python---多线程采集示例

# coding:utf-8
import urllib2

import time
from lxml import etree
from bs4 import BeautifulSoup
import requests
import types
import sys
import json
from Queue import Queue
import threading

CRAWL_EXIT = False
PARSE_EXIT = False

class ThreadCrawl(threading.Thread):
    def __init__(self, threadName, pageQueue, dataQueue):
        # threading.Thread.__init__(self)
        super(ThreadCrawl, self).__init__()
        self.threadName = threadName
        self.pageQueue = pageQueue
        self.dataQueue = dataQueue
        self.headers = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}

    def run(self):
        print "启动 " + self.threadName
        while not CRAWL_EXIT:
            try:
                page = self.pageQueue.get(False)
                url = "https://tieba.baidu.com/f?kw=%E5%A6%B9%E5%AD%90&ie=utf-8&pn=" + str(page * 50)
                content = requests.get(url, headers=self.headers).text
                time.sleep(1)
                self.dataQueue.put(content)
            except:
                pass

        print "结束 " + self.threadName


class ThreadParse(threading.Thread):
    def __init__(self, threadName, dataQueue, filename, lock):
        super(ThreadParse, self).__init__()
        self.threadName = threadName
        self.dataQueue = dataQueue
        self.fileName = filename
        self.lock = lock

    def run(self):
        print "启动" + self.threadName
        while not PARSE_EXIT:
            try:
                html = self.dataQueue.get(False)
                self.parse(html)
            except:
                pass
        print "退出" + self.threadName

    def parse(self, html):
        html = etree.HTML(html)
        nodeList = html.xpath('//*[@id="thread_list"]//li/div/div[2]/div[1]/div[1]/a')
        for title in nodeList:
            items = {
                "title" : title.text
            }
            with self.lock:
                self.fileName.write(json.dumps(items, ensure_ascii=False).encode("utf-8") + "\n")





def main():
    pageQueue = Queue(10)
    for i in range(1, 11):
        pageQueue.put(i)

    dataQueue = Queue()

    filename = open("duanzi.json", "a")

    lock = threading.Lock()

    # 三个采集线程的名字
    crawlList = ["采集线程1号", "采集线程2号", "采集线程3号"]
    # 存储三个采集线程的列表集合
    threadcrawl = []
    for threadName in crawlList:
        thread = ThreadCrawl(threadName, pageQueue, dataQueue)
        thread.start()
        threadcrawl.append(thread)

    # 三个解析线程的名字
    parseList = ["解析线程1号", "解析线程2号", "解析线程3号"]
    # 存储三个解析线程
    threadparse = []
    for threadName in parseList:
        thread = ThreadParse(threadName, dataQueue, filename, lock)
        thread.start()
        threadparse.append(thread)

    while not pageQueue.empty():
        pass

    # 如果pageQueue为空，采集线程退出循环
    global CRAWL_EXIT
    CRAWL_EXIT = True

    print "pageQueue is empty"

    for thread in threadcrawl:
        thread.join()
        print "1"

    while not dataQueue.empty():
        pass

    global PARSE_EXIT
    PARSE_EXIT = True

    for thread in threadparse:
        thread.join()
        print "2"

    with lock:
        # 关闭文件
        filename.close()
    print "谢谢使用！"


if __name__ == "__main__":
    main()