实例001_py：爬取京东收集图片

1、爬取目标

URL:https://list.jd.com/list.html?cat=9987,653,655

 

2、代码

import re
import urllib.request

def  craw(url, page):
    htmlMain = urllib.request.urlopen(url).read();
    htmlMain = str(htmlMain);
    pattern1 = '<div id="plist".+? <div class="page clearfix">';
    rst1 = re.compile(pattern1).findall(htmlMain);
    rst1 = rst1[0];
    pattern2 = '<img width="220" height="220" .+?//.+?\.jpg';
    imagelist = re.compile(pattern2).findall(rst1);

    x = 1;
    for imageurl in imagelist:
        imagename = "D:/python/精通Python网路爬虫实例/Cha6/image/"+str(page)+"_"+str(x)+".jpg";
        pattern3 = '//.+?\.jpg';
        imageurl = re.compile(pattern3).findall(imageurl);
        imageurl = "http:"+imageurl[0];
        try:
            urllib.request.urlretrieve(imageurl, filename=imagename);
        except urllib.error.URLError as e:
            if hasattr(e, 'code'):
                x+=1;
            if hasattr(e, 'reason'):
                x+=1;
        x+=1;

for i in range(1, 51):
    url = "https://list.jd.com/list.html?cat=9987,653,655&page=" + str(i);
    craw(url, i);

 

3、效果