与Scrapy集成

以下是Crawlab跟Scrapy集成的例子，利用了Crawlab传过来的task_id和collection_name。

import os
from pymongo import MongoClient

MONGO_HOST = '192.168.99.100'
MONGO_PORT = 27017
MONGO_DB = 'crawlab_test'

# scrapy example in the pipeline
class JuejinPipeline(object):
    mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT)
    db = mongo[MONGO_DB]
    col_name = os.environ.get('CRAWLAB_COLLECTION')
    if not col_name:
        col_name = 'test'
    col = db[col_name]

    def process_item(self, item, spider):
        item['task_id'] = os.environ.get('CRAWLAB_TASK_ID')
        self.col.save(item)
        return item