爬虫基础（案例：站长之家图片）

爬取思路：
1、首先找到图片分类信息，然后获取每个分类的url
2、请求每个分类的url可以得到相应页面的HTML源码
3、得到源码后使用BS4对信息所在的标签进行定位。
4、得到图片URL后保存一下就可以了
code：

import requests
from bs4 import BeautifulSoup
import json

class zhanzhang():
    def __init__(self):
        self.url = "https://sc.chinaz.com/tupian/"
        self.headers = {
            "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36"
        }
        self.img_a_label = []
        self.img_url_2 = []
    def deal_label(self,html):
        soup = BeautifulSoup(html,"html.parser")
        fenlei_list = soup.find("div",attrs = {"class":"mt10 feilei"}).find_all("div")
        for fenlei in fenlei_list:
            self.img_a_label.extend(fenlei.find_all("a",attrs = {"target":"_blank"}))
        
        for img in self.img_a_label:
            # print(img.attrs["title"])
            # print(img.attrs["href"])
            self.img_url_2.append(img.attrs["href"])
        
        
    def run(self):
        res = requests.get(self.url,headers = self.headers)
        html = res.text
        self.deal_label(html)
        self.get_img_url()
    def get_img(self,html):
        soup = BeautifulSoup(html,"html.parser")
        #找到目标图片所在的url
        img_list = soup.find("div",attrs = {"id":"container"}).find_all("img")
        for i,img_url in enumerate(img_list) :
            url = "https:"+img_url.attrs["src2"].replace("_s","")
            # self.img_down(url, i)
    def img_down(self,url,num):        
        file = open("C:/Users/孤桥/Desktop/项目/站长之家/{}.jpg".format(num),"wb")
        res = requests.get(url,headers = self.headers)
        file.write(res.content)
        file.close()
        
    def get_img_url(self):
        for img in self.img_url_2:
            url = self.url+img[8:]
            #这样就得到了每一类图片所在的网址，然后再从该网站上爬取每一张图片
            res = requests.get(url,headers = self.headers)
            self.get_img(res.text)
            break
            

zhanzhang_spide = zhanzhang()
zhanzhang_spide.run()