供以後寫代碼參考:
一、同步執行
import pymysql
class CollectDataPipeline(object):
def open_spider(self, spider):
print('open' * 20)
self.conn = pymysql.connect(host="127.0.0.1", user="root", password="****", database="collect_data",
charset="utf8")
self.db_cur = self.conn.cursor()
def close_spider(self, spider):
self.conn.close()
def process_item(self, item, spider):
val = (item['title'],
item['contents'],
item['time'])
# 先刪除數據
sql = '''delete from data where length(time)>0;'''
self.db_cur.execute(sql)
self.conn.commit()
# 插入新數據
sql = '''INSERT INTO data(title,contents,time) VALUES(%s,%s,%s);'''
self.db_cur.execute(sql, val)
self.conn.commit()
return item
二、異步執行
import pymysql
from twisted.enterprise import adbapi
# 異步更新操作
class LvyouPipeline(object):
def __init__(self, dbpool):
self.dbpool = dbpool
@classmethod
def from_settings(cls, settings): # 函數名固定,會被scrapy調用,直接可用settings的值
"""
數據庫建立連接
:param settings: 配置參數
:return: 實例化參數
"""
adbparams = dict(
host=settings['MYSQL_HOST'],
db=settings['MYSQL_DBNAME'],
user=settings['MYSQL_USER'],
password=settings['MYSQL_PASSWORD'],
charset='utf8',
cursorclass=pymysql.cursors.DictCursor # 指定cursor類型
)
# 連接數據池ConnectionPool,使用pymysql或者Mysqldb連接
dbpool = adbapi.ConnectionPool('pymysql', **adbparams)
# 返回實例化參數
return cls(dbpool)
def process_item(self, item, spider):
"""
使用twisted將MySQL插入變成異步執行。通過連接池執行具體的sql操作,返回一個對象
"""
query = self.dbpool.runInteraction(self.do_insert, item) # 指定操作方法和操作數據
# 添加異常處理
query.addCallback(self.handle_error) # 處理異常
#其他代碼都一樣,SQL語句不一樣即可,可複用。
def do_insert(self, cursor, item):
val=(item['Name'], item['Address'], item['Grade'], item['Score'],item['Price'])
# 對數據庫進行插入操作,並不需要commit,twisted會自動commit
insert_sql = """
insert into daname(name1, address, grade, score, price) VALUES (%s,%s,%s,%s,%s)
"""
self.cursor.execute(insert_sql, val)
def handle_error(self, failure):
if failure:
# 打印錯誤信息
print(failure)