python实现简单爬虫功能代码

实现爬取指定网页，下载图片到本地

原博地址：http://www.cnblogs.com/fnng/p/3576154.html

1.打开网页，读取，最后输出

#coding=utf-8
import urllib

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

html = getHtml("http://tieba.baidu.com/p/2738151262")

print html

2.定义getImg函数，获得图片地址。最后输出图片地址

import re
import urllib

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def getImg(html):
    reg = r'src="(.+?\.jpg)" pic_ext'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    return imglist      
   
html = getHtml("http://tieba.baidu.com/p/2460150866")
print getImg(html)

3.增加 下载图片到本地

#coding=utf-8
import urllib
import re

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def getImg(html):
    reg = r'src="(.+?\.jpg)" pic_ext'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl,'%s.jpg' % x)
        x+=1


html = getHtml("http://tieba.baidu.com/p/2460150866")

print getImg(html)

学习链接：

正则表达式#http://www.runoob.com/python/python-reg-expressions.html

#http://www.cnblogs.com/fnng/archive/2013/05/20/3089816.html