update struct

Author: Germey

Diff for: .idea/workspace.xml

@@ -1 +0,0 @@
-__author__ = 'WiseDoge'

Diff for: proxypool/__init__.py

@@ -1,16 +1,3 @@
-"""
--------------------------------------------------
-    File Name:     api.py
-    Description:   API模块，运行后打开浏览器，访问
-                   http://127.0.0.1:5000/进入主页。
-                   访问 http://127.0.0.1:5000/get 
-                   从代理池中获取一个代理。 
-                   访问 http://127.0.0.1:5000/count
-                   获取代理池中可用代理的总数。
-    Author:        Liu
-    Date:          2016/12/9
--------------------------------------------------
-"""
 from flask import Flask, g
 
 from .db import RedisClient

Diff for: proxypool/api.py

@@ -1,16 +1,6 @@
-"""
--------------------------------------------------
-    File Name:     db.py
-    Description:   数据库操作模块，负责对象与底层数据库
-                   的交互。
-    Author:        Liu
-    Date:          2016/12/9
--------------------------------------------------
-"""
 import redis
-
-from .error import PoolEmptyError
-from .setting import HOST, PORT
+from proxypool.error import PoolEmptyError
+from proxypool.setting import HOST, PORT
 
 
 class RedisClient(object):
@@ -19,21 +9,21 @@ class RedisClient(object):
     """
 
     def __init__(self, host=HOST, port=PORT):
-        self.__db = redis.Redis(host, port)
+        self._db = redis.Redis(host, port)
 
     def get(self, count=1):
         """从Pool中获取一定量数据。"""
-        proxies = self.__db.lrange("proxies", 0, count - 1)
-        self.__db.ltrim("proxies", count, -1)
+        proxies = self._db.lrange("proxies", 0, count - 1)
+        self._db.ltrim("proxies", count, -1)
         return proxies
 
     def put(self, proxy):
         """将代理压入Pool中。
         用Redis的set容器来负责去重，如果proxy能被压入proxy_set，
         就将其放入proxy pool中，否则不压入。
         """
-        if self.__db.sadd("proxy_set", proxy):
-            self.__db.rpush("proxies", proxy)
+        if self._db.sadd("set", proxy):
+            self._db.rpush("proxies", proxy)
         else:
             pass
 
@@ -47,17 +37,22 @@ def pop(self):
         """弹出一个可用代理。
         """
         try:
-            return self.__db.blpop("proxies", 30)[1].decode('utf-8')
+            return self._db.blpop("proxies", 30)[1].decode('utf-8')
         except:
             raise PoolEmptyError
 
     @property
     def queue_len(self):
         """获取proxy pool的大小。
         """
-        return self.__db.llen("proxies")
+        return self._db.llen("proxies")
 
     def flush(self):
         """刷新Redis中的全部内容，测试用。
         """
-        self.__db.flushall()
+        self._db.flushall()
+
+
+if __name__ == '__main__':
+    conn = RedisClient()
+    print(conn.get(20))

Diff for: proxypool/db.py

@@ -1,13 +1,3 @@
-"""
--------------------------------------------------
-    File Name:     error.py
-    Description:   异常模块
-    Author:        Liu
-    Date:          2016/12/9
--------------------------------------------------
-"""
-
-
 class ResourceDepletionError(Exception):
     """
     资源枯竭异常，如果从所有抓取网站都抓不到可用的代理资源，

Diff for: proxypool/error.py

@@ -1,18 +1,3 @@
-"""
--------------------------------------------------
-    File Name:     proxyGetter.py
-    Description:   代理抓取模块，负责与网络的交互。
-                   注意，代理网站的HTML结构可能会时常的更新，
-                   会导致本文件下的抓取函数失效，所以，在运行
-                   代理池之前，需要更新一下FreeProxyGetter类
-                   中以crawl_开头的方法。
-    Author:        Liu
-    Date:          2016/12/9
--------------------------------------------------
-"""
-
-import time
-
 from .utils import get_page
 from pyquery import PyQuery as pq
 
@@ -43,7 +28,7 @@ class FreeProxyGetter(object, metaclass=ProxyMetaclass):
     添加器会自动识别并调用此类函数。
     """
 
