Scrapy 爬虫中的数据解析和处理：如何处理 JSON、XML 和 YAML 等数据格式？

import scrapy
import json

class JsonSpider(scrapy.Spider):
    name = "json_spider"
    start_urls = [
        "http://example.com/sample.json"
    ]

    def parse(self, response):
        data = json.loads(response.body)
        for item in data:
            yield {
                'name': item['name'],
                'age': item['age'],
                'website': item['website']
            }

import scrapy
from scrapy.selector import Selector

class XmlSpider(scrapy.Spider):
    name = "xml_spider"
    start_urls = [
        "http://example.com/sample.xml"
    ]

    def parse(self, response):
        xml = Selector(response)
        for node in xml.xpath('//movie'):
            yield {
                'title': node.xpath('title/text()').extract_first(),
                'description': node.xpath('description/text()').extract_first(),
                'director': node.xpath('director/text()').extract_first()
            }

import scrapy
import yaml

class YamlSpider(scrapy.Spider):
    name = "yaml_spider"
    start_urls = [
        "http://example.com/sample.yml"
    ]

    def parse(self, response):
        data = yaml.safe_load(response.body)
        for item in data:
            yield {
                'name': item['name'],
                'age': item['age'],
                'website': item['website']
            }