Python이 JD 휴대폰 사진 크롤링을 구현하는 방법에 대한 분석 예

<span style="font-size: 14px; font-family: 微软雅黑, "Microsoft YaHei";">#爬取京东手机图片import re #导入re模块import urllib.request  #导入urllib.request模块def craw(url,page): #定义函数craw<br/>    html1 = urllib.request.urlopen(url).read() #调用urllib.request模块里的urlopen函数打开url链接，并且读取，最后赋值给html1<br/>    html1 = str(html1) #将html1网页内容变成字符串<br/>    pat1 = &#39;&#39;&#39;<p id="plist".+? <p class="page clearfix">&#39;&#39;&#39; #利用pat1正则表达式进行第一次信息过滤<br/>    result1 = re.compile(pat1).findall(html1)  #查找所有符合条件的信息<br/>    result1 = result1[0]<br/>    pat2 = &#39;&#39;&#39;<img width="220" height="220" data-img="1".+?"//(.+?\.jpg)">&#39;&#39;&#39;#".+?"组合可以匹配除换行外的任意字符，第二个正则表达式进行第二次过滤<br/>    imagelist = re.compile(pat2).findall(result1)<br/>    x = 1<br/>    for imageurl in imagelist:<br/>        imagename = "D:/Python35/myweb/part6/img1/"+"第"+str(page)+"页图"+str(x)+".jpg"<br/>        imageurl = "http://"+imageurl        try:<br/>            urllib.request.urlretrieve(imageurl,filename=imagename)        except urllib.error.URLError as e:            if hasattr(e,"code"):<br/>                x+=1<br/>            if hasattr(e,"reason"):<br/>                x+=1<br/>        x+=1for i in range(1,2):<br/>    url = "http://list.jd.com/list.html?cat=9987,653,655&page="+str(i)<br/>    craw(url,i)</span>