对糗事百科进行了重构-协程池(高性能)

Author: Kr1s77

qsbk/qiushibaike.py

@@ -1,88 +1,83 @@
-#!/usr/bin/env python3.6
-# coding=utf-8
+# !/usr/bin/python3
+# -*- coding: utf-8 -*-
+
+# 1. 导入线程池模块
+# 线程池
+import gevent.monkey
+gevent.monkey.patch_all()
+from gevent.pool import Pool
+from queue import Queue
 import requests
 from lxml import etree
-import os
-import sys
-
-"""
-info:
-author:CriseLYJ
-github:https://github.com/CriseLYJ/
-update_time:2019-3-9
-"""
-page_init = "https://www.qiushibaike.com/text/"
-joke_init = "https://www.qiushibaike.com/article/"
-SAVE_PATH = os.path.join(os.getcwd(), 'jokes/')
-
-
-class Spider(object):
-    def __init__(self, page_num):
-        self.page_num = int(page_num)
-        # 第一页特殊处理
-        self.page_urls = ["https://www.qiushibaike.com/text/"]
-        # page_url -> joke_url
-        self.joke_urls = []
-        # joke_url -> joke_name joke_content
-        # dict name : content
-        self.joke_content = ""
-        self.joke_id = 1;
-        try:
-            os.mkdir(SAVE_PATH)
-        except Exception as e:
-            print(e)
-
-    def get_page_urls(self):
-        if self.page_num > 1:
-            # 通过遍历获取到链接
-            for n in range(2, self.page_num + 1):
-                page_url = page_init + 'page/' + str(n) + '/'
-                self.page_urls.append(page_url)
-
-    def get_joke_urls(self):
-        for page_url in self.page_urls:
-            html = requests.get(page_url).content
-            selector = etree.HTML(html)
-            qiushi_id = selector.xpath('/html/body/div[@id="content"]/div/div[@id="content-left"]/div/@id')
-            for q_id in qiushi_id:
-                id = q_id.split('_')[2]
-                joke_url = joke_init + id + '/'
-                print(joke_url)
-                self.joke_urls.append(joke_url)
-
-    def get_joke(self):
-        for joke_url in self.joke_urls:
-            html = requests.get(joke_url).content
-            selector = etree.HTML(html)
-            one_joke = selector.xpath('//div[@class="word"]/div/text()')
-            self.joke_content = ""
-            for words in one_joke:
-                self.joke_content += words + '\n'
-            self.download()
-
-    def download(self):
-        joke_path = SAVE_PATH + str(self.joke_id) + '.txt'
-        self.joke_id += 1
-        # 笑话路径
-        print(joke_path)
-        with open(joke_path, "w") as f:
-            f.write(self.joke_content)
-
-    def start(self):
-        # 获取主页url
-        self.get_page_urls()
-        # 获取笑话链接
-        self.get_joke_urls()
-        # 获取笑话
-        self.get_joke()
-        # 调用下载接口
-        self.download()
 
+class QiushiSpider():
 
-if __name__ == '__main__':
-    # 获取账号
-    page_num = input('请告诉我：你想获取多少页的糗事？')
+    def __init__(self, max_page):
+        self.max_page = max_page
+        # 2. 创建线程池，初始化线程数量
+        self.pool = Pool(5)
+
+        self.base_url = "http://www.qiushibaike.com/8hr/page/{}/"
+        self.headers = {
+            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"
+        }
+
+        # 专门存放 url 容器
+        self.url_queue = Queue()
+        pass
+
+    def get_url_list(self):
+        '''
+        获取 url 列表放入到 url 容器中
+        :return:
+        '''
+        for page in range(1,self.max_page,1):
+            url = self.base_url.format(page)
+            self.url_queue.put(url)
+
+    # 3. 实现执行任务
+    def exec_task(self):
+        # 1> 获取url
+        url = self.url_queue.get()
+
+        # 2> 发送请求获取 html
+        response = requests.get(url,headers=self.headers)
+        html = response.text
+
+        # 3> 解析 html 提取数据
+        eroot = etree.HTML(html)
+
+        titles = eroot.xpath('//a[@class="recmd-content"]/text()')
+        for title in titles:
+            item = {}
+            item["title"] = title
 
-    qb = Spider(page_num)
-    # 启动爬虫程序
-    qb.start()
+            # 4> 保存数据
+            print(item)
+        self.url_queue.task_done()
+
+
+
+    # 4. 实现执行任务完成后的操作,必须至少有一个参数
+    # result 任务执行的最终结果的返回值
+    def exec_task_finished(self,result):
+        print("result:",result)
+        print("执行任务完成")
+        self.pool.apply_async(self.exec_task,callback=self.exec_task_finished)
+
+
+    def run(self):
+
+        self.get_url_list()
+
+        # 5. 让任务使用线程池中的线程执行并且设置执行后的回调操作
+        # callback 表示执行完成后的回调
+        for i in range(5):
+            self.pool.apply_async(self.exec_task,callback=self.exec_task_finished)
+        self.url_queue.join()
+        pass
+
+if __name__ == '__main__':
+    max_page = input("请输入您需要多少页内容：")
+    spider = QiushiSpider(int(max_page))
+    spider.run()