下载redis数据库
首先需要下载redis数据库，可以直接去Redis官网下载。或者可以看这里下载过程。
pycharm项目文件下载redis库
> pip install redis
然后在程序中连接redis服务：
from redis import RedisredisObj = Redis(host='127.0.0.1', port=6379)
这次笔记记录爬取芒果TV的视频信息，通过md5加密并去重存入Redis数据库。
目标地址：https://www.mgtv.com/lib/2?lastp=list_index&lastp=ch_tv&kind=19&area=10&year=all&sort=c2&chargeInfo=a1&fpa=2912&fpos=
爬取视频的名称，简介、演员及上映时间吧，代码示例：
import requests
import redis
import pymongo
import hashlib
import json
import timeclass MangGuo:url = 'https://pianku.api.mgtv.com/rider/list/pcweb/v3?allowedRC=1&platform=pcweb&channelId=2&pn=3&pc=80&hudong=1&_support=10000000&kind=19&area=10&year=all&chargeInfo=a1&sort=c2&feature=all'headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'}def __init__(self):self.redis_obj = redis.Redis(host="localhost", port=6379)self.mongo = pymongo.MongoClient()self.mongo_connection = self.mongo['py_spider']['movies']@classmethoddef get_tv_list(cls):response = requests.get(cls.url, headers=cls.headers).json()# print(response["data"]["hitDocs"])return response["data"]["hitDocs"]def parse_tv_list(self):data_lists = self.get_tv_list()for data in data_lists:deal_data = dict()deal_data["name"] = data["title"]deal_data["desc"] = data["story"]deal_data["stars"] = data["subtitle"]deal_data["year"] = data["year"]print(deal_data)# obj = hashlib.md5()# obj.update(json.dumps(data).encode())# res = obj.hexdigest()hash_obj = hashlib.md5(json.dumps(deal_data).encode()).hexdigest()self.insert_redis(deal_data, hash_obj)# 插入数据到Redis数据库并进行去重def insert_redis(self, data, hash_data):result = self.redis_obj.sadd('movies:filter', hash_data)# 插入数据成功返回1，失败返回0# print(result)if result:print('数据插入成功')# 插入成功说明是没有重复数据的，也就是作去重后多插入一份到MongoDB数据库self.insert_mongodb(data)else:print('重复数据，插入失败')def insert_mongodb(self, data):self.mongo_connection.insert_one(data)# 休眠测试是否同步# time.sleep(1.5)def main(self):self.parse_tv_list()if __name__ == '__main__':manGuo = MangGuo()manGuo.main()
