画师通网站团片爬取——二次元的福利

先声明一下画师通的的网址，这里面存在大量的二次元的图片。总有一款适合你，但小孩子才做选择题，我们全要!!!

进入画师通

爬取效果

爬取代码

import requests

from lxml import etree


class Dmimg:
    def __init__(self):
        self.headers = {
            "User - Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36",
            "Cookie": "UM_distinctid = 1712e065ee94a5 - 0fe79487749dc4 - f313f6d - 144000 - 1712e065eea910;hstud = u2ltte469895f389;auth_tk = MGRiNjZhODQxODE3NGM4ZTllMmFmYzQyODhjZGNhZTZvbzd2bl8yODcwNQ ==;Hm_lvt_a3e2ff554f3229fd90bcfe77f75b9806 = 1585615106, 1585615135;Hm_lpvt_a3e2ff554f3229fd90bcfe77f75b9806 = 1585651165"
           , "If - Modified - Since": "Sun, 29 Mar 2020 05:38: 04GMT",
            "If - None - Match": "AIF7wq3NzjqeN4RpTnJILDgjP8SQ",
                   }
        self.conut=0
    def get_url_list(self):
        url_list =[]
        url_list.append("https://www.huashi6.com/share")
        for i in range(1000, 10000):
            url_list.append("https://www.huashi6.com/draw/{}".format(i))
        return url_list

    def get_img_url(self,url_list):
        print(url_list)
        content = requests.get(url_list,headers =self.headers)
        img_url = etree.HTML(content.content)
        url = img_url.xpath('//*[@id="imgTooles"]/div/img/@src')

        try:
            for url_img in url :
                img = requests.get(url_img,headers =self.headers)
            name = "jpg"
            if "png" in url_img:
                name = "png"
            with open('img/'+str(self.conut)+'.'+name,"wb") as f:
                print("写入成功")
                print(img.content)
                f.write(img.content)

                self.conut = self.conut + 1

        except:
            print("写入失败")
    def run(self):
        pass
        # 1.获取爬取网站的列表
        url_list = self.get_url_list()
        # 2.访问网站内容并提取图片链接
        for url in url_list:
            img_url = self.get_img_url(url)


if __name__ == "__main__":
    Dm = Dmimg()
    Dm.run()