python简单爬虫示例

Posted 2020-07-12 mrdoor

#coding=utf-8

 

import urllib

import re

 

def downloadPage(url):

    h = urllib.urlopen(url)

    return h.read()

 

def downloadImg(content):

    pattern = r‘src="(.+?\.jpg)" pic_ext‘

    m = re.compile(pattern)

    urls = re.findall(m, content)

 

    for i, url in enumerate(urls):

        urllib.urlretrieve(url, "%s.jpg" % (i, ))

 

content = downloadPage("http://tieba.baidu.com/p/2460150866")

downloadImg(content)

 

针对图片的批量下载 urllib提供了相关接口可以执行！