python将html文件转换为pdf

目录下的html文件转换为pdf

#coding=utf-8
import os
import pdfkit
import filetype
import _thread
import time
import  shutil


dir='C:\\Users\\Administrator\\Desktop\\SQL必知必会\\'  #html文件所在位置
pd_dir='C:\\Users\\Administrator\\Desktop\\mysql学习\\SQL必知必会' #输出pdf位置
path_wkthmltopdf=r'C:\\Program Files\\wkhtmltopdf\\bin\\wkhtmltopdf.exe'  #wkhtmltopdf工具下载界面：https://wkhtmltopdf.org/downloads.html
config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)
txt_name=[]
dir_name = []

def file_name():
    for dirpath, dirname, filenames in os.walk(dir, topdown=False):
        for name in filenames:
            cc=os.path.join(dirpath,name)
            dir_name.append(cc)
            txt_name.append(name)
#判断文件后缀，分别进行处理
def get_file_type():
    html_n=[]
    pdf_n=[]
    for i in dir_name:
        aaa = os.path.splitext(i)[-1]
        if aaa == '.html':
            html_n.append(i)
        if aaa == '.pdf' or aaa=='.htmlpdf':
            pdf_n.append(i)
    for p in pdf_n:
        os.remove(p)
    for h in html_n:
        ppp=h+'.pdf'
        pdfkit.from_file(h, output_path=ppp, configuration=config)
        shutil.copy(ppp,pd_dir)

if __name__ == '__main__':
    file_name()
    get_file_type()