当我试图将我的刮擦结果保存到mongodb时,我遇到了问题。在终端上没有显示错误,但数据没有保存到mongodb。
pipline.py
class MongoDBPipeline(object):
collection_name = 'lalaland'
def __init__(self, mongo_uri, mongo_db):
self.mongo_uri = mongo_uri
self.mongo_db = mongo_db
@classmethod
def from_crawler(cls, crawler):
return cls(
mongo_uri = crawler.settings.get('MONGO_URI'),
mongo_db = crawler.settings.get('MONGO_DATABASE', 'items')
)
def open_spider(self, spider):
self.client = MongoClient(self.mongo_uri)
self.db = self.client[self.mongo_db]
def close_spider(self, spider):
self.client.close()
def process_item(self, item, spider):
self.db[self.collection_name].insert(dict(item))
logging.debug("Added to mongo")
return item
settings.py
ITEM_PIPELINES = {
'lalaland.pipelines.MongoDBPipeline':300
}
MONGO_URI = 'mongodb://localhost:27017'
MONGODB_DATABASE = 'lala_db'
item.py
class InforItem(Item):
link = Field()
caption = Field()
spider.py
item = InfoItem()
item['link'] = response.url
item['body'] = ' '.join(response.xpath("//li[@class='_cak6a'][1]/h1/span//text()").extract())
yield item