采用多进程实现糗事百科的爬取

from multiprocessing import Process
p1 = Process(target=func,args=(,))
p1.daemon = True  #设置为守护进程
p1.start() #此时线程才会启动

3.2 多进程中队列的使用

多进程中使用普通的队列模块会发生阻塞，对应的需要使用multiprocessing提供的JoinableQueue模块，其使用过程和在线程中使用的queue方法相同

"""
@author:Rudy

@time : 12月5日

@message:多进程爬取糗事百科热门上的段子用户昵称

"""


from multiprocessing import Process
import requests
from lxml import etree
from multiprocessing import JoinableQueue as Queue
import time


class QiuBai():
    def __init__(self):
        self.temp_url = "https://www.qiushibaike.com/8hr/page{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36"}
        self.url_queue = Queue()
        self.html_queue = Queue()
        self.content_list_queue = Queue()
        self.proxies = {"http":"http://58.242.136.18:808"} # 可以在此添加IP代理

    def get_url_list(self):
        for i in range(1,14):
            self.url_queue.put(self.temp_url.format(i))

    def parse_url(self): # 不在接收参数,而是直接从url列表中取
        while True:
            url = self.url_queue.get()
            response = requests.get(url, headers=self.headers,proxies=self.proxies)
            print(response)
            if response.status_code != 200:
                self.url_queue.put(url)
            # return response.content.decode() 取完之后不在返回
            else:
                self.html_queue.put(response.content.decode())
            self.url_queue.task_done() # 让队列的计数减1

    def get_content_list(self):  # 提取数据
        while True:
            html_str = self.html_queue.get()
            html = etree.HTML(html_str)
            div_list = html.xpath("//div[@id='content-left']/div")
            content_list = []
            for div in div_list:
                item = {}
                item["user_name"] = div.xpath(".//h2/text()")
                item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")] # 列表推导式
                content_list.append(item)
            # return content_list
            self.content_list_queue.put(content_list)
            self.html_queue.task_done()

    def save_content_list(self):
        while True:
            content_list = self.content_list_queue.get()
            for content in content_list:
                # print(content)
                pass
            self.content_list_queue.task_done()

    def run(self):  # 实现主要的逻辑
        thread_list = []
        # 1 准备URL列表
        t_url = Process(target= self.get_url_list)
        thread_list.append(t_url)
        # 2 遍历发送请求,获取响应
        for i in range(4): # 启动3个进程,如果感觉爬取速度还很慢,可以加大进程
            t_parse = Process(target=self.parse_url)
            thread_list.append(t_parse)
        # 3 提取数据
        t_content = Process(target=self.get_content_list)
        thread_list.append(t_content)
        # 4 保存
        t_save = Process(target=self.save_content_list)
        thread_list.append(t_save)

        for process in thread_list: # 设置子进程守护线程
            process.daemon = True
            process.start()

        for q in [self.url_queue,self.content_list_queue,self.html_queue]:
            q.join() # 让主进程阻塞,等待队列计数为0


if __name__ == '__main__':
    t1 = time.time()
    qiubai = QiuBai()
    qiubai.run()
    print("total cost:",time.time()-t1)