python实现PDF转图片的简单粗暴处理办法

# -*- coding:utf-8 -*-
'''
_AUTHOR_='QXY'
_MTIME_='2020/12/24'
'''
from win32com import client
import os

if __name__ == '__main__':
    path = r"C:\Users\user_Guest\Desktop\ky2020"	#pdf文件所在目录
    word = client.Dispatch('Word.Application')
    for pdf in os.listdir(path):	#批量处理该目录下的所有文件
        doc = word.Documents.Open(path + "\\" + pdf)
        doc.SaveAs(path + '\\' + pdf[:-4]+'.html', 8)  # 数字对应下方注释中的文件类型代码
        doc.Close()
    word.Quit()
'''
wdFormatDocument = 0
wdFormatDocument97 = 0
wdFormatDocumentDefault = 16
wdFormatDOSText = 4
wdFormatDOSTextLineBreaks = 5
wdFormatEncodedText = 7
wdFormatFilteredHTML = 10
wdFormatFlatXML = 19
wdFormatFlatXMLMacroEnabled = 20
wdFormatFlatXMLTemplate = 21
wdFormatFlatXMLTemplateMacroEnabled = 22
wdFormatHTML = 8
wdFormatPDF = 17
wdFormatRTF = 6
wdFormatTemplate = 1
wdFormatTemplate97 = 1
wdFormatText = 2
wdFormatTextLineBreaks = 3
wdFormatUnicodeText = 7
wdFormatWebArchive = 9
wdFormatXML = 11
wdFormatXMLDocument = 12
wdFormatXMLDocumentMacroEnabled = 13
wdFormatXMLTemplate = 14
wdFormatXMLTemplateMacroEnabled = 15
wdFormatXPS = 18
'''

转换完成后会生成一个网页+一个文件夹,文件每一页的图片都在文件夹里,这样就完成啦~

参考:
https://blog.csdn.net/ynyn2013/article/details/49120731?ops_request_misc=%25257B%252522request%25255Fid%252522%25253A%252522160874667716780261981156%252522%25252C%252522scm%252522%25253A%25252220140713.130102334…%252522%25257D&request_id=160874667716780261981156&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2_allsobaiduend~default-3-49120731.first_rank_v2_pc_rank_v29&utm_term=python%20%E5%8F%A6%E5%AD%98%E4%B8%BA