python爬虫之下载京东页面图片

Posted 2021-02-07 小胡子oYi

import requests
from bs4 import BeautifulSoup
import time
import re
t = 0   #用于给图片命名
for i in range(10):
    url = "https://list.jd.com/list.html?cat=9987,653,655&page=%s&sort=sort_rank_asc&trans=1&JL=6_0_0&ms=6#J_main"%i #起始url
    #设置header，模拟浏览器发出请求
    header = {
    ‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36‘,
    }
    data = requests.get(url,headers=header).content 
    soup = BeautifulSoup(data,‘lxml‘)#使用beautifulsoup解析上面获得的html为文档
    img_link  = soup.select(‘div#plist div.p-img‘)#先缩小目标数据所在的范围
    link_list = re.findall(‘//img[0-9|.|a-z|/|A-Z]+‘,str(img_link))#在上面的范围中使用正则找到对应的img src

    #遍历img src 下载到本地
    for url in link_list:
        url = ‘https:‘+str(url)
        data = requests.get(url).content
        filename = "C:/Users/Administrator/Desktop/京东图片/" + str(t) +".jpg"
        t += 1
        with open(filename,mode=‘wb‘) as f:
            f.write(data)