python爬虫框架scrapy之Pipeline的一些用法

1、启动pipeline

ITEM_PIPELINES = {
   # 'jingxi.pipelines.JingxiPipeline': 200,
   'jingxi.pipelines.BaiduPipeline': 300,
   'jingxi.pipelines.TencentPipeline': 100,
}

开启多个pipeline后，yield出的item会在所有pipeline中流转，流转的顺序以后便分配的数字为依据，数字越小，流转次序越高。

2、如何区分不同的pipeline

class BaiduPipeline:

    def open_spider(self, spider):
        if spider.name != 'baidu': return
        print("开始运行-百度爬虫")

    def process_item(self, item, spider):
        print('&&&&&&&&&',spider.name,item)
        print('进入通道')
        print("写入成功")
        return item

    def close_spider(self, spider):
        print("运行结束-百度爬虫")


class TencentPipeline:

    def open_spider(self, spider):
        if spider.name != 'tencent': return
        print("开始运行-腾讯爬虫")

    def process_item(self, item, spider):
        if spider.name != 'tencent': return item
        print('@@@@@@@@@@@@@',spider.name,item)
        print('进入通道')
        print("写入成功")
        return item

    def close_spider(self, spider):
        if spider.name != 'tencent': return
        print("运行结束-腾讯爬虫")

简单来说，就是以spider.name 区分不同的爬虫，当该item正好流转到该爬虫时，可截断它继续流转。当流过目标pipeline时，可将其直接抛出。

在pipelin中引入settings

import pymongo

class MongoPipeline(object):

    collection_name = 'scrapy_items'

    def __init__(self, mongo_uri, mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URI'),
            mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')
        )

    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]

    def close_spider(self, spider):
        self.client.close()

    def process_item(self, item, spider):
        self.db[self.collection_name].insert(dict(item))
        return item

简单粗暴，利用pipeline的类方法from_crawler