test

import urllib2
import socket

def spider(self,url,headers,tryTime=3):
    try:
        req = urllib2.Request(url=url,headers=headers)
        page = urllib2.urlopen(req,timeout=30)
    except urllib2.URLError,e:
        if hasattr(e,'reason'):
            #判断是否为超时，若是则重试，且不超过3次
              if isinstance(e.reason,socket.timeout)
                if retries>0:
                    return self.spider(self,url,headers,tryTime-1)
            return None
        #HTTPError实例产生后会有整型的code属性
          elif hasattr(e,'code'):
            #重定向处理
              #if e.code==301 or e.code==302:
                #Python实现了重定向请求函数，自动跳转
             return None
    else:
        html = page.read()

#先解码成无编码格式(参数为原编码格式)
html = html.decode('gbk')
#再编码成指定格式
html= html.encode('utf8')
#若使用BeautifulSoup模块则增加一个参数，会将其转换成Unicode编码
#newHtml = BeautifulSoup(str(html),fromEncoding='gbk')

import re
reg = '<h3>.*<h3>'
content = re.findall(reg,html,re.I)
for item in content:
    #do something


import BeautifulSoup
soup = BeautifulSoup(str(html))
#获取class属性的值为page或者a1的全部标签内的文本内容，即展示在页面上的
pageInfo = soup.find(attrs={'class':'page'}).find(attrs={'class':'a1'}).get_text()
#获取<a>标签中href属性的值
hrefInfo = soup.a['href']
#抽取新闻文本正文，存放在id值为'art_cont'的标签文本中
#每个段落在一对<p></p>标签文本中
contents = soup.find(attrs={'id':'art_cont'}).findAll('p')
text = ''
for content in contents:
    content = content.get_text().encode('utf-8').strip()
    text += content+'\n'
text = text.strip()
import threading
#修改run()函数的加锁机制：
class Test(threading.Thread):
    def __init__(self, num):
        threading.Thread.__init__(self)
        self._run_num = num
 
    def run(self):
        global count, mutex
        threadname = threading.currentThread().getName()
 
        for x in xrange(0, int(self._run_num)):
            mutex.acquire()   #对count变量加锁，获得权限
            count = count + 1
            mutex.release()   #对count变量解锁，释放权限
            print threadname, x, count
            time.sleep(1)
 
if __name__ == '__main__':
    global count, mutex
    threads = []
    num = 4
    count = 1
    # 创建锁
    mutex = threading.Lock()
    for x in xrange(0, num):
        threads.append(Test(10))   # 创建4个线程对象
    for t in threads:
        t.start()	           # 启动线程
    for t in threads:	# 设置主线程必须等待
        t.join()	# 所有子线程结束后才能结束
import MySQLdb

sql = "SELECT * FROM Users WHERE Value= " + a_variable + "..."
a_variable = "'SA001’;drop table c_order--"
#若直接拼接，产生的SQL语句如下
#执行了意外的表删除操作，而后面的语句被当成注释被忽略了
#sql = "SELECT * FROM Users WHERE Value= 'SA001’;drop table c_order--..."

#利用MySQLdb模块自带的方法进行语义转义
MySQLdb.escape_string(a_variable)
#转义之后
#a_variable = "\'SA001\’\;drop table c_order\-\-"