一.区分
根据yield
迭代器生成的对象是request对象
还是item对象
二.item
1.配置tem对象
在items.py
文件中设置类
class MyscrapyItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
price = scrapy.Field()
prostatus = scrapy.Field()
2.在爬虫程序中导入该类写相应的函数
from myscrapy.items import MyscrapyItem
def get_info(self,response):
elements_list = response.css('.product')
for element in elements_list:
title = element.css('.productTitle a::attr(title)').extract_first() #这是css选择器
price = element.css('.productPrice em::attr(title)').extract_first()
prostatus = element.css('.productStatus em::text').extract_first()
item = MyscrapyItem() #实例话一个item对象
item['title'] = title #填写配置的参数
item['price'] = price
item['prostatus'] = prostatus
yield item
三.再获得item参数后scrapy会自动执行pipelines.py文件中内容
1.settings文件进行注册
ITEM_PIPELINES = {
'myscrapy.pipelines.MyscrapyPipeline': 300, #小的优先级高
# 'myscrapy.pipelines.MyscrapyPipeline1': 500,
}
#和中间件一个道理
2.配置MyscrapyPipeline方法
#其中两个方法非常常用
#def open_spider(self): 运行这个函数开始执行,一般都是连接数据库用
#def close_spider(self): 运行完这个函数执行,一般都是关闭数据库用
#简单拿MongoDB举例
from pymongo import MongoClient
class MyscrapyPipeline(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
#执行__init__之前执行
@classmethod
def from_crawler(cls,crawler):
HOST = crawler.settings.get('HOST') #crawler.settings可以直接获得setting文件中的所有名称
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):
self.client = MongoClient(host=self.HOST,port=self.PORT,username=self.USER,password=self.PWD)
print('连接数据库成功')
def close_spider(self,spider):
self.client.close()
print('关闭数据库')
def process_item(self, item, spider):
self.client[self.DB][self.TABLE].insert_one(dict(item))
return item