如何抓取 Weebly 网站：从数百万个站点中提取数据

import asyncio; from playwright.async_api import async_playwright; async def run(): async with async_playwright() as p: browser = await p.chromium.launch(); page = await browser.new_page(); await page.goto('https://example.weebly.com/store'); await page.wait_for_selector('.wsite-com-product-title'); products = await page.query_selector_all('.wsite-com-product-title'); for product in products: print(await product.inner_text()); await browser.close(); asyncio.run(run())

import scrapy; class WeeblySpider(scrapy.Spider): name = 'weebly'; start_urls = ['https://example.weebly.com/blog']; def parse(self, response): for post in response.css('.blog-post'): yield {'title': post.css('.blog-title::text').get().strip(), 'date': post.css('.blog-date::text').get()}; next_page = response.css('a.next-page::attr(href)').get(); if next_page: yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer'); (async () => { const browser = await puppeteer.launch(); const page = await browser.newPage(); await page.goto('https://example.weebly.com'); const titles = await page.evaluate(() => Array.from(document.querySelectorAll('.wsite-content-title')).map(el => el.innerText)); console.log(titles); await browser.close(); })();