002--Python网络篇

1.打印网页数据

#coding=utf-8
'''
    将一个网页的所有文字全部打印
'''
import urllib

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

html = 

print html

2.筛选网页数据

#coding=utf-8
'''
    筛选页面中想要的数据：Python 提供了非常强大的正则表达式，对数据进行筛选
    
'''
import re
import urllib

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

def getImg(html):
    reg = r'src="(.+?\.jpg)"'
    imgre = 
    imglist = re.findall(imgre,html)
    return imglist      
   
html = 
print getImg(html)

3.下载网页图片

#coding=utf-8
'''
    筛选页面中想要的数据：Python 提供了非常强大的正则表达式，对数据进行筛选
    
'''
import re
import urllib

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

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

html = 

print getImg(html)