dengshilong

//
// $Id: sphinxclient.c 4097 2013-08-20 09:28:24Z kevg $
//

//
// Copyright (c) 2001-2013, Andrew Aksyonoff
// Copyright (c) 2008-2013, Sphinx Technologies Inc
// All rights reserved
//
// This program is free software; you can redistribute it and/or modify

dengshilong

# -*- encoding: UTF-8 -*-
import urllib2
import re
from datetime import date
def get_page(url):
    """得到一个网页的内容"""
    try:
        print "crawling %s" % url
        headers = {"User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1) Gecko/20090624 Firefox/3.5",\
             "Referer": 'http://www.baidu.com'}

dengshilong

import math
from operator import itemgetter, attrgetter
from collections import defaultdict
def UserSimilarity(train):
    #build inverse table for item_users
    print "build inverse table for item_users"
    item_users = defaultdict(set)
    for u,items in train.iteritems():
        for i in items.keys():
            item_users[i].add(u)

dengshilong

#--*-- encoding:utf-8 --*--
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.base import MIMEBase
from email import encoders
from datetime import date
def sendMail(user,pwd,to,subject,filename):
    outer = MIMEMultipart()
    outer['From'] = user
    outer['To'] = to

dengshilong

# -*- coding: utf-8 -*-
"""统计指定目录下,指定源文件类型的总行数"""
from collections import defaultdict
import os
d = defaultdict(int)
path = r"D:/vc++workspaces"  #路径
f = ['.c','.cpp'] #需要统计源文件的类型
for dirpath,dirnames,filenames in os.walk(path):
    for filename in filenames:
        path = os.path.join(dirpath, filename)