#在進行操作之前，先把mongodb資料庫啟動起來，新建一個mongo_cache.py檔案

import pickle
import zlib
from datetime import datetime,timedelta

import requests
from pymongo import MongoClient
from bson.binary import Binary

class MongoCache(object):
    """
    資料庫快取
    """
    def __init__(self,client=None,expires=timedelta(days=30
 
)):
        self.client = MongoClient("localhost",27017)
        self.db = self.client.cache
        ##加速查詢設定索引，設定超時時間,如果達到expi reAfterSeconds設定的超時時間，mongodb會自動刪除超時資料
        self.db.webpage.create_index('timestamp',expireAfterSeconds=expires.total_seconds())


    def __setitem__(self, key, value):
        # 壓縮資料設定時間戳
        record 
 
= {"result":Binary(zlib.compress(pickle.dumps(value))),"timestamp":datetime.utcnow()}
        ##使用update的upsert (如果不存在執行insert,存在update)引數迸行插入更新操作，$set內建函式表示覆蓋原始資料
        self.db.webpage.update({"_id":key},{'$set':record},upsert=True)

    def __getitem__(self, item):
        #根據_id以item作為關鍵字，查詢相關網頁
        record 
 
= self.db.webpage.find_one({"_id":item})
        if record:
            #如果存在進行解壓縮反序列化
            return pickle.loads(zlib.decompress(record["result"]))
        else:
            raise KeyError(item + "does not exist")#找不到丟擲異常

    def __contains__(self, item):
        try:
            self[item]#執行__getitem__方法
        except KeyError:
            return False#捕獲到keyerror異常
        else:
            return True#找到相應資料說明說句酷白喊下載內容

    def clear(self):
        self.db.webpage.drop()

if __name__ == '__main__':
    mongo_cache = MongoCache()
    url = 'http://tieba.baidu.com/f?kw=貓&red_tag=1'
    response = requests.get(url)
    mongo_cache[url] = response.text
    print(mongo_cache[url])

#在建一個檔案
import requests

import mongo_cache

download_url = "http://tieba.baidu.com/f?kw=貓&red_tag=2"
download_response = requests.get(download_url)
m_cache = mongo_cache. MongoCache()
m_cache [download_url] = download_response.content
print (m_cache [download_url]. decode('utf-8'))
print(download_url in m_cache)