sheel.to_excel(dir2 + 'statics.xlsx', index=False, encoding='utf8')

  一些参考链接:

    1.https://code.activestate.com/recipes/279003-converting-word-documents-to-text/

    2.https://*.com/questions/1468099/python-win32-extensions-documentation

    3.https://*.com/questions/10366596/how-to-read-contents-of-an-table-in-ms-word-file-using-python

    4.https://*.com/questions/38468442/multiple-doc-to-docx-file-conversion-using-python

    5.https://www.jianshu.com/p/4fa504c720c1

上一篇:如何使用Python从doc / docx文件中提取数据


下一篇:PHP读取Word文档仅获取电子邮件地址