[Python]爬虫v0.1

#coding:utf-8
import urllib
######
#爬虫v0.1 利用urlib2 和 字符串内建函数
######

# 获取网页内容
def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def content(html):
    # 内容分割的标签
    str = ‘<article class="article-content">‘
    content = html.partition(str)[2]
    str1 = ‘<div class="article-social">‘
    content = content.partition(str1)[0]
    return content # 得到网页的内容
    
def title(content,beg = 0):
    # 思路是利用str.index()和序列的切片
    try:
        title_list = []
        while beg >=0:   
            num1 = content.index(‘】‘,beg)
            num2 = content.index(‘</p>‘,num1)
            title_list.append(content[num1:num2])
            beg = num2
        
    except ValueError:
         return title_list
        
        
    
def get_title():
    # 利用循环更新num1和num2，从而匹配出全部title
    pass
    
content = content(getHtml("http://bohaishibei.com/post/10449/"))
#num = content.index(‘】‘)
title = title(content)
for i,e in enumerate(title):
    print ‘第%d个，title：%s‘ % (i,e)

# 今天爬的单个页面的title