基于python实现生产者与消费者实例-多线程获取儒林外史电子书

1. 代码实现
# -*- coding: utf-8 -*-
import re
from queue import Queue
from threading import Thread
import requests

article_url = []


class Producer(Thread):
    """生产者"""

    def __init__(self):
        Thread.__init__(self)

    def run(self):
        while True:
            if not url_queue.empty():
                try:
                    url = url_queue.get()
                    data = requests.get(url)
                    html = data.content.decode('gbk')
                    title = re.findall(r"<title>(.*?)</title>", html, re.S)[0]
                    content = re.findall('<p>(.*?)</p>', html, re.S)[0]
                    content = content.replace('&nbsp;', '')  # 替换 &nbsp; 网页空格符
                    print(title)
                    content_queue.put({title: content})
                except Exception as e:
                    print(e)
            else:
                break


class Consumer(Thread):
    """消费者"""

    def __init__(self):
        Thread.__init__(self)

    def run(self):
        while True:
            if content_queue.empty() and flag:
                break
            try:
                article = content_queue.get()
                title, content = list(article.keys())[0], list(article.values())[0]
                print('--------- 正在保存{} ---------'.format(title))
                with open('./{}.txt'.format(title), mode='a') as f:
                    f.write(content)
            except Exception as e:
                print(e)


def get_url_list(url_queue):
    content = requests.get(base_url).content.decode('gbk')
    url_flg = re.findall(r'a href="2560/(.*?).html"', content, re.S)
    for url in url_flg:
        url_queue.put(base_url.replace('.html', '/{}.html').format(url))
    return url_queue


if __name__ == '__main__':
    base_url = 'https://www.kanunu8.com/files/old/2011/2560.html'
    # 1.创建url、章回内容线程池
    url_queue = Queue()
    content_queue = Queue()
    # 获取url队列
    url_queue = get_url_list(url_queue)

    # 2.创建生产者
    crawl = []
    for i in range(5):
        t = Producer()
        t.start()
        crawl.append(t)

    # 3. 创建消费者
    flag = False
    for i in range(5):
        c = Consumer()
        c.start()

    # 4.保证p都做完了，将flag-->False
    # 阻塞在这里--监测p都是否完成。---join()
    a = [p.join() for p in crawl]
    print('-------- 生产者任务完成 --------')
    flag = True