抓取图片爬虫

简介

个人学习编写的一个抓取图片的爬虫，仅作记录。

代码

#目的 下载某网站的图片
# 1. 获取网页源代码，拿到子网站的url
# 2. 从每个子页面得到图片的下载连接
# 3. 下载图片

import requests
import bs4
import time

#获取网页源代码
url = 'https://www.umei.cc/bizhitupian/diannaobizhi/'
url_tihuan = 'https://www.umei.cc'
resp = requests.get(url)
resp.encoding = "utf-8"
# print(resp.text)

#获取子网站URL
main_pag = bs4.BeautifulSoup(resp.text,"html.parser")#声明为HTML
list1 = main_pag.find("div",class_="TypeList").findAll("a")
#循环每个子页面获得每个子页面的图片地址并下载
for a in list1:
    url_chlid =url_tihuan+a.get("href")
    # print(url_chlid)
    chlid_page_resp = requests.get(url_chlid)
    chlid_page_resp.encoding = "utf-8"
    chlid_page_mian = bs4.BeautifulSoup(chlid_page_resp.text,"html.parser")
    chlid_page_list = chlid_page_mian.find("p",align="center").find("img")
    src = chlid_page_list.get("src")
    # print(src)
    #下载图片
    img_resp = requests.get(src)
    img_name = src.split("/")[-1]
    with open("img/"+img_name,mode="wb") as f:
        f.write(img_resp.content)#comtent拿到的是字节  这里把图片内容写入文件
    print("ok~")
    time.sleep(1)

print("11")