Indiegogoをスクレイピングする方法：クラウドファンディング・データ抽出の究極ガイド

from playwright.sync_api import sync_playwright

def scrape_indiegogo_dynamic(url):
    with sync_playwright() as p:
        # クリーンなコンテキストでブラウザを起動
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        
        # Reactがコンポーネントをハイドレートするのを待つために移動
        page.goto(url, wait_until='networkidle')
        
        # 資金額の特定のセレクターを待機
        page.wait_for_selector('.i-project-raise-amount')
        
        results = {
            "title": page.inner_text('h1'),
            "funding": page.inner_text('.i-project-raise-amount'),
            "backers": page.inner_text('.i-project-raise-backers')
        }
        
        print(results)
        browser.close()

# 使用例:
# scrape_indiegogo_dynamic('https://www.indiegogo.com/projects/example-project')

import scrapy
from scrapy_playwright.page import PageMethod

class IndiegogoSpider(scrapy.Spider):
    name = 'indiegogo_spider'

    def start_requests(self):
        # 動的コンテンツを処理するために scrapy-playwright を使用
        yield scrapy.Request(
            'https://www.indiegogo.com/explore/all',
            meta={
                "playwright": True,
                "playwright_page_methods": [
                    PageMethod("wait_for_selector", ".discoverableCard-base"),
                ],
            }
        )

    def parse(self, response):
        for card in response.css('.discoverableCard-base'):
            yield {
                'name': card.css('.discoverableCard-title::text').get(),
                'raised': card.css('.discoverableCard-formattedAmount::text').get(),
                'url': response.urljoin(card.css('a::attr(href)').get())
            }

const puppeteer = require('puppeteer');

async function scrapeIndiegogo(url) {
    const browser = await puppeteer.launch({ headless: true });
    const page = await browser.newPage();
    
    // 基本的なボット検知を回避するためにカスタムユーザーエージェントを設定
    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0');

    await page.goto(url, { waitUntil: 'networkidle2' });

    const data = await page.evaluate(() => {
        return {
            projectTitle: document.querySelector('h1')?.innerText,
            amountRaised: document.querySelector('.i-project-raise-amount')?.innerText,
            percentFunded: document.querySelector('.i-project-raise-percent')?.innerText
        };
    });

    console.log(data);
    await browser.close();
}

// scrapeIndiegogo('https://www.indiegogo.com/projects/example-project');