zk2epub/epub.py

import base64
import hashlib
import time
import re
import requests
import zipfile
import os
from filetools import FileTools
from template import Template

file_tools= FileTools()
template=Template(file_tools.get_ab_path('templates'))

class Epub:
    id = ""
    name = ""
    temp_dir = "" # 相对路径

    def __init__(self, name):
        self.name=name
        self.id = str(base64.b64encode(bytes(hashlib.md5(base64.b64encode(
            bytes(name, encoding='utf-8'))).hexdigest(), encoding='utf-8'))[-10:-1], encoding='utf-8')
        self.temp_dir='temp/%s%s' % (int(time.time()), self.id)
        file_tools.mkdir(self.temp_dir)
        self.write_base_file()

    def get_path(self, file):
        return "%s/%s" % (self.temp_dir, file)
    
    def write_base_file(self):
        file_tools.mkdir(self.get_path('META-INF'))
        file_tools.mkdir(self.get_path('OEBPF'))
        file_tools.mkdir(self.get_path('OEBPF/content'))
        file_tools.mkdir(self.get_path('OEBPF/css'))
        file_tools.mkdir(self.get_path('OEBPF/images'))
        file='mimetype'; file_tools.write(self.get_path(file), template.get(file))
        file='META-INF/container.xml'; file_tools.write(self.get_path(file), template.get(file))
        file='OEBPF/css/ebook.css'; file_tools.write(self.get_path(file), template.get(file))
        file='OEBPF/css/ebook.css'; file_tools.write(self.get_path(file), template.get(file))
        file='OEBPF/ebook.opf'; file_tools.write(self.get_path(file), template.get(file, name=self.name, id=self.id))
        file='OEBPF/navigation.ncx'; file_tools.write(self.get_path(file), template.get(file, name=self.name, id=self.id))

    def image_process(self, text):
        pattern = re.compile(r'https://sdjrzk-1251357229.cos.ap-guangzhou.myqcloud.com/exam/paper/\d+/images/\d+.[a-z]{3}')
        res=pattern.findall(text)
        if res:
            header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                        'Chrome/63.0.3239.132 Safari/537.36'}
            for image in res:
                temp_file=image.replace('/images/','_').replace('https://sdjrzk-1251357229.cos.ap-guangzhou.myqcloud.com/exam/paper/','%s/OEBPF/images/' % self.temp_dir)
                pic=requests.get(image, headers=header)
                print(file_tools.write_b(temp_file, pic.content))
        return text.replace('/images/','_').replace('https://sdjrzk-1251357229.cos.ap-guangzhou.myqcloud.com/exam/paper/','../images/')

    def process(self, text):
        cwd=os.getcwd()
        text = self.image_process(text)
        file='OEBPF/content/s1.xhtml'; file_tools.write(self.get_path(file), template.get(file, title=self.name, data=text))
        z=zipfile.ZipFile(file_tools.get_ab_path("output/%s.epub"%self.name), 'w', zipfile.ZIP_STORED)
        os.chdir(file_tools.get_ab_path(self.temp_dir))
        for dirpath, dirnames, filenames in os.walk('./'):
            for filename in filenames:
                z.write(os.path.join(dirpath, filename))
        os.chdir(cwd)
        
    def clean(self):
        file_tools.rm(self.temp_dir)