Scrapy之pipeline&扩展

1.自定义pipeline

#一：可以写多个Pipeline类
#1、如果优先级高的Pipeline的process_item返回一个值或者None，会自动传给下一个pipline的process_item,
#2、如果只想让第一个Pipeline执行，那得让第一个pipline的process_item抛出异常raise DropItem()

#3、可以用spider.name == '爬虫名' 来控制哪些爬虫用哪些pipeline

二：示范
from scrapy.exceptions import DropItem

class CustomPipeline(object):
    def __init__(self,v):
        self.value = v

    @classmethod
    def from_crawler(cls, crawler):
        """
        Scrapy会先通过getattr判断我们是否自定义了from_crawler,有则调它来完
        成实例化
        """
        val = crawler.settings.getint('MMMM')
        return cls(val)

    def open_spider(self,spider):
        """
        爬虫刚启动时执行一次
        """
        print('000000')

    def close_spider(self,spider):
        """
        爬虫关闭时执行一次
        """
        print('111111')


    def process_item(self, item, spider):
        # 操作并进行持久化

        # return表示会被后续的pipeline继续处理
        return item

        # 表示将item丢弃，不会被后续pipeline处理
        # raise DropItem()

实例

#1、settings.py
HOST="127.0.0.1"
PORT=27017
USER="root"
PWD="123"
DB="amazon"
TABLE="goods"



ITEM_PIPELINES = {
   'Amazon.pipelines.CustomPipeline': 200,
}

#2、pipelines.py
class CustomPipeline(object):
    def __init__(self,host,port,user,pwd,db,table):
        self.host=host
        self.port=port
        self.user=user
        self.pwd=pwd
        self.db=db
        self.table=table

    @classmethod
    def from_crawler(cls, crawler):
        """
        Scrapy会先通过getattr判断我们是否自定义了from_crawler,有则调它来完
        成实例化
        """
        HOST = crawler.settings.get('HOST')
        PORT = crawler.settings.get('PORT')
        USER = crawler.settings.get('USER')
        PWD = crawler.settings.get('PWD')
        DB = crawler.settings.get('DB')
        TABLE = crawler.settings.get('TABLE')
        return cls(HOST,PORT,USER,PWD,DB,TABLE)

    def open_spider(self,spider):
        """
        爬虫刚启动时执行一次
        """
        self.client = MongoClient('mongodb://%s:%s@%s:%s' %(self.user,self.pwd,self.host,self.port))

    def close_spider(self,spider):
        """
        爬虫关闭时执行一次
        """
        self.client.close()


    def process_item(self, item, spider):
        # 操作并进行持久化

        self.client[self.db][self.table].save(dict(item))

2. 自定义扩展

自定义扩展（与django的信号类似）
    1、django的信号是django是预留的扩展，信号一旦被触发，相应的功能就会执行
    2、scrapy自定义扩展的好处是可以在任意我们想要的位置添加功能，而其他组件中提供的功能只能在规定的位置执行

#1、在与settings同级目录下新建一个文件，文件名可以为extentions.py,内容如下
from scrapy import signals


class MyExtension(object):
    def __init__(self, value):
        self.value = value

    @classmethod
    def from_crawler(cls, crawler):
        val = crawler.settings.getint('MMMM')
        obj = cls(val)

        crawler.signals.connect(obj.spider_opened, signal=signals.spider_opened)
        crawler.signals.connect(obj.spider_closed, signal=signals.spider_closed)

        return obj

    def spider_opened(self, spider):
        print('=============>open')

    def spider_closed(self, spider):
        print('=============>close')

#2、配置生效
EXTENSIONS = {
    "Amazon.extentions.MyExtension":200
}