Python爬虫之Scrapy框架系列（12）——实战ZH小说的爬取来深入学习CrawlSpider

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule

class ZhihuUserSpider(CrawlSpider):
    name = 'zh_user'
    allowed_domains = ['www.zhihu.com']
    start_urls = ['https://www.zhihu.com/people/excited-vczh']

    rules = (
        Rule(LinkExtractor(allow=r'/people/[^\s]+'), callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        # 这里提供了一个简单的例子来说明如何解析用户主页
        # 实际应用中，你可能需要解析更多的信息，比如关注者数量、回答数量等
        name = response.css('h1.zm-edit-header-content::text').extract_first()
        follower_num = response.css('a[class="zm-edit-follower-num"]::text').extract_first()
        print(f"用户名: {name}, 关注者数量: {follower_num}")