用Python抓取漫画并制作mobi格式电子书

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
import requests
import os



def mkdir(path):
    '''
    防止目录存在
    :param path:
    :return:
    '''
    if not os.path.exists(path):
        os.mkdir(path)


def SavePic(filename,url):
    '''
    图片的保存
    :param filename: 
    :param url: 
    :return: 
    '''
    content = requests.get(url).content
    with open(filename,'wb') as f:
        f.write(content)

def get_TOF(index_url):
    url_list = []
    chrome_options = Options()
    chrome_options.add_argument('--headless')#启用Chrome浏览器“无头模式”，提高抓取速率
    browser = webdriver.Chrome(chrome_options=chrome_options)    
    browser.get(index_url)
    browser.implicitly_wait(3)

    title = browser.title.split(',')[0]#获取漫画标题
    mkdir(title)#创建目录

    comics_lists = browser.find_elements_by_class_name('comic_Serial_list')#找到漫画章节
    for part in comics_lists:#找到每一章节所在的标签信息
        links = part.find_elements_by_tag_name('a')
        for link in links:
            url_list.append(link.get_attribute('href'))#获取每个单独章节链接
    browser.quit()
    Comics = {'name':title,'urls':url_list}
    return Comics

def get_pic(Comics):
    comic_list = Comics['urls']
    basedir = Comics['name']
    chrome_options = Options()
    chrome_options.add_argument('--headless')
    browser = webdriver.Chrome(chrome_options=chrome_options)    for url in comic_list:
        browser.get(url)
        browser.implicitly_wait(3)
        dirname = basedir+'/'+browser.title.split('-')[1]
        mkdir(dirname)
        #找到漫画一共有多少页
        pageNum = len(browser.find_elements_by_tag_name('option'))
        #找到下一页按钮
        nextpage = browser.find_element_by_xpath('//*[@id="AD_j1"]/div/a[4]')
        for i in range(pageNum):
            pic_url = browser.find_element_by_id('curPic').get_attribute('src')
            filename = dirname+'/'+str(i)+'.png'
            SavePic(filename,pic_url)
            nextpage.click()
        print('当前章节\t{}  下载完毕'.format(browser.title))
    browser.quit()
    print('所有章节下载完毕！')


if __name__ == '__main__':
    url = str(input('请输入漫画首页地址：\n'))
    Comics = get_TOF(url)
    
#print(Comics)
    get_pic(Comics)