-    def get_raw_proxies(self, callback, count=40):
+    def get_raw_proxies(self, callback):
         proxies = []
         print('Callback', callback)
         for proxy in eval("self.{}()".format(callback)):

Diff for: proxypool/getter.py

@@ -1,56 +1,49 @@
-"""
--------------------------------------------------
-    File Name:     schedule.py
-    Description:   调度器模块，
-                   包含ValidityTester，PoolAdder，
-                   Schedule三个类，负责维护代理池。
-    Author:        Liu
-    Date:          2016/12/9
--------------------------------------------------
-"""
 import time
 from multiprocessing import Process
 import asyncio
 import aiohttp
-from .db import RedisClient
-from .error import ResourceDepletionError
-from .getter import FreeProxyGetter
-from .setting import *
+from proxypool.db import RedisClient
+from proxypool.error import ResourceDepletionError
+from proxypool.getter import FreeProxyGetter
+from proxypool.setting import *
 
 
 class ValidityTester(object):
     """
     检验器，负责对未知的代理进行异步检测。
     """
     # 用百度的首页来检验
-    test_api = 'http://www.baidu.com'
+    test_api = TEST_API
 
     def __init__(self):
         self._raw_proxies = None
         self._usable_proxies = []
 
     def set_raw_proxies(self, proxies):
-        """设置待检测的代理。
+        """
+        设置待检测的代理。
         """
         self._raw_proxies = proxies
         self._usable_proxies = []
 
     async def test_single_proxy(self, proxy):
-        """检测单个代理，如果可用，则将其加入_usable_proxies
+        """
+        检测单个代理，如果可用，则将其加入_usable_proxies
         """
         async with aiohttp.ClientSession() as session:
             try:
                 real_proxy = 'http://' + proxy
                 print('Testing', real_proxy)
                 async with session.get(self.test_api, proxy=real_proxy, timeout=15) as response:
                     await response
-                    print('Response from', proxy)
                     self._usable_proxies.append(proxy)
+                    print('Valid proxy', proxy)
             except Exception:
-                pass
+                print('Invalid proxy', proxy)
 
     def test(self):
-        """异步检测_raw_proxies中的全部代理。
+        """
+        异步检测_raw_proxies中的全部代理。
         """
         print('ValidityTester is working')
         loop = asyncio.get_event_loop()
@@ -92,9 +85,6 @@ def add_to_queue(self):
             for callback_label in range(self._crawler.__CrawlFuncCount__):
                 callback = self._crawler.__CrawlFunc__[callback_label]
                 raw_proxies = self._crawler.get_raw_proxies(callback)
-                self._tester.set_raw_proxies(raw_proxies)
-                self._tester.test()
-                self._conn.put_many(self._tester.get_usable_proxies())
                 proxy_count += len(raw_proxies)
             if proxy_count == 0:
                 raise ResourceDepletionError

Diff for: proxypool/schedule.py

@@ -1,12 +1,3 @@
-"""
--------------------------------------------------
-    File Name:     setting.py
-    Description:   设置模块，包含了一些常量。
-    Author:        Liu
-    Date:          2016/12/9
--------------------------------------------------
-"""
-
 # Redis Host
 HOST = 'localhost'
 # Redis PORT
@@ -18,3 +9,5 @@
 
 VALID_CHECK_CYCLE = 600
 POOL_LEN_CHECK_CYCLE = 20
+
+TEST_API='http://www.baidu.com'

Diff for: proxypool/setting.py

@@ -1,22 +1,18 @@
 import requests
-import lxml
 import asyncio
-import time
 import aiohttp
-from bs4 import BeautifulSoup
 from requests.exceptions import ConnectionError
 
 base_headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 \
-    (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36',
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36',
     'Accept-Encoding': 'gzip, deflate, sdch',
     'Accept-Language': 'zh-CN,zh;q=0.8'
 }
 
 
 def get_page(url, options={}):
     headers = dict(base_headers, **options)
-    print('Getting', url, headers)
+    print('Getting', url)
     try:
         r = requests.get(url, headers=headers)
         print('Getting result', url, r.status_code)