第九篇数据表设计和保存item到json文件

#存储item到json文件
class JsonWithEncodingPipeline(object):
    def __init__(self):
        #使用codecs模块来打开文件，可以帮我们解决很多编码问题,下面先初始化打开一个json文件
        import codecs
        self.file = codecs.open('article.json','w',encoding='utf-8')
    #接着创建process_item方法执行item的具体的动作
    def process_item(self, item, spider):
        import json
        #注意ensure_ascii入参设置成False，否则在存储非英文的字符会报错
        lines = json.dumps(dict(item),ensure_ascii=False) + "\n"
        self.file.write(lines)
        #注意最后需要返回item，因为可能后面的Pipeline会调用它
        return item
    #最后关闭文件
    def spider_close(self,spider):
        self.file.close()

from scrapy.exporters import JsonItemExporter

class JsonExporterPipeline(object):
    #调用scrapy提供的json export导出json文件
    def __init__(self):
        #打开一个json文件
        self.file = open('articleexport.json','wb')
        #创建一个exporter实例,入参分别是下面三个，类似前面的自定义导出json
        self.exporter = JsonItemExporter(self.file,encoding='utf-8',ensure_ascii=False)
        #开始导出
        self.exporter.start_exporting()
    def close_spider(self,spider):
        #完成导出
        self.exporter.finish_exporting()
        #关闭文件
        self.file.close()
    #最后也需要调用process_item返回item
    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item

import pymysql
class MysqlPipeline(object):
    def __init__(self):
        """
        初始化，建立mysql连接conn，并创建游标cursor
        """
        self.conn = pymysql.connect(
            host='localhost',
            database='spider',
            user='root',
            passwd='123456',
            charset='utf8',
            use_unicode=True
        )
        self.cursor = self.conn.cursor()
    def process_item(self,item,spider):
        #要执行的sql语句
        insert_sql = """
            insert into jobbole_article(title,create_date,url,url_object_id,
            front_image_url,front_image_path,praise_num,comment_num,fav_num,tags,content)
            VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
        """
        #使用游标的execute方法执行sql
        self.cursor.execute(insert_sql,(item["title"],item['create_date'],
                                        item['url'],item['url_object_id'],
                                        item['front_image_url'],item['front_image_path'],
                                        item['praise_num'],item['comment_num'],item['fav_num'],
                                        item['tags'],item['content']))
        #commit提交才能生效
        self.conn.commit()
        return item

MYSQL_HOST = "localhost"
MYSQL_DBNAME = 'spider'
MYSQL_USER = "root"
MYSQL_PASSWORD = "123456"

from twisted.enterprise import adbapi

class MysqlTwistedPipeline(object):
    #下面这两个函数完成了在启动spider的时候，就把dbpool传入进来了
    def __init__(self,dbpool):
        self.dbpool = dbpool

    #通过下面这种方式，可以很方便的拿到setting配置信息
    @classmethod
    def from_settings(cls,setting):
        dbparms = dict(
        host = setting['MYSQL_HOST'],
        db = setting['MYSQL_DBNAME'],
        user = setting['MYSQL_USER'],
        password = setting['MYSQL_PASSWORD'],
        charset = 'utf8',
        #cursorclass = pymysql.cursors.DictCursor,

        use_unicode = True,

        )

        #创建连接池，
        dbpool = adbapi.ConnectionPool("pymysql",**dbparms)

        return cls(dbpool)

    # 使用twisted将mysql插入变成异步执行
    def process_item(self, item, spider):
        # 指定操作方法和操作的数据
        query = self.dbpool.runInteraction(self.do_insert,item)
        #处理可能存在的异常，hangdle_error是自定义的方法
        query.addErrback(self.handle_error,item,spider)

    def handle_error(self,failure,item,spider):
        print(failure)

    def do_insert(self,cursor,item):
        #执行具体的插入
        # 根据不同的item 构建不同的sql语句并插入到mysql中
        insert_sql = """
                       insert into jobbole_article(title,create_date,url,url_object_id,
                       front_image_url,front_image_path,praise_num,comment_num,fav_num,tags,content)
                       VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
                   """
        # 使用游标的execute方法执行sql
        cursor.execute(insert_sql, (item["title"], item['create_date'],
                                         item['url'], item['url_object_id'],
                                         item['front_image_url'], item['front_image_path'],
                                         item['praise_num'], item['comment_num'], item['fav_num'],
                                         item['tags'], item['content']))

import pymysql
import pymysql.cursors

(one_project) laoni@ubuntu:~$ sudo apt-get install libmysqlclient-dev

(one_project) laoni@ubuntu:~$ sudo yum install python-devel mysql-devel