scrapy--將爬取得數據保存到數據庫中

首先要作的：

• 建庫 article 建表 article
• 在cmd中的工做環境中安裝mysql的驅動 mysqlclient
  pip install mysqlclient #若是是使用centos 須要 yum install python-devel mysql-devel

接下來保存數據庫兩種方法：

1. 同步操做：數據少能夠
2. 異步操做：大數據（scrapy爬取得速度快於數據庫插入速度，當數據量大時，就會出現阻塞，異步就能解決）

1.同步

修改數據，因爲咱們抓取的時間格式是str 須要轉換成date存入數據庫

import  datetime

try:
    create_date=datetime.datetime.strptime('create_date',"%Y/%m/%d").date()
except Exception as e:
    create_date =datetime.datetime.now().date()  #若是沒有就取當前時間
article_item['create_date'] =create_date

創建MysqlPipeline

import MySQLdb

class MysqlPipeline(object):
    def __init__(self):
        self.conn=MySQLdb.connect('localhost','root','root','article',charset='utf8',use_unicode=True)
        self.cursor=self.conn.cursor()

    def process_item(self, item, spider):
        insert_sql="""
            insert into article(title,url,create_date,url_object_id,front_image_url,front_image_path,
            praise,collect_nums,comment_nums,contents,tags)VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
        """
        self.cursor.execute(insert_sql,(item['title'],item['url'],item['create_date'],item['url_object_id'],
        item['front_image_url'],item['front_image_path'],item['praise'],item['collect_nums'],item['comment_nums'],item['contents'],item['tags'] ))
        self.conn.commit()

PIPELINE添加配置

ITEM_PIPELINES = {
  'spider_first.pipelines.ArticleImagePipeline': 1,
  'spider_first.pipelines.MysqlPipeline':2,
}

2.異步

settings.py
MYSQL_HOST='localhost'
MYSQL_DBNAME='article'
MYSQL_USER='root'
MYSQL_PASSWORD='root'

建立異步pipeline

import MySQLdb
import MySQLdb.cursors
from twisted.enterprise import adbapi

class MysqlTwistPipeline(object):

    @classmethod
    def from_settings(cls,settings):#名稱固定 會被scrapy調用 直接可用setting的值
        adbparams=dict(
            host=settings['MYSQL_HOST'],
            db = settings['MYSQL_DBNAME'],
            user = settings['MYSQL_USER'],
            password = settings['MYSQL_PASSWORD'],
            charset='utf8',
            cursorclass=MySQLdb.cursors.DictCursor,
            use_unicode=True,
            )
        #這是連接數據庫的另外一種方法，在settings中寫入參數
        dbpool=adbapi.ConnectionPool('MySQLdb',**adbparams)
        return cls(dbpool)

    def __init__(self,dbpool):
        self.dbpool=dbpool

    def process_item(self, item, spider):
        #使用twiest將mysql插入變成異步
        query=self.dbpool.runInteraction(self.do_insert,item)
        #由於異步 可能有些錯誤不能及時爆出
        query.addErrback(self.handle_error)

    #處理異步的異常
    def handle_error(self,failure):
        print('failure')

    def do_insert(self,cursor,item):
        insert_sql = """
                    insert into article(title,url,create_date,url_object_id,front_image_url,front_image_path,
                    praise,collect_nums,comment_nums,contents,tags)VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
                """
        cursor.execute(insert_sql, (item['title'], item['url'], item['create_date'], item['url_object_id'],item['front_image_url'], item['front_image_path'], item['praise'],item['collect_nums'], item['comment_nums'], item['contents'], item['tags']))

最後一樣添加配置便可