scrapy pipeline中mysql和mongo数据库入库

 mysql数据库

在setting.py文件中

# Mysql Settings
MYSQL_HOST = 'localhost'
MYSQL_DATABASE = 'images360'
MYSQL_PORT = 3306

pipeline.py中

class MysqlPipeline():
    def __init__(self, host, database, user, password, port):
        self.host = host
        self.database = database
        self.port = port

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            host=crawler.settings.get('MYSQL_HOST'),
            database=crawler.settings.get('MYSQL_DATABASE'),
            user=crawler.settings.get('MYSQL_USER'),
            password=crawler.settings.get('MYSQL_PASSWORD'),
            port=crawler.settings.get('MYSQL_PORT'),
        )

    def open_spider(self, spider):
        self.db = pymysql.connect(self.host,self.database, charset='utf8', port=self.port)
        self.cursor = self.db.cursor()

    def process_item(self, item, spider):
        data = dict(item)
        keys = ', '.join(data.keys())
        values = ', '.join(['%s'] * len(data))
        sql = 'insert into %s (%s) values (%s)' % (item.table, keys, values)
        self.cursor.execute(sql, tuple(data.values()))
        self.db.commit()
        return item

    def close_spider(self, spider):
        self.db.close()

mongo数据库

在setting.py文件中

MONGO_URL = 'localhost'
MONGO_DB = 'images360'

pipeline.py中

class MongoPipeline(object):
    def __init__(self, mongo_url, mongo_db):
        self.mongo_url = mongo_url
        self.mong_db = mongo_db

    @classmethod
    def from_crawler(cls, crawler):
        # 通过crawler对象拿到Scrapy的所有核心组件(如全局配置信息)并创建一个Pipeline实例
        return cls(
            mongo_url=crawler.settings.get('MONGO_URL'),
            mongo_db=crawler.settings.get('MONGO_DB')
        )

    def open_spider(self, spider):
        # 创建数据库连接对象
        self.client = pymongo.MongoClient(self.mongo_url)
        # 指定数据库
        self.db = self.client[self.mong_db]

    def process_item(self, item, spider):
        # 将数据插入到指定的表格
        self.db[item.collection].insert(dict(item))
        return item

    def close_spider(self, spider):
        # 关闭数据库连接
        self.client.close()

自带的imagepipeline下载

setting.py

IMAGES_STORE = './images'
ITEM_PIPELINES = {
    'images360.pipelines.MongoPipeline': 300,
    'images360.pipelines.MysqlPipeline': 301,
    'images360.pipelines.ImagePipeline': 302,
}

pipeline.py

class ImagePipeline(ImagesPipeline):
    def file_path(self, request, response=None, info=None):
        url = request.url
        file_name = url.split('/')[-1]
        return file_name

    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok, x in results if ok]
        if not image_paths:
            raise DropItem('Image Downloaded Failed')
        return item

    def get_media_requests(self, item, info):
        yield Request(item['url'])