案例_(多线程)爬取糗事百科-蒲公英云

讲解都写在代码注释中了,直接上代码

# 使用了线程库
import threading
# 队列
from queue import Queue
# 解析库
from lxml import etree
# 请求处理
import requests
# json处理
import time
class ThreadCrawl(threading.Thread):
    def __init__(self, thread_name, page_queue, data_queue):
        # threading.Thread.__init__(self)
        # 调用父类初始化方法
        super(ThreadCrawl, self).__init__()
        # 线程名
        self.thread_name = thread_name
        # 页码队列
        self.page_queue = page_queue
        # 数据队列
        self.data_queue = data_queue
        # 请求报头
        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.thread_name)
        while not CRAWL_EXIT:
            try:
                # 取出一个数字，先进先出
                # 可选参数block，默认值为True
                # 1. 如果对列为空，block为True的话，不会结束，会进入阻塞状态，直到队列有新的数据
                # 2. 如果队列为空，block为False的话，就弹出一个Queue.empty()异常，
                page = self.page_queue.get(False)
                url = "http://www.qiushibaike.com/8hr/page/" + str(page) + "/"
                # print url
                content = requests.get(url, headers=self.headers).text
                time.sleep(1)
                self.data_queue.put(content)
                # print len(content)
            except:
                pass
        print("结束 " + self.thread_name)
class ThreadParse(threading.Thread):
    def __init__(self, thread_name, data_queue):
        super(ThreadParse, self).__init__()
        # 线程名
        self.thread_name = thread_name
        # 数据队列
        self.data_queue = data_queue
    def run(self):
        print("启动" + self.thread_name)
        while not PARSE_EXIT:
            try:
                html = self.data_queue.get(False)
                self.parse(html)
            except:
                pass
        print("退出" + self.thread_name)
    def parse(self, html):
        selector = etree.HTML(html)
        # 返回所有段子的节点位置,contant()模糊查询方法,第一个参数是要匹配的标签,第二个参数是这个标签的部分内容
        # 每个节点包括一条完整的段子(用户名,段子内容,点赞,评论等)
        node_list = selector.xpath('//div[contains(@id,"qiushi_tag_")]')
        for node in node_list:
            # 爬取所有用户名信息
            # 取出标签里的内容,使用.text方法
            user_name = node.xpath('./div[@class="author clearfix"]//h2')[0].text
            # 爬取段子内容,匹配规则必须加点  不然还是会从整个页面开始匹配
            # 注意:如果span标签中有br 在插件中没问题,在代码中会把br也弄进来
            duanzi_info = node.xpath('.//div[@class="content"]/span')[0].text.strip()
            # 爬取段子的点赞数
            vote_num = node.xpath('.//span[@class="stats-vote"]/i')[0].text
            # 爬取评论数
            comment_num = node.xpath('.//span[@class="stats-comments"]//i')[0].text
            # 爬取图片链接
            # 属性src的值,所以不需要.text
            img_url = node.xpath('.//div[@class="thumb"]//@src')
            if len(img_url) > 0:
                img_url = img_url[0]
            else:
                img_url = "无图片"
            self.save_info(user_name, duanzi_info, vote_num, comment_num, img_url)
    def save_info(self, user_name, duanzi_info, vote_num, comment_num, img_url):
        """把每条段子的相关信息写进字典"""
        item = {
            "username": user_name,
            "content": duanzi_info,
            "zan": vote_num,
            "comment": comment_num,
            "image_url": img_url
        }
        print(item)
CRAWL_EXIT = False
PARSE_EXIT = False
def main():
    # 页码的队列，表示20个页面
    pageQueue = Queue(20)
    # 放入1~10的数字，先进先出
    for i in range(1, 21):
        pageQueue.put(i)
    # 采集结果(每页的HTML源码)的数据队列，参数为空表示不限制
    dataQueue = Queue()
    filename = open("duanzi.json", "a")
    # 创建锁
    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
    thread_crawl = []
    for threadName in crawlList:
        thread = ThreadCrawl(threadName, pageQueue, dataQueue)
        thread.start()
        thread_crawl.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
    thread_parse = []
    for threadName in parseList:
        thread = ThreadParse(threadName, dataQueue)
        thread.start()
        thread_parse.append(thread)
    # 等待pageQueue队列为空，也就是等待之前的操作执行完毕
    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为空")
    for thread in thread_crawl:
        thread.join()
    while not dataQueue.empty():
        pass
    global PARSE_EXIT
    PARSE_EXIT = True
    for thread in thread_parse:
        thread.join()
if __name__ == "__main__":
    main()