Python刷CSDN博客脚本v2.0

__author__ = 'change'
# coding=utf-8

"""
 ** Python Blog's Visit Count V2.0
 ** （V1.0 http://blog.csdn.net/change518/article/details/14108511）
 ** By change
 ** 2015.11.4
 ** http://blog.csdn.net/change518
 ** 首先遍历获取文章列表，提取每篇博客的地址
 ** 再构造HTTP请求访问这些地址，使用了线程提高速度
 ** 将博客中所有文章访问一遍，从而达到刷访问量的目的
 ** 由于缓存的原因，访问量一段时间后才会更新
"""

import urllib2
import re
import datetime
import Queue
import threading

# 记录程序运行开始时间
startTime = datetime.datetime.now()

# 线程数
threadNum = 10
threadList = []

# 所有文章链接地址列表
myList = list()
myLinks = Queue.Queue()

# 添加请求头
requestHeader = {'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.80 Safari/537.36"}

# 循环读取分页
for i in range(1, 5):
    url = "http://blog.csdn.net/change518/article/list/" + str(i) + "?viewmode=contents"
    request = urllib2.Request(url, headers=requestHeader)
    response = urllib2.urlopen(request)

    htmlResult = response.read()

    myPattern = '<span class="link_title"><a href="/change518/article/details/\d{7,8}">'
    firstResult = re.findall(myPattern, htmlResult)

    myPattern = '/change518/article/details/\d{7,8}'
    firstResultStr = ''.join(firstResult)
    myList += re.findall(myPattern, firstResultStr)

# 将List中的所有元素添加到Queue中
for linkAddress in myList:
    myLinks.put('http://blog.csdn.net' + linkAddress)


def mySpiderThread(j):
    """
    循环读取URL列表，使用Queue进行线程间资源同步
    :return:
    """
    while not (myLinks.empty()):
        singleLink = myLinks.get()
        request = urllib2.Request(singleLink, headers=requestHeader)
        print singleLink + " :" +str(j)
        for i in range(10):
            urllib2.urlopen(request)


# 建立 threadNum 个线程
for i in range(threadNum):
    t = threading.Thread(target=mySpiderThread, args=(i,))
    threadList.append(t)

# 开启 threadNum 个线程
for i in range(threadNum):
    threadList[i].start()

# 程序挂起，直到所有线程结束
for i in range(threadNum):
    threadList[i].join()


"""
如果不需要在所有线程执行完毕后进行一些操作，如统计所有线程的执行时间等
上面3个for循环也可以写成：

# 开启 threadNum 个线程
for i in range(threadNum):
    t = threading.Thread(target=mySpiderThread, args=(i,))
    t.start()

"""


print 'Done'

# 记录程序运行结束时间
endTime = datetime.datetime.now()
# 计算程序运行时长
print (endTime - startTime).seconds

.