import scrapy

class NewsSpider(scrapy.Spider):
    name = 'news_spider'
    allowed_domains = ['example.com']
    start_urls = ['http://example.com/news']

    def parse(self, response):
        # 提取新闻详情页的链接
        for news_link in response.css('a.news-link::attr(href)').getall():
            yield response.follow(news_link, self.parse_news)

        # 寻找下一页的链接
        next_page = response.css('a.next-page::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

    def parse_news(self, response):
        # 提取新闻详情页的内容
        title = response.css('h1.news-title::text').get()
        content = response.css('div.news-content::text').getall()
        # 这里你可以继续提取其他字段，比如发布日期、作者等

        yield {
            'title': title,
            'content': content,
            # 其他字段
        }

爬虫技术仅供学习，请勿用于违法犯罪活动