Python Scrapy连接MySQL

1.在settings.py文件下定义数据库信息字段

mysql_host = '127.0.0.1'
mysql_user = 'root'
mysql_db = 'pad_woll'
mysql_db_charset ='utf8'
mysql_password = '123456'

2.在pipelines.py文件下定义MySQL连接通道

from pad_wool_crawl import settings // pad_wool_crawl：项目名称

class MySQLPipeline(object):
    def __init__(self):
        self.mysql_host = settings.mysql_host
        self.mysql_user = settings.mysql_user
        self.mysql_password = settings.mysql_password
        self.mysql_db = settings.mysql_db
        self.mysql_db_charset = settings.mysql_db_charset
        self.connect()

    def connect(self):
        self.conn = pymysql.connect(host=self.mysql_host, user=self.mysql_user, password=self.mysql_password, db=self.mysql_db, charset=self.mysql_db_charset)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):  // 插入数据
        sql = 'INSERT INTO line_report_table (title, time, content, images, type) VALUES ("%s", "%s", "%s", "%s", "%s")' % (item['title'], item['time'], item['content'], item['images'], item['type'])
        self.cursor.execute(sql)
        self.conn.commit()
        return item

    def close_spider(self, spider):
        self.conn.close()
        self.cursor.close()

3.启用MySQL连接通道（接收到数据，会自动进入定义的通道）

// 在settings.py文件中打开注释并添加定义的MySQL连接通道
ITEM_PIPELINES = {
   'pad_wool_crawl.pipelines.MySQLPipeline': 301,
}