线程池实现糗事百科爬取

最新推荐文章于 2021-02-04 17:51:03 发布

Xs-1

最新推荐文章于 2021-02-04 17:51:03 发布

阅读量137

点赞数

分类专栏： python爬虫

本文链接：https://blog.csdn.net/qq_44224678/article/details/107169255

版权

python爬虫专栏收录该内容

7 篇文章 0 订阅

订阅专栏

线程池实现糗事百科爬取

import requests
from lxml import etree
from queue import Queue
from pprint import pprint
from multiprocessing.dummy import Pool
import time


class Qiubai:
    def __init__(self):
        self.temp_url = "https://www.qiushibaike.com/hot/page/{}"
        self.headers = {
            "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.68 Safari/537.36"}
        self.queue = Queue()
        self.pool = Pool()
        self.is_running = 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))
            # print(self.temp_url.format(i))
            self.total_request_num += 1

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

    def get_content_list(self, html_str):
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@class='col1 old-style-col1']/div")
        content_list = []
        for div in div_list:
            item = {}
            item['user_name'] = div.xpath(".//h2/text()")[0].strip()
            item['content'] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
            content_list.append(item)
        return content_list

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


    def _execute_request_content_save(self):  # 进行一次url请求，提取，保存
        url = self.queue.get()
        html_str = self.parse_url(url)
        content_list = self.get_content_list(html_str)
        self.save_content_list(content_list)
        self.total_response_num += 1

    def _callback(self, temp):
        if self.is_running:
            self.pool.apply_async(self._execute_request_content_save, callback=self._callback)

    def run(self):
        # 1. 准备url列表
        self.get_url_list()
        for i in range(3):
            self.pool.apply_async(self._execute_request_content_save, callback=self._callback)
        while True:
            time.sleep(0.0001)
            if self.total_response_num >= self.total_request_num:
                self.is_running = False
                break


if __name__ == "__main__":
    qiubai = Qiubai()
    qiubai.run()