Crawl Pictures From Website

#coding = utf-8

import requests
import os
from lxml import etree
from urllib.parse import quote,unquote
# import urllib.request

class DmdSpider(object):
        name = "dmd"
        save_path = 'E:/python/manhuadao/pics/'
        __picNo = 0

        # 访问漫画岛网页
        def start_request(self, url):
                header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'}
                r = requests.get(url, params=header)
                # print(r.text)

                self.__get_imgs(r)

                # 自动跳转下一页
                html = etree.HTML(r.text)
                next_urls = html.xpath('//div[@class="read-bottom"]//a[@class="next"]/@href')
                # print(next)
                for href in next_urls:
                        nexturl = href.split('=')[-1]
                        self.start_request(unquote(nexturl))

        # 使用xpath提取网页中的图片网址
        def __get_imgs(self, resbonse):
                html = etree.HTML(resbonse.text)
                # print(html)
                # result = etree.tostring(html)
                # print(result.decode("utf-8"))
                img_srcs = html.xpath('//div[@class="center-t"]//div[@class="main-content"]//img/@src')
                # print(img_srcs)
                for url in img_srcs:
                        self.__save_img(url)


        # 下载图片
        def __save_img(self, url):
                # arr = url.split('-')
                # picName = arr[-1].split('.')[0]

                header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'}
                # request = urllib.request.Request(url, None, header)  
                # response = urllib.request.urlopen(request)
                # with open('E:/python/manhuadao/pics/%s.jpg' %picName, "wb") as f:
                #     f.write(response.read())
                # print(response)

                response = requests.get(url, params = header)
                # print(response.content)
                if not os.path.exists(self.save_path):
                        os.makedirs(self.save_path)

                with open(self.save_path + '%s.jpg'%self.__picNo, "wb") as f:
                        f.write(response.content)
                        self.__picNo = self.__picNo + 1

def main():
        dmd = DmdSpider()
        dmd.start_request('http://www.manhuadao.cn/Comic/ComicView?comicid=58df8c73d401da325c9cf77c&chapterid=9587480')
    


if __name__ == "__main__":
    main()