//httperror265001_266001.txt
265002 httperror
265002 httperror
265002 httperror
265002 httperror
265003 httperror
265003 httperror
265003 httperror
265003 httperror

def main():
  reload(sys)
  sys.setdefaultencoding('utf-8')
  global sexRe,timeRe,notexistRe,url1,url2,file1,file2,file3,file4,startNum,endNum,file5
  sexRe = re.compile(u'em>\u6027\u522b</em>(.*?)</li')
  timeRe = re.compile(u'em>\u4e0a\u6b21\u6d3b\u52a8\u65f6\u95f4</em>(.*?)</li')
  notexistRe = re.compile(u'(p>)\u62b1\u6b49\uff0c\u60a8\u6307\u5b9a\u7684\u7528\u6237\u7a7a\u95f4\u4e0d\u5b58\u5728<')
  url1 = 'http://rs.xidian.edu.cn/home.php?mod=space&uid=%s'
  url2 = 'http://rs.xidian.edu.cn/home.php?mod=space&uid=%s&do=profile'
  file1 = 'ruisi\\correct_re.txt'
  file2 = 'ruisi\\errTime_re.txt'
  file3 = 'ruisi\\notexist_re.txt'
  file4 = 'ruisi\\unkownsex_re.txt'
  file5 = 'ruisi\\httperror_re.txt'

  #遍历文件夹里面以httperror开头的文本
  for filename in os.listdir(r'E:\pythonProject\ruisi'):
    if filename.startswith('httperror'):
      count = 0
      newName = 'E:\\pythonProject\\ruisi\\%s' % (filename)
      readFile = open(newName,'r')
      oldLine = '0'
      for line in readFile:
        #newLine 用来比较是否是重复的id
        newLine = line
        if (newLine != oldLine):
          nu = newLine.split()[0]
          oldLine = newLine
          count += 1
          searchWeb((int(nu),))
      print "%s deal %s lines" %(filename, count)

 file1 = 'ruisi\\correct_re.txt'
  file2 = 'ruisi\\errTime_re.txt'
  file3 = 'ruisi\\notexist_re.txt'
  file4 = 'ruisi\\unkownsex_re.txt'
  file5 = 'ruisi\\httperror_re.txt'

"D:\Program Files\Python27\python.exe" E:/pythonProject/webCrawler/reload.py
httperror132001-133001.txt deal 21 lines
httperror2001-3001.txt deal 4 lines
httperror251001-252001.txt deal 5 lines
httperror254001-255001.txt deal 1 lines

253042 unkownsex
253087 unkownsex
253102 unkownsex
253118 unkownsex
253125 unkownsex
253136 unkownsex
253161 unkownsex

import os,time
sumCount = 0

startTime = time.clock()

for filename in os.listdir(r'E:\pythonProject\ruisi'):
  if filename.startswith('unkownsex'):
    count = 0
    newName = 'E:\\pythonProject\\ruisi\\%s' % (filename)
    readFile = open(newName,'r')
    for line in open(newName):
      count += 1
      sumCount +=1
    print "%s deal %s lines" %(filename, count)
print '%s unkowns sex' %(sumCount)

endTime = time.clock()
print "cost time " + str(endTime - startTime) + " s"

unkownsex1-1001.txt deal 204 lines
unkownsex100001-101001.txt deal 50 lines
unkownsex10001-11001.txt deal 206 lines
#...省略中间输出信息
unkownsex99001-100001.txt deal 56 lines
unkownsex_re.txt deal 1085 lines
14223 unkowns sex
cost time 0.0813142301261 s

31024 男 2014-11-11 13:20
31283 男 2013-3-25 19:41
31340 保密 2015-2-2 15:17
31427 保密 2014-8-10 09:17
31475 保密 2013-7-2 08:59
31554 保密 2014-10-17 17:02
31621 男 2015-5-16 19:27
31872 保密 2015-1-11 16:49
31915 保密 2014-5-4 11:01
31997 保密 2015-5-16 20:14

import os,sys,time
reload(sys)
sys.setdefaultencoding('utf-8')
startTime = time.clock()
sumCount = 0
boycount = 0
girlcount = 0
secretcount = 0
for filename in os.listdir(r'E:\pythonProject\ruisi'):
  if filename.startswith('correct'):
    newName = 'E:\\pythonProject\\ruisi\\%s' % (filename)
    readFile = open(newName,'r')
    for line in readFile:
      sexInfo = line.split()[1]
      sumCount +=1
      if sexInfo == u'\u7537' :
        boycount += 1
      elif sexInfo == u'\u5973':
        girlcount +=1
      elif sexInfo == u'\u4fdd\u5bc6':
        secretcount +=1
    print "until %s, sum is %s boys; %s girls; %s secret;" %(filename, boycount,girlcount,secretcount)
print "total is %s; %s boys; %s girls; %s secret;" %(sumCount, boycount,girlcount,secretcount)
endTime = time.clock()
print "cost time " + str(endTime - startTime) + " s"

until correct1-1001.txt, sum is 110 boys; 7 girls; 414 secret;
until correct100001-101001.txt, sum is 125 boys; 13 girls; 542 secret;
#...省略
until correct99001-100001.txt, sum is 11070 boys; 3113 girls; 26636 secret;
until correct_re.txt, sum is 13937 boys; 4007 girls; 28941 secret;
total is 46885; 13937 boys; 4007 girls; 28941 secret;
cost time 3.60047888495 s

