腾讯云怎么装爬虫

npm install -g playwright

playwright install

const { chromium } = require('playwright');

(async () => {
  for (let i = 1; i <= 5; i++) {
    const browser = await chromium.launch();
    const page = await browser.newPage();
    await page.goto(`https://www.example.com/page/${i}`);
    const content = await page.content();
    console.log(content);
    await browser.close();
  }
})();

pip install scrapy

scrapy startproject myproject

import scrapy

class MySpider(scrapy.Spider):
    name = 'myspider'
    start_urls = ['http://www.example.com']

    def parse(self, response):
        self.log('Visited %s' % response.url)
        for quote in response.css('div.quote'):
            item = {
                'author_name': quote.css('span.text::text').get(),
                'author_url': quote.xpath('span/small/a/@href').get(),
            }
            yield item

scrapy crawl myspider