scrapy基礎知識之將item 通過pipeline保存數據到mysql mongoDB：

pipelines.py

class xxPipeline(object):

      def process_item(self, item, spider):

            con=pymysql.connect(host='localhost,user='',passwd='',db='',charset='utf8')

            cur=con.cursor()

            sql=("insert into 表名(字段)”"values(%s)")

            lis=(item['字段'])

            cur.execute(sql,lis)

            con.commit()

            cur.close()

            con.close()

            return item

在settings.py中配置

ITEM_PIPELINES = {

          ’MySpider.pipelines.xxPipeline': 300,

}

需要在mysql中創建數據庫以及數據表字段    

pipelines.py

import pymongo

class MyspiderPipeline(object): def __init__(self):  # pymongo.MongoClient(host, port) 創建MongoDB鏈接 client = pymongo.MongoClient(host="localhost",port=27017) # 指向指定的數據庫 db_name = client["dbname"]
 table_name=db_name["tablename"] # 獲取數據庫里存放數據的表名 self.post = table_name def process_item(self, item, spider): data = dict(item) # 向指定的表里添加數據 self.post.insert(data) return item

settings.py配置

DEFAULT_REQUEST_HEADERS = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:53.0) Gecko/20100101 Firefox/53.0'}