python 下载网页内容 包括图片_python完成网页下载（包括图片和css） | 学步园

import urllib2

import os

from bs4 import BeautifulSoup

import re

siteUrls = " "

url = "http://www.sina.com.cn"

def getContent(url):

content = urllib2.urlopen(url).read()

content = writeCss(url,content)

content = writefileName(url,content)

fileNames = re.findall(r'/[^\?]*\?([^/|^\?]*)$',url)

fileName = fileNames[0]

print fileName

f = file(fileName+".html",'w')

f.write(content)

f.close()

def writeCss(url,content):

soup = BeautifulSoup(content)

csss = soup.findAll('link',attrs={'type':'text/css'})

css_pat = re.compile('.*/(.*)\.css')

fileNames = re.findall(r'/[^\?]*\?([^/|^\?]*)$',url)

fileName = fileNames[0]

print fileNam