协程池爬虫

# 线程池和协程池实现爬虫

# 学习目标

掌握协程池模块的使用
掌握使用线程池实现爬虫的流程

# 1 协程池模块使用介绍

协程池模块

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

1
2
3

# 2 使用协程池实现爬虫的具体实现过程

# coding=utf-8
import gevent.monkey
gevent.monkey.patch_all()
from gevent.pool import Pool

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

class QiubaiSpider:
    def __init__(self):
        self.url_temp = "https://www.qiushibaike.com/8hr/page/{}/"
        self.headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X \
        10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36"}
        self.queue = Queue()
        self.pool = Pool(5)
        self.is_running = True
        self.total_requests_num = 0
        self.total_response_num = 0

    def get_url_list(self):  # 获取url列表
        for i in range(1, 14):
            self.queue.put(self.url_temp.format(i))
            self.total_requests_num += 1

    def parse_url(self, url):  # 发送请求，获取响应
        return requests.get(url, headers=self.headers).content.decode()

    def get_content_list(self, html_str):  # 提取段子
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            content = {}
            content["content"] = div.xpath(".//div[@class='content']/span/text()")
            print(content)
            content_list.append(content)
        return content_list

    def save_content_list(self, content_list):  # 保存数据
        for content in content_list:
            print(content)  # 此处对数据进行保存操作

    def exetute_requests_item_save(self):
        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.exetute_requests_item_save, callback=self._callback)

    def run(self):
        self.get_url_list()

        for i in range(2):  # 控制并发
            self.pool.apply_async(self.exetute_requests_item_save, callback=self._callback)

        while True:  # 防止主线程结束
            time.sleep(0.0001)  # 避免cpu空转，浪费资源
            if self.total_response_num >= self.total_requests_num:
                self.is_running = False
                break

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

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70

# 小结

协程池的导包:from gevent.pool import Pool
协程池异步方法:pool.apply_async()

编辑

← 线程池爬虫小结→