python利用urllib实现爬取京东网站商品图片的爬虫实例

脚本专栏 2025/1/10 佚名

3 2 1

本例程使用urlib实现的，基于python2.7版本，采用beautifulsoup进行网页分析，没有第三方库的应该安装上之后才能运行，我用的IDE是pycharm，闲话少说，直接上代码！

# -*- coding: utf-8 -*
import re
import os
import urllib
import urllib2
from bs4 import BeautifulSoup
def craw(url,page):
 html1=urllib2.urlopen(url).read()
 html1=str(html1)
 soup=BeautifulSoup(html1,'lxml')
 imagelist=soup.select('#J_goodsList > ul > li > div > div.p-img > a > img')
 namelist=soup.select('#J_goodsList > ul > li > div > div.p-name > a > em')
 #pricelist=soup.select('#plist > ul > li > div > div.p-price > strong')
 #print pricelist
 path = "E:/{}/".format(str(goods))
 if not os.path.exists(path):
  os.mkdir(path)
 for (imageurl,name) in zip(imagelist,namelist):
  name=name.get_text()
  imagename=path + name +".jpg"
  imgurl="http:"+str(imageurl.get('data-lazy-img'))
  if imgurl == 'http:None':
   imgurl = "http:" + str(imageurl.get('src'))
  try:
   urllib.urlretrieve(imgurl,filename=imagename)
  except:
   continue

'''
#J_goodsList > ul > li:nth-child(1) > div > div.p-img > a > img
#plist > ul > li:nth-child(1) > div > div.p-name.p-name-type3 > a > em
#plist > ul > li:nth-child(1) > div > div.p-price > strong:nth-child(1) > i
'''

if __name__ == "__main__":
 goods=raw_input('please input the goos you want:')
 pages=input('please input the pages you want:')
 count =0.0
 for i in range(1,int(pages+1),2):
  url="https://search.jd.com/Search".format(str(goods),str(i))
  craw(url,i)
  count += 1
  print 'work completed {:.2f}%'.format(count/int(pages)*100)

图片的命名为商品的名称，京东商品图片地址的属性很可能会有所变动，所以大家进行编写的时候应该举一反三，灵活运用！
这是我下载下来的手机类图片文件的截图：