import requests
from bs4 import BeautifulSoup
import time
import re
t = 0   #用於給圖片命名
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
    #設置header，模擬瀏覽器發出請求
    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解析上面獲得的html為文檔
    img_link  = soup.select(‘div#plist div.p-img‘)#先縮小目標數據所在的範圍
    link_list = re.findall(‘
 
//img[0-9|\.|a-z|\/|A-Z]+‘,str(img_link))#在上面的範圍中使用正則找到對應的img src

    #遍歷img src 下載到本地
    for url in link_list:
        url = ‘https:‘+str(url)
        data = requests.get(url).content
        filename = "C:/Users/Administrator/Desktop/京東圖片/" + str(t) +".jpg"
        t += 1
        with open(filename,mode=‘
 
wb‘) as f:
            f.write(data)

python爬蟲之下載京東頁面圖片