Scrapy：如何构建一个从多个 URL 收集信息的项目？

pip install scrapy

scrapy startproject project_name

import scrapy

class ProjectNameItem(scrapy.Item):
    title = scrapy.Field()
    link = scrapy.Field()
    description = scrapy.Field()

import scrapy
from project_name.items import ProjectNameItem

class MySpider(scrapy.Spider):
    name = 'my_spider'
    start_urls = [
        'https://example.com/page1',
        'https://example.com/page2',
        # 添加更多 URL 地址
    ]

    def parse(self, response):
        for item in response.css('.item'):
            project_name_item = ProjectNameItem()
            project_name_item['title'] = item.css('.title::text').get()
            project_name_item['link'] = item.css('.link::attr(href)').get()
            project_name_item['description'] = item.css('.description::text').get()
            yield project_name_item

scrapy crawl my_spider

scrapy crawl my_spider -o output.json