# encoding: UTF-8
import threading
import time,os,sys

#全局变量
SUM = 0
BOY = 0
GIRL = 0
SECRET = 0
NUM =0

#本来继承自threading.Thread，覆盖run()方法，用start()启动线程
#这和java里面很像
class StaFileList(threading.Thread):
  #文本名称列表
  fileList = []

  def __init__(self, fileList):
    threading.Thread.__init__(self)
    self.fileList = fileList

  def run(self):
    global SUM, BOY, GIRL, SECRET
    #可以加上个耗时时间，这样多线程更加明显，而不是顺序的thread-1,2,3
    #time.sleep(1)
    #acquire获取锁
    if mutex.acquire(1):
      self.staFiles(self.fileList)
      #release释放锁
      mutex.release()

  #处理输入的files列表，统计男女人数
  #注意这儿数据同步问题，global使用全局变量
  def staFiles(self, files):
    global SUM, BOY, GIRL, SECRET
    for name in files:
      newName = 'E:\\pythonProject\\ruisi\\%s' % (name)
      readFile = open(newName,'r')
      for line in readFile:
        sexInfo = line.split()[1]
        SUM +=1
        if sexInfo == u'\u7537' :
          BOY += 1
        elif sexInfo == u'\u5973':
          GIRL +=1
        elif sexInfo == u'\u4fdd\u5bc6':
          SECRET +=1
      # print "thread %s, until %s, total is %s; %s boys; %s girls;" \
      #    " %s secret;" %(self.name, name, SUM, BOY,GIRL,SECRET)


def test():
  #files保存多个文件，可以设定一个线程处理多少个文件
  files = []

  #用来保存所有的线程，方便最后主线程等待所以子线程结束
  staThreads = []
  i = 0
  for filename in os.listdir(r'E:\pythonProject\ruisi'):
    #没获取10个文本，就创建一个线程
    if filename.startswith('correct'):
      files.append(filename)
      i+=1
      #一个线程处理20个文件
      if i == 20 :
        staThreads.append(StaFileList(files))
        files = []
        i = 0
  #最后剩余的files，很可能长度不足10个
  if files:
    staThreads.append(StaFileList(files))

  for t in staThreads:
    t.start()
  # 主线程中等待所有子线程退出，如果不加这个，速度更快些？
  for t in staThreads:
    t.join()



if __name__ == '__main__':
  reload(sys)
  sys.setdefaultencoding('utf-8')
  startTime = time.clock()
  mutex = threading.Lock()
  test()
  print "Multi Thread, total is %s; %s boys; %s girls; %s secret;" %(SUM, BOY,GIRL,SECRET)
  endTime = time.clock()
  print "cost time " + str(endTime - startTime) + " s"

Multi Thread, total is 46885; 13937 boys; 4007 girls; 28941 secret;
cost time 0.132137192794 s

# coding=utf-8
import os,sys,time
reload(sys)
sys.setdefaultencoding('utf-8')
startTime = time.clock()
sumCount = 0
boycount = 0
girlcount = 0
secretcount = 0
unkowncount = 0
for filename in os.listdir(r'E:\pythonProject\ruisi'):
  # 有性别、活动时间
  if filename.startswith('correct') :
    newName = 'E:\\pythonProject\\ruisi\\%s' % (filename)
    readFile = open(newName,'r')
    for line in readFile:
      sexInfo =line.split()[1]
      sumCount +=1
      if sexInfo == u'\u7537' :
        boycount += 1
      elif sexInfo == u'\u5973':
        girlcount +=1
      elif sexInfo == u'\u4fdd\u5bc6':
        secretcount +=1
    # print "until %s, sum is %s boys; %s girls; %s secret;" %(filename, boycount,girlcount,secretcount)
  #没有活动时间，但是有性别
  elif filename.startswith("errTime"):
    newName = 'E:\\pythonProject\\ruisi\\%s' % (filename)
    readFile = open(newName,'r')
    for line in readFile:
      sexInfo =line.split()[1]
      sumCount +=1
      if sexInfo == u'\u7537' :
        boycount += 1
      elif sexInfo == u'\u5973':
        girlcount +=1
      elif sexInfo == u'\u4fdd\u5bc6':
        secretcount +=1
    # print "until %s, sum is %s boys; %s girls; %s secret;" %(filename, boycount,girlcount,secretcount)
  #没有性别，也没有时间，直接统计行数
  elif filename.startswith("unkownsex"):
    newName = 'E:\\pythonProject\\ruisi\\%s' % (filename)
    # count = len(open(newName,'rU').readlines())
    #对于大文件用循环方法，count 初始值为 -1 是为了应对空行的情况，最后+1得到0行
    count = -1
    for count, line in enumerate(open(newName, 'rU')):
      pass
    count += 1
    unkowncount += count
    sumCount += count
    # print "until %s, sum is %s unkownsex" %(filename, unkowncount)



print "Single Thread, total is %s; %s boys; %s girls; %s secret; %s unkownsex;" %(sumCount, boycount,girlcount,secretcount,unkowncount)
endTime = time.clock()
print "cost time " + str(endTime - startTime) + " s"

