pyhton Office文档转txt_python将wps转为txt

只能说是网上代码进行优化后的究极缝合怪

import sys
#from win32com.client import Dispatch, constants
from pptx import Presentation
from pptx.util import Cm, Pt
import codecs
import pandas as pd
import win32com.client
import textract
import docx2txt
import docx
def change_doc_to_txt(word_path, save_path):
    word = win32com.client.Dispatch('Word.Application')  # 调用word应用
    doc = word.Documents.Open(word_path)
    print('保存中。。。')
    doc.SaveAs(save_path, 2)  # 保存格式为txt
    doc.Close()
    word.Quit()
def change_docx_to_txt(word_path, save_path):
    print('读取中。。。')
    doc = docx.Document(word_path)
    f = open(save_path, "w")
    for paragraph in doc.paragraphs:
        f.write(paragraph.text)

    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                f.write(cell.text)
    f.close()

def change_ppt_to_txt(word_path, save_path):
    #兼容ppt和pptx
    # ppt = win32com.client.Dispatch('PowerPoint.Application')
    # pptSel = ppt.Presentations.Open(word_path, Untitled=0, WithWindow=0)
    # print('读取中。。。')
    #
    # f = open(save_path, "w")
    # slide_count = pptSel.Slides.Count
    # for i in range(1, slide_count + 1):
    #
    #     shape_count = pptSel.Slides(i).Shapes.Count
    #
    #     for j in range(1, shape_count + 1):
    #
    #         if pptSel.Slides(i).Shapes(j).HasTextFrame:
    #             s = pptSel.Slides(i).Shapes(j).TextFrame.TextRange.Text
    #             f.write(s)
    #
    # f.close()
    # pptSel.Close()
    # ppt.Quit()
    #只能解ppt
    prs = Presentation(word_path)
    f = open(save_path, "w")
    # 获取slide幻灯片
    for slide in prs.slides:
        # 获取形状shape
        for shape in slide.shapes:
            if shape.has_text_frame:  # 判断是否有文字
                text_frame = shape.text_frame  # 获取文字框
                f.write(text_frame.text)
                # 从shape中找段落paragraphs
                for paragraph in text_frame.paragraphs:
                    f.write(paragraph.text)

    f.close()

def change_xls_to_txt(word_path, save_path):
    # 读取excel保存成txt格式，xls和xlsx都可以
    excel_file = pd.read_excel(word_path)
    excel_file.to_csv(save_path, sep=' ', index=False)

if __name__ == '__main__':
    try:
        if len(sys.argv)==3:
            readPath = sys.argv[1]
            type = sys.argv[2]
            savePath = readPath+'.txt'
            if type=='1':
                change_doc_to_txt(readPath, savePath)
            elif type=='2':
                change_docx_to_txt(readPath, savePath)
            elif type =='3':
                change_xls_to_txt(readPath, savePath)
            elif type =='4':
                change_ppt_to_txt(readPath, savePath)
            print('保存成功！')
    except Exception as e:
        print(e)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90

代码写到这里后突然想到这种方式为什么不会有人用exe已经解决了呢，于是找了下就找到了
巨nb的office文字提取exe

下载了直接cmd调用里面的doctotext.exe就好,其中支持doc,docx各种office文档直接提取文字