python 实战项目1爬取京东手机模块图片

1.环境python.36,PyCharm
2.分析URL,得到URL=https://list.jd.com/list.html?cat=9987,653,655&page=1 这种格式

3观察图片链接，img开始.jpg结尾

4.代码

import re
import urllib.request
import traceback
import os

for num in range(1, 20):
    url = "https://list.jd.com/list.html?cat=9987,653,655"
    pageurl = url + "&page=" + str(num)
    response = urllib.request.urlopen(pageurl)
    content = response.read().decode('utf-8')
    pattern = '\/\/(img.*?\.jpg)'
    urls = re.findall(pattern, content)
    count = 1;
    base = "F:/Python/img/"
    for url in urls:
        newurl = "http://" + url
        end = base + str(num) + "page"
        if (os.path.isdir(end) == False):
            os.makedirs(end)
        name = end + "/" + str(count) + ".jpg"
        try:
            urllib.request.urlretrieve(newurl, name)
            count = count + 1
        except:
            print(traceback.format_exc())
    num = num + 1;