爬虫数据的存储

1，Json

class JsonWithEncodingPipeline(object):
    #自定义json文件的导出
    def __init__(self):
        self.file = codecs.open('article.json', 'w', encoding="utf-8")
    def process_item(self, item, spider):
        lines = json.dumps(dict(item), ensure_ascii=False) + "\n"
        self.file.write(lines)
        return item
    def spider_closed(self, spider):
        self.file.close()


class JsonExporterPipleline(object):
    #调用scrapy提供的json export导出json文件
    def __init__(self):
        self.file = open('articleexport.json', 'wb')
        self.exporter = JsonItemExporter(self.file, encoding="utf-8", ensure_ascii=False)
        self.exporter.start_exporting()

    def close_spider(self, spider):
        self.exporter.finish_exporting()
        self.file.close()

    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item

open_spider 当spider开启时，这个方法被调用

close_spider 当scrapy关闭时，这个方法会被调用。

最主要的是process_item这个方法执行了数据库的插入操作

2，MYSQL

 

from twisted.enterprise import adbapi  # 将MySQL操作异步化
import MySQLdb.cursors

 

class MysqlPipeline(object):
    #采用同步的机制写入mysql
    def __init__(self):
        self.conn = MySQLdb.connect('192.168.0.106', 'root', 'root', 'article_spider', charset="utf8", use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        insert_sql = """
            insert into jobbole_article(title, url, create_date, fav_nums)
            VALUES (%s, %s, %s, %s)
        """
        self.cursor.execute(insert_sql, (item["title"], item["url"], item["create_date"], item["fav_nums"]))
        self.conn.commit()


class MysqlTwistedPipline(object):
    def __init__(self, dbpool):
        self.dbpool = dbpool

    @classmethod
    def from_settings(cls, settings):  # 这个方法会将settings配置传递进来
        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, item, spider) #处理异常

    def handle_error(self, failure, item, spider):
        # 处理异步插入的异常
        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, params = item.get_insert_sql()
        print (insert_sql, params)
        cursor.execute(insert_sql, params)

使用MySQLTwistedPipline是因为爬取速度远超插入关系型数据库的速度，因此用它来实现异步插入数据库的操作，一般都是使用下面的这种