Python自学-第12次作业

#coding=utf8

'''

题目一： 写一个网页数据操作类。完成下面的功能：

提示：需要用到urllib模块

get_httpcode()获取网页的状态码，返回结果例如：200,301,404等 类型为int

get_htmlcontent() 获取网页的内容。返回类型:str

get_linknum()计算网页的链接数目。

'''

import urllib
import re

class mywebapp(object):

    def __init__(self):
        pass

    def get_httpcode(self,url):
        print url
        if not url.startswith('http://') and  not url.startswith('https://'):
            raise  TypeError,'Url must start with http:// or https:// .....'
        res = urllib.urlopen(url)
        page_status = res.getcode()
        print 'http status is %d' %page_status

    def get_htmlcontent(self,url):
        if not (url.startswith('http://') or url.startswith('https://')):
            raise TypeError, 'Url must start with http:// or https:// .....'
        content = urllib.urlopen(url)
        print content.read()

    def get_linknum(self,url):
        content = urllib.urlopen(url)
        print 'url is start'
        replace_content = content.read().replace(' ','')
        urls = re.findall(r'(http|ftp|https):\/\/[\w\-_]+(\.[\w\-_]+)+([\w\-\.,@?^=%&:/~\+#]*[\w\-\@?^=%&/~\+#])?',replace_content,re.I)
        for i in urls :
            print i
        #print len(content.split(')
print myapp.get_linknum('http://www.baidu.com')