Python简单抓取新浪某网页新闻链接及标题

进行了一些拓展（还可以再扩展，吧tele中间路径从主页中获取到，然后用map给用户选择）：

#这里可以再改进，进行扩展，自行输入时间（貌似都一样，正则还是可以用）
#doc = urlopen("http://roll.tech.sina.com.cn/tele/2012-05-01.shtml").read()
newsYear = raw_input("Please input the year likes 2012: ")
newsMouth = raw_input("Please input the mouth likes 03: ")
newsDay = raw_input("Please input the day likes 02: ")
doc = urlopen("http://roll.tech.sina.com.cn/tele/" + \
              newsYear + "-" + \
              newsMouth + "-" + \
              newsDay + \
              ".shtml").read()

没怎么接触网页及网络相关知识，再用没上手的Python，下面这段程序一波三折，bugs不少，但勉强还算是实现了对http://roll.tech.sina.com.cn/tele/2012-05-01.shtml网页新闻的抓取。win系统服务没加上，及一堆问题，待续……

# -*- coding: cp936 -*-
import win32serviceutil
import win32service
import win32event
from urllib import urlretrieve
from urllib import urlopen
import smtplib
from email.mime.text import MIMEText
from email.MIMEMultipart import MIMEMultipart
from email.Header import Header
#这个正则库感觉很棒
import re
import os
import xlrd

doc = urlopen("http://roll.tech.sina.com.cn/tele/2012-05-01.shtml").read()

#分别寻找链接和新闻标题
def extract_url(info):
    rege = "<li><a href=\"(.*)\" target=_blank>"
    url = re.findall(rege, info)
    return url

def extract_title(info):
    pat = "\" target=_blank>(.*)</a><span class="
    title = re.findall(pat, info)
    return title

url = extract_url(doc)
title = extract_title(doc)

#xlrd模块的使用有问题，打开路径出错
# XLRDError('Unsupported format, or corrupt file: ' + msg)
def get_email_list():
    path = os.getcwd()
    wb = xlrd.open_workbook(path + "\\email_list.xls", encoding_override="cp1252")
    sheet = wb.sheet_by_name("mail")
    first_column = sheet.col_values(0)

    return first_column

#emaildest = get_email_list()

n = len(url)
#邮件表格仍然有问题
#换为div去实现简单换行
#<a href="http://www.baidu.com" target="_blank">fsddfs</a>
mail_context = ""
#mail_context += "<table width=\"700\" border=\"1\" align=\"left\" face=\"宋体\">"
for i in range(0, n):
#    mail_context += "<tr><td><font size=\"2\">"
#    mail_context += "<span class=\"line1\"><a href=\""
#    mail_context += url[i]
#    mail_context += "\" target=_blank>"
#    mail_context += title[i]
#    mail_context += "</a></span>"
#    mail_context += "</font></td>"
#    mail_context += "</table>"
    mail_context += "<div><a href=\""
    mail_context += url[i]
    mail_context += "\" target=\"_blank\">"
    mail_context += title[i]
    mail_context += "</a></div>"

def sendsimplemail(text, dest):
    msg = MIMEText(text, 'html', 'gb2312')
    msg['Subject'] = Header('title', 'gb2312')
    msg['From'] = 'sourcedest'
    msg['To'] = str(dest)
    try:
        #登录邮箱服务器
        smtp = smtplib.SMTP()
        #登录验证
        smtp.connect(r'smtp.Serve.com')
        smtp.login('user','password')
        #发送邮箱
        #有验证现在，所以发送还是相同为好
        smtp.sendmail('user', dest, msg.as_string())
        smtp.close()
    except Exception, e:
        print e

dest = ['targetEmailAddress']
sendsimplemail(mail_context, dest)