ziw2pdf

import pdfkit
import zipfile
import os
import sys
import re

# 出现乱码时解码
def recode(raw: str) -> str:
    try:
        return raw.encode('cp437').decode('gbk')
    except:
        return raw.encode('utf-8').decode('utf-8')

def saveFile(htmlobj,pdfobj):
    options = {
        'page-size':'Letter','margin-top':'0.75in','margin-right':'0.75in',
        'margin-bottom':'0.75in','margin-left':'0.75in','encoding':"UTF-8",
        'custom-header': [('Accept-Encoding','gzip')],
        'cookie': [('cookie-name1','cookie-value1'),('cookie-name2','cookie-value2'),],
        "enable-local-file-access": None,
        "header-left" : "收集人：冯际成 QQ：604756218 ",
        "header-right" : "[date] 机密文件请勿外传",
        "header-spacing" : 3,
        "footer-spacing" : 3,
        "footer-center" : "- 第 [page] 页-",
        "header-line":None,
        "page-size": 'A4',
        "outline-depth":10,
    }
    config = pdfkit.configuration(wkhtmltopdf=r'C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe') 
    pdfDir = os.path.dirname(pdfobj)
    if not os.path.exists(pdfDir):
        os.makedirs(pdfDir)
    pdfkit.from_file(htmlobj,pdfobj,options=options,configuration=config,verbose=True)

def ziw2pdf(root,file):

    current_directory = os.path.dirname(os.path.abspath(__file__)) #获得当前路径
    pathZip = os.path.join(root,file)
    #开始合合成路径
    split_list=pathZip.replace(".ziw","").split("\\")[7:]
    head=current_directory+r"\tmp"
    if not os.path.exists(head):
        os.makedirs(head)
    for path in split_list:
        head = os.path.join(head, re.sub(r"\s+", "", path))
    ziwobj    = head
    
    split_list=pathZip.replace(".ziw",".pdf").split("\\")[7:]
    head=current_directory+r"\pdf"
    if not os.path.exists(head):
        os.makedirs(head)
    for path in split_list:
        head = os.path.join(head, re.sub(r"\s+", "", path))
    pdfobj = head
    zipFile = zipfile.ZipFile(pathZip)          # 压缩包路径
    zipFileList = zipFile.namelist()            # 获取压缩包里所有文件
    for f in zipFileList:
        zipFile.extract(f, ziwobj)                 # 循环解压文件到指定目录
        name1 = os.path.join(ziwobj, f)            # 乱码文件名
        name2 = os.path.join(ziwobj, recode(f))    # 解码后文件名
        os.rename(name1, name2)                 # 文件重命名
    zipFile.close()                             # 关闭文件释放内存
    htmlobj =os.path.join(ziwobj ,"index.html")
    saveFile(htmlobj,pdfobj)

if __name__ == '__main__':
    ziw_list = []
    file_dir = "C:\\Users\\fengjicheng\\Documents\\My Knowledge\\Data\\caoxiancc@live.cn\\SAP"
    #file_dir = "C:\\Users\\fengjicheng\\Documents\\My Knowledge\\Data\\caoxiancc@live.cn\\AI"
    for root,dirs,files in os.walk(file_dir):
        for file in files:
            if file.endswith(".ziw"):
                ziw2pdf(root,file)