class MysqlTwistedPipeline(object):
# 异步执行
def __init__(self, dbpool):
self.dbpool = dbpool
@classmethod
def from_settings(cls, settings):
dbparms = dict(
host=settings["MYSQL_HOST"],
db=settings["MYSQL_DBNAME"],
user=settings["MYSQL_USER"],
passwd=settings["MYSQL_PASSWORD"],
charset='utf8',
cursorclass=MySQLdb.cursors.DictCursor,
use_unicode=True,
)
dbpool = adbapi.ConnectionPool("MySQLdb", **dbparms)
return cls(dbpool)
def process_item(self, item, spider):
# 使用twisted将mysql插入变成异步执行
query = self.dbpool.runInteraction(self.do_insert, item)
query.addErrback(self.handle_error) # 处理异常
def handle_error(self, failure):
# 处理异步插入异常
print(failure)
def do_insert(self, cursor, item):
# 执行具体的插入
insert_sql = """
insert into jobbole_article(title, url, url_object_id, create_date, fav_nums)
VALUES(%s, %s, %s, %s, %s)
"""
cursor.execute(insert_sql, (item["title"], item["url"], item["url_object_id"], item["create_date"], item["fav_nums"]))