__author__ = 'admin'
# encoding: UTF-8
#多线程处理程序
import threading
import time,os,sys

#全局变量
SUM = 0
BOY = 0
GIRL = 0
SECRET = 0
UNKOWN = 0

class StaFileList(threading.Thread):
  #文本名称列表
  fileList = []

  def __init__(self, fileList):
    threading.Thread.__init__(self)
    self.fileList = fileList

  def run(self):
    global SUM, BOY, GIRL, SECRET
    if mutex.acquire(1):
      self.staManyFiles(self.fileList)
      mutex.release()

  #处理输入的files列表，统计男女人数
  #注意这儿数据同步问题
  def staCorrectFiles(self, files):
    global SUM, BOY, GIRL, SECRET
    for name in files:
      newName = 'E:\\pythonProject\\ruisi\\%s' % (name)
      readFile = open(newName,'r')
      for line in readFile:
        sexInfo = line.split()[1]
        SUM +=1
        if sexInfo == u'\u7537' :
          BOY += 1
        elif sexInfo == u'\u5973':
          GIRL +=1
        elif sexInfo == u'\u4fdd\u5bc6':
          SECRET +=1
      # print "thread %s, until %s, total is %s; %s boys; %s girls;" \
      #    " %s secret;" %(self.name, name, SUM, BOY,GIRL,SECRET)

  def staManyFiles(self, files):
    global SUM, BOY, GIRL, SECRET,UNKOWN
    for name in files:
      if name.startswith('correct') :
        newName = 'E:\\pythonProject\\ruisi\\%s' % (name)
        readFile = open(newName,'r')
        for line in readFile:
          sexInfo = line.split()[1]
          SUM +=1
          if sexInfo == u'\u7537' :
            BOY += 1
          elif sexInfo == u'\u5973':
            GIRL +=1
          elif sexInfo == u'\u4fdd\u5bc6':
            SECRET +=1
        # print "thread %s, until %s, total is %s; %s boys; %s girls;" \
        #    " %s secret;" %(self.name, name, SUM, BOY,GIRL,SECRET)
      #没有活动时间，但是有性别
      elif name.startswith("errTime"):
        newName = 'E:\\pythonProject\\ruisi\\%s' % (name)
        readFile = open(newName,'r')
        for line in readFile:
          sexInfo = line.split()[1]
          SUM +=1
          if sexInfo == u'\u7537' :
            BOY += 1
          elif sexInfo == u'\u5973':
            GIRL +=1
          elif sexInfo == u'\u4fdd\u5bc6':
            SECRET +=1
        # print "thread %s, until %s, total is %s; %s boys; %s girls;" \
        #    " %s secret;" %(self.name, name, SUM, BOY,GIRL,SECRET)
      #没有性别，也没有时间，直接统计行数
      elif name.startswith("unkownsex"):
        newName = 'E:\\pythonProject\\ruisi\\%s' % (name)
        # count = len(open(newName,'rU').readlines())
        #对于大文件用循环方法，count 初始值为 -1 是为了应对空行的情况，最后+1得到0行
        count = -1
        for count, line in enumerate(open(newName, 'rU')):
          pass
        count += 1
        UNKOWN += count
        SUM += count
        # print "thread %s, until %s, total is %s; %s unkownsex" %(self.name, name, SUM, UNKOWN)


def test():
  files = []
  #用来保存所有的线程，方便最后主线程等待所以子线程结束
  staThreads = []
  i = 0
  for filename in os.listdir(r'E:\pythonProject\ruisi'):
    #没获取10个文本，就创建一个线程
    if filename.startswith("correct") or filename.startswith("errTime") or filename.startswith("unkownsex"):
      files.append(filename)
      i+=1
      if i == 20 :
        staThreads.append(StaFileList(files))
        files = []
        i = 0
  #最后剩余的files，很可能长度不足10个
  if files:
    staThreads.append(StaFileList(files))

  for t in staThreads:
    t.start()
  # 主线程中等待所有子线程退出
  for t in staThreads:
    t.join()



if __name__ == '__main__':
  reload(sys)
  sys.setdefaultencoding('utf-8')
  startTime = time.clock()
  mutex = threading.Lock()
  test()
  print "Multi Thread, total is %s; %s boys; %s girls; %s secret; %s unkownsex" %(SUM, BOY,GIRL,SECRET,UNKOWN)
  endTime = time.clock()
  print "cost time " + str(endTime - startTime) + " s"
  endTime = time.clock()
  print "cost time " + str(endTime - startTime) + " s"

 def __init__(self, fileList):
    threading.Thread.__init__(self)
    self.fileList = fileList

  def run(self):
    global SUM, BOY, GIRL, SECRET
    if mutex.acquire(1):
      #调用类内部方法需要加self
      self.staFiles(self.fileList)
      mutex.release()