学习中心
登录
已解决
猎云网爬取的数据数量不对?

老师,爬取数据的数量不对?同样是用了正则,杨老师在讲课的视频中就能爬取100多数据,而我的只爬取了2个数据,应该是一页中的内容,难道正则写错了吗?

# coding:utf-8
from scrapy import cmdline
cmdline.execute('scrapy crawl lyw'.split(' '))
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from ..items import LieyunItem


class LywSpider(CrawlSpider):
    name = "lyw"
    allowed_domains = ["lieyunpro.com"]
    start_urls = ["https://lieyunpro.com/latest/p1.html"]

    rules = (
        Rule(LinkExtractor(allow=r"/latest/p\d+.html/"),follow=True),
        Rule(LinkExtractor(allow=r"/archives/\d+"),callback='parse_item',follow=False),
             )

    def parse_item(self, response):
        title_lst = response.xpath('//h1[@class="lyw-article-title-inner"]/text()').getall()
        title = ''.join(title_lst).strip()  #标题
        publish_time = response.xpath('//h1[@class="lyw-article-title-inner"]/span/text()').get()  # 发布时间
        author_name = response.xpath('//a[contains(@class,"author-name")]/text()').get()  # 作者
        content = response.xpath('//div[@class="main-text"]//text()').getall()
        content = ''.join(content).strip()
        article_url = response.url

        # 创建Item的对象
        item = LieyunItem()
        item['title'] = title
        item['author_name'] = author_name
        item['publish_time'] = publish_time
        item['content'] = content
        item['article_url'] = article_url

        yield item

        # print(title)

d0e4e0a310d1f9b4393a2c03546df842.png

66f0ca7fdde0a7df0d3e3ffc659e8bc5.png

110 1
    1个回答
    写回答