bs4图片爬取

一、步骤

1、拿到主页面的前端源码，然后提取子页面的链接地址

2、通过href拿到子页面的内容。从子页面中找到图片的下载地址

3、下载图片

二、代码

import requests
from bs4 import BeautifulSoup
import os

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 Edg/95.0.1020.40"
}

url = "https://umei.cc/bizhitupian/weimeibizhi/"

resp = requests.get(url,headers)
resp.encoding = 'tuf-8'


main_page = BeautifulSoup(resp.text,"html.parser")

alist = main_page.find("div",class_="TypeList").find_all("a")




for i in alist:
	href = i.get('href')
        #获取子页面完整url 
	child_href = url + href.split("/")[-1]
	
	
	child_href_resp = requests.get(child_href,headers)	
	child_href_resp.encoding = 'tuf-8'
	child_href_text = child_href_resp.text
	
	child_page = BeautifulSoup(child_href_text,"html.parser")
        # 定位图片地址
	p = child_page.find("p",align="center")
	img = p.find('img')
        # 获取图片URL
	src = img.get("src")
	
	img_resp = requests.get(src,headers=headers)
	img_name = src.split("/")[-1]
        # 判断所在目录下是否有该文件名的文件夹
	if  not os.path.exists('img'): 
                # 不存在创建
    		os.makedirs('img')
	else:
                # 存在打开写入，with open在windows下不存在会直接创建，但是在linux下我没成功所以加了个判断
		with open("img/"+img_name,mode="wb") as f:
                        # img_resp.content拿到的是字节
			f.write(img_resp.content)
resp.close()