Scrapy custom exporter

Question

I am defining an item exporter that pushes items to a message queue. Below is the code.

from scrapy.contrib.exporter import JsonLinesItemExporter
from scrapy.uti         


        

Answer 1

Tip: Good example to start from is Writing Items to MongoDb from official docs.

I've done a similar thing. I've created a pipeline that places each item into an S3-like service (I'm using Minio here, but you get the idea). It creates a new bucket for each spider and places each item into an object with a random name. Full source code can by found in my repo.

Starting with simple quotes spider from the tutorial:

import scrapy

class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = ['http://quotes.toscrape.com/page/1/',
                    'http://quotes.toscrape.com/page/1/']

    def parse(self, response):
        for quote in response.css('div.quote'):
            yield {
                    'text':quote.css('span.text::text').extract_first(),
                    'author':quote.css('span small::text').extract_first(),
                    'tags':quote.css('div.tags a.tag::text').extract()
                    }
        next_page = response.css('li.next a::attr(href)').extract_first()
        if next_page is not None:
            next_page = response.urljoin(next_page)
            yield scrapy.Request(next_page, callback=self.parse)

In settings.py:

ITEM_PIPELINES = {
    'scrapy_quotes.pipelines.ScrapyQuotesPipeline': 300,
}

In scrapy_quotes/pipelines.py create a pipeline and an item exporter:

import uuid
from StringIO import StringIO
from scrapy.contrib.exporter import BaseItemExporter
from scrapy.conf import settings
from scrapy import signals
from scrapy.xlib.pydispatch import dispatcher
from scrapy import log
from scrapy.utils.python import to_bytes
from scrapy.utils.serialize import ScrapyJSONEncoder

class S3ItemExporter(BaseItemExporter):
    def __init__(self, bucket, **kwargs):
        self._configure(kwargs)
        self.bucket = bucket
        kwargs.setdefault('ensure_ascii', not self.encoding)
        self.encoder = ScrapyJSONEncoder(**kwargs)

    def start_exporting(self):
        self.client = connect()
        create_bucket(self.client, self.bucket)

    def finish_exporting(self):
        log.msg("Done from S3 item exporter", level=log.DEBUG)

    def export_item(self, item):
        log.msg("S3 item exporter got item: %s" % item, level=log.DEBUG)
        itemdict = dict(self._get_serialized_fields(item))
        data = self.encoder.encode(itemdict)
        size = len(data) 
        object_data = StringIO(data)
        name = str(uuid.uuid4())
        put_object(self.client, self.bucket, name, object_data, size)  


class ScrapyQuotesPipeline(object):
    """Export scraped items, to different buckets,
    one per spider"""
    @classmethod
    def from_crawler(cls, crawler):
        pipeline = cls()
        crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
        crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
        return pipeline

    def spider_opened(self, spider):
        self.exporter = S3ItemExporter(spider.name)
        self.exporter.start_exporting()

    def spider_closed(self, spider):
        self.exporter.finish_exporting()

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

# S3 Related
from minio import Minio
import os
from minio.error import ResponseError
def connect():
    return Minio('192.168.1.111:9000',
            access_key='0M6PYKBBAVQVQGVWVZKQ',
            secret_key='H6vPxz0aHSMZPgagZ3G0lJ6CbhN8RlTtD78SPsL8',
            secure=False)

def create_bucket(client, name):
    client.make_bucket(name)

def put_object(client, bucket_name, object_name, object_data, size):
    client.put_object(bucket_name, object_name, object_data, size)