scrapy持久化

官网：https://docs.scrapy.org/en/latest/

a、pipeline的四个作用

官方

1、持久化

2、去重

3、清理HTML数据

4、验证爬取的数据，检测爬取的字段
我的认知

持久化、去重、数据清洗(取空格，换行符，引号等)

b、流程

1、yield item

2、process_items

　　return item　　# 添加成功

　　raise DropItem 　　# 添加失败

注意：item类可以定义 table_name = "表名"。用于mysql的储存

一、磁盘文件

1、基于终端指令的持久化存储

item

scrapy crawl quote -o qutoes.json

2、基于管道的持久化存储

保存图片

二、数据库

1、mysql(注意：自定义ip池可以参考这个作为修改)

import pymysql

def MysqlPipeline(object):
    def __init__(self, host, database, user, password, port):
        self.host = host
        self.database = database
        self.user = user
        self.password = password
        self.port = port
    @classmethod  
    def from_crawler(self, crawler):
        return cls(
            host = crawler.settings.get('MYSQL_HOST')
            database = crawler.settings.get('MYSQL_DATABASE')
            user = crawler.settings.get('MYSQL_USER')
            password= crawler.settings.get('MYSQL_PASSWORD')
            port = crawler.settings.get('MYSQL_PORT')
        )
    
    def open_spider(self, spider):
        self.conn = pymysql.connect(self.host, self.user, self.password, self.database, charset='utf-8', port=self.port)
        self.cursor = self.conn.cursor()
        
    def process_item(self, item, spider):
        data = dict(item)
        keys = ','.join(data.keys())
        values = ','.join(['%s']*len(data))
        sql = 'insert into %s (%s) values (%s)' % (table, keys, values)
        try:
            self.cursor.execute(sql, tuple(data.values()))
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()
        return item
    
    def close_spider(self):
        self.cursor.close()
        self.conn.close()

 

2、mogodb

import Pymongo
class MongoPipeline(object):
    def __init__(self, mongo_uri, mongo_db):
        self.mongo_url = mongo_uri
        self.mongo_db = mongo_db
        
    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_url = crawler.settings.get('MONGO_URI'),
            mongo_db = crawler.settings.get('MONGO_DB')
        )
    
    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]
        
    def process_item(self, item, spider):
        try:
            self.db[collection].insert(dict(item))
        except Exception as e:
            print(e)
        return item
    
    def close_spider(self, spider):
        self.client.close()

 

4、redis

import redis
import json
class FirstprojectPipeline(object):
    def __init__(self, redis_host, redis_port, redis_pwd):
        self.redis_host = redis_host
        self.redis_port = redis_port
        self.redis_pwd = redis_pwd
       
       @classmethod
    def from_crawler(cls, crawler):
        return cls(
            redis_host = crawler.settings.get('REDIS_HOST'),
            redis_port = crawler.settings.get('REDIS_PORT'),
            redis_pwd = crawler.settings.get('REDIS_PWD')
        )
 
    def open_spider(self, spider):
        print("start spider")
        self.conn = redis.Redis(host=self.redis_host, port=self.redis_port, password=self.redis_pwd)
 
    def process_item(self, item, spider):
        my_dict = {
            "author": item['author'],
            'content': item['content'],
        }
        # print(my_dict)
        try:
            self.conn.rpush("my_data", json.dumps(my_dict))
        except Exception as e:
            print(e)
        return item

 或

import redis
from scrapy.exceptions import DropItem


class FirstprojectPipeline(object):
    def __init__(self, redis_host, redis_port, redis_pwd):
        self.redis_host = redis_host
        self.redis_port = redis_port
        self.redis_pwd = redis_pwd

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            redis_host=crawler.settings.get('REDIS_HOST'),
            redis_port=crawler.settings.get('REDIS_PORT'),
            redis_pwd=crawler.settings.get('REDIS_PWD')
        )

    def open_spider(self, spider):
        self.conn = redis.Redis(host=self.redis_host, port=self.redis_port, password=self.redis_pwd)

    def process_item(self, item, spider):
　　　　 # 集合
        if self.conn.sadd(spider.name, item['name']):
            return item
        raise DropItem