Python 中正则表达式无法匹配的问题

[listhome]

是这样的，在下新手，在使用Python遇到如下问题，请各位不吝赐教，先谢谢了。

需求
我用Python的UrlLib模块返回一个网页的源码，然后用正则找出我要的部分。

在编写正则时，因为每次要抓网页需要时间，所以我就把网页的内容保存成字符串，然后用正则匹配这个字符串。

问题：
正则写好后，使用本地字符串，完全没有问题，这时我用抓取网页，就根本匹配不上！但是，如果我把匹配不上的网页Print出来，存成字符串，就马上可以用正则匹配！网上查了，有人说是编码的问题，但我还是不知道怎么解决。谢谢大家

我的源代码的编码是GBK
# coding=GBK

我的正则条件是
if taskListPage.find(U"任务进行中") != -1:
Log("有")
Log(taskListPage)

[listhome]

自己消灭零回复

[iambic]

U"任务进行中"改成'\xc8\xce\xce\xf1\xbd\xf8\xd0\xd0\xd6\xd0'试试。

[listhome]

上面那个贴错了，正则条件是

pattern = re.compile(u'^\s*(<tr>$\s*<td height="25.*?</tr>)$', re.M | re.I | re.DOTALL)

[iambic]

1. r'...'
2. 你要匹配的是unicode还是str？

[listhome]

我把全部代码贴上

#coding=utf-8
'''
Created on 2011-7-1

@author: Yunanw
'''

import cookielib, urllib2, urllib
import time
import re
import string
import sys

debug = 1

#
# 用户名或密码
#
usrAndPwd = {"UserName":"selina", "PassWord":"123456Aa"}

#保证金
GMoney = 30

cookiejar = cookielib.CookieJar()
urlOpener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookiejar))

def Log(msg):
    if debug:
        print msg

def Post(url, Data):
    request = urllib2.Request(url, urllib.urlencode(Data))
    page = urlOpener.open(request)
    return page.read()
    
def Get(url):
    request = urllib2.Request(url)
    page = urlOpener.open(request)
    return page.read()

def Login():
    ##登陆的URL
    loginUrl = "http://www.shuazuanla.com/user_log.asp"
    Post(loginUrl, usrAndPwd)

def OpenTaskListPage():
    return Get("http://www.shuazuanla.com/taobao.asp?flag=0")

def AnlyseTaskListPage(taskListPage):
    #分析任务列表
    Log("开始分析")
    
    if taskListPage.find("等待接手") != -1:
        Log("有") 
        Log(taskListPage)
               
    pattern = re.compile(ur'^\s*(<tr>$\s*<td height="25.*?</tr>)$', re.M | re.DOTALL | re.I | re.U)
    taskList = []
    for task in pattern.findall(taskListPage):

        taskStatePattern = re.compile(r'^\s*(<tr>$\s*<td height="25.*?</tr>)$', re.M | re.DOTALL | re.I)
                
        for avilTask in taskStatePattern.findall(task):

            getMeoneyPattern = re.compile(r'^\s*(<td>.*等待接手.*?</a></td>)', re.M | re.DOTALL | re.I | re.U)
            cells = getMeoneyPattern.findall(avilTask)
            taskmoney = cells[1].replace("<td>", "").replace("</td>", "").replace(" ", "").replace(" ", "")
            taskmoney = string.atof(taskmoney)
            
            if (taskmoney < GMoney):
                dinPattern = re.compile(r'\d + ')
                taskID = dinPattern.findall(cells[7])[0]
                taskList.append(taskID)
        
    return taskList

def ViewTaskPage(taskID): 
    ViewTaskPageUrl = "http://www.shuazuanla.com/showinfo.asp?action=jie&din=" + taskID
    return Get(ViewTaskPageUrl);

def IsTaskAvil(taskPage):
    return taskPage.find(' < input type = "Submit" name = "Submit"disabled value = ') == -1

def ProcessTask(taskID):
    print "找到任务ID" + taskID 
    taskPage = ViewTaskPage(taskID)
    
    print submitTask(taskID)
    
    if IsTaskAvil(taskPage):
        submitTask(submitTask)
        
def ProcessTaskAsync(taskID):  
    return ProcessTask(taskID)  

def submitTask(taskID):
    url = 'http://www.shuazuanla.com/showinfo.asp?action=sbuto&din=' + taskID
    postData = {"xiaohao":"", "xiaohao":"" , "txiaohao_842":"selina10121", "select":"" , "opPassWord":"xunan19821012", "Submit":""}
    return Post(url, postData)


