爬虫实战30：多线程爬取bilibili网站视频数据

# coding:utf-8

# 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 requests
import json
import json
import bs4
import time
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
result = []

class ThreadCrawl(threading.Thread):
    def __init__(self, threadName, pageQueue, dataQueue):
        #threading.Thread.__init__(self)
        # 调用父类初始化方法
        super(ThreadCrawl, self).__init__()
        # 线程名
        self.threadName = threadName
        # 页码队列
        self.pageQueue = pageQueue
        # 数据队列
        self.dataQueue = dataQueue
        # 请求报头
        self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}

    def run(self):
        print("启动 " + self.threadName)
        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.pageQueue.get(False)
                url = 'https://search.bilibili.com/all?keyword=爬虫&from_source=nav_search&spm_id_from=333.851.b_696e7465726e6174696f6e616c486561646572.11' + '&page=' + str(page)

                response = requests.get(url, headers=self.headers, verify=False).text
                time.sleep(0.5)
                try:
                    soup = bs4.BeautifulSoup(response, 'lxml').find('div', attrs={'id': 'all-list'})
                    ul = soup.find('ul', attrs={'class': 'video-list clearfix'}).find_all('li',
                                                                                          attrs={
                                                                                              'class': 'video-item matrix'})
                    for item in ul:
                        # print(item)
                        info = item.find('div', attrs={'class': 'headline clearfix'}).find('span',
                                                                                           attrs={
                                                                                               'class': 'type avid'}).get_text()
                        aid = info.replace('av', '')
                        # print(aid)
                        self.dataQueue.put(aid)
                        result.append(aid)
                    return result
                except:
                    print('something is wrong')
            except:
                pass


class ThreadParse(threading.Thread):
    def __init__(self, threadName, dataQueue, lock):
        super(ThreadParse, self).__init__()
        # 线程名
        self.threadName = threadName
        # 数据队列
        self.dataQueue = dataQueue
        # 保存解析后数据的文件名

        # 锁
        self.lock = lock
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}

    def run(self):
        print("启动" + self.threadName)

        while not PARSE_EXIT:
            try:
                aid = self.dataQueue.get(False)
                url = 'https://api.bilibili.com/x/web-interface/view?aid=' + str(aid)
                self.parse(url)
            except:
                pass
        print("退出" + self.threadName)

    def parse(self, url):
        response = requests.get(url=url, headers=self.headers, verify=False).json()
        time.sleep(1)
        try:
            with self.lock:
                data_1 = response['data']
                data = data_1['stat']
                aid = data['aid']
                view = data['view']
                coin = data['coin']
                like = data['like']
                favorite = data['favorite']
                share = data['share']
                danmaku = data['danmaku']

                print('视频编号', aid)
                print('观看数量', view)
                print('投币数量', coin)
                print('收藏数量', favorite)
                print('点赞数量', like)
                print('分享数量', share)
                print('弹幕数量', danmaku)
                print('------------')

        except:
            print('------------++++')

CRAWL_EXIT = False
PARSE_EXIT = False


def main():
    # 页码的队列，表示50个页面
    pageQueue = Queue(50)
    # 放入1~10的数字，先进先出
    for i in range(1, 51):
        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", "采集线程4号", "采集线程5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","解析线程4号","解析线程5号","解析线程6号"]
    # 存储三个解析线程
    threadparse = []
    for threadName in parseList:
        thread = ThreadParse(threadName, dataQueue, lock)
        thread.start()
        threadparse.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 threadcrawl:
        thread.join()
        print("1")



    while not dataQueue.empty():
        pass

    global PARSE_EXIT
    PARSE_EXIT = True
    print("dataQueue为空")

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

    with lock:
        pass

    print("谢谢使用！")

if __name__ == "__main__":
    main()