使用协程池实现爬虫的具体实现

"""
@author:Rudy

@time : 12月5日

@message:采用协程池爬取糗事百科热门上的段子用户昵称

"""
import gevent.monkey

gevent.monkey.patch_all()
from gevent.pool import Pool

import time
from queue import Queue
import requests
from lxml import etree


# from multiprocessing.dummy import Pool


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.queue = Queue()
        self.pool = Pool(5)
        self.is_runnig = True
        self.total_request_num = 0
        self.total_response_num = 0

    def get_url_list(self):
        for i in range(1, 14):
            self.queue.put(self.temp_url.format(i))
            self.total_request_num += 1

    def parse_url(self, url):
        response = requests.get(url, headers=self.headers)
        return response.content.decode()

    def get_content_list(self, html_str):
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            item = {}
            item["username"] = div.xpath(".//h2/text()")[0]
            item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]  # 敲黑板
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list):
        for content in content_list:
            print(content)

    def _execete_request_content_save(self):
        url = self.queue.get()  # 进行一次url的地址的请求和保存
        html_str = self.parse_url(url)
        # 3 提取数据
        content_list = self.get_content_list(html_str)

        # 4 保存

        self.save_content_list(content_list)

        self.total_response_num += 1

    def _callback(self, temp):
        if self.is_runnig:
            self.pool.apply_async(self._execete_request_content_save, callback=self._callback)

    def run(self):  # 实现主要的逻辑
        # 1 获取URL
        self.get_url_list()
        for i in range(3):  # 设置并发数为3
            # 2 发送请求  获取响应
            self.pool.apply_async(self._execete_request_content_save, callback=self._callback)

        while True:
            time.sleep(0.0001)
            if self.total_response_num >= self.total_request_num:
                self.is_runnig = False
                break


if __name__ == '__main__':
    qiubai = QiuBai()
    qiubai.run()