    
Login()

while(1): 
    taskListPage = OpenTaskListPage()
    TaskList = AnlyseTaskListPage(taskListPage)
    
    if len(TaskList) == 0:
        print "未找到可用任务"
    
    for taskid in TaskList:
        ProcessTaskAsync(taskid)
        
    time.sleep(2)

[listhome]

上面那个编码不对，我改一下

# coding=GBK
'''
Created on 2011-7-1

@author: Yunanw
'''

import cookielib, urllib2, urllib
import time
import re
import string
import sys

debug = 1

#
# 用户名或密码
#
usrAndPwd = {"UserName":"selina", "PassWord":"123456Aa"}

#保证金
GMoney = 30

cookiejar = cookielib.CookieJar()
urlOpener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookiejar))

def Log(msg):
    if debug:
        print msg

def Post(url, Data):
    request = urllib2.Request(url, urllib.urlencode(Data))
    page = urlOpener.open(request)
    return page.read()
    
def Get(url):
    request = urllib2.Request(url)
    page = urlOpener.open(request)
    return page.read()

def Login():
    ##登陆的URL
    loginUrl = "http://www.shuazuanla.com/user_log.asp"
    Post(loginUrl, usrAndPwd)

def OpenTaskListPage():
    #return Get("http://www.shuazuanla.com/taobao.asp?flag=0")
   
def AnlyseTaskListPage(taskListPage):
    #分析任务列表
    Log("开始分析")
    
    if taskListPage.find(U"等待接手") != -1:
        Log("有") 
        Log(taskListPage)


        
    pattern = re.compile(u'^\s*(<tr>$\s*<td height="25.*?</tr>)$', re.M | re.I | re.DOTALL)
    taskList = []
    for task in pattern.findall(taskListPage):

        taskStatePattern = re.compile(u'^\s*(<tr>$\s*<td height="25.*?</tr>)$', re.M | re.DOTALL | re.I)
                
        for avilTask in taskStatePattern.findall(task):

            getMeoneyPattern = re.compile(r'^\s*(<td>.*等待接手.*?</a></td>)', re.M | re.DOTALL | re.I | re.U)
            cells = getMeoneyPattern.findall(avilTask)
            taskmoney = cells[1].replace("<td>", "").replace("</td>", "").replace(" ", "").replace(" ", "")
            taskmoney = string.atof(taskmoney)
            
            if (taskmoney < GMoney):
                dinPattern = re.compile(r'\d + ')
                taskID = dinPattern.findall(cells[7])[0]
                taskList.append(taskID)
        
    return taskList

def ViewTaskPage(taskID): 
    ViewTaskPageUrl = "http://www.shuazuanla.com/showinfo.asp?action=jie&din=" + taskID
    return Get(ViewTaskPageUrl);

def IsTaskAvil(taskPage):
    return taskPage.find(' < input type = "Submit" name = "Submit"disabled value = ') == -1

def ProcessTask(taskID):
    print "找到任务ID" + taskID 
    taskPage = ViewTaskPage(taskID)
    
    print submitTask(taskID)
    
    if IsTaskAvil(taskPage):
        submitTask(submitTask)
        
def ProcessTaskAsync(taskID):  
    return ProcessTask(taskID)  

def submitTask(taskID):
    url = 'http://www.shuazuanla.com/showinfo.asp?action=sbuto&din=' + taskID
    postData = {"xiaohao":"", "xiaohao":"" , "txiaohao_842":"selina10121", "select":"" , "opPassWord":"xunan19821012", "Submit":""}
    return Post(url, postData)


    
Login()

while(1): 
    taskListPage = OpenTaskListPage()
    TaskList = AnlyseTaskListPage(taskListPage)
    
    if len(TaskList) == 0:
        print "未找到可用任务"
    
    for taskid in TaskList:
        ProcessTaskAsync(taskid)
        
    time.sleep(2)

[listhome]

pattern = re.compile(ur'^\s*(<tr>$\s*<td height="25.*?</tr>)$', re.M | re.DOTALL | re.I | re.U)
这句匹配不上

[iambic]

问你两个问题都不回复。自己解决吧。

[listhome]

不好意思，没看懂你的问题，我要从抓回来网页里匹配
应该是String吧

[「已注销」]

正则的编码也要是GBK的才好。