JavaScriptを実行するブラウザ自動化から軽量HTTPリクエストまで、あらゆるウェブスクレイピングシーンに対応する適応的Pythonフレームワーク

pip install Scrapling

python -c "from scrapling.fetchers import Fetcher; p = Fetcher.get('https://quotes.toscrape.com/'); print(p.css('.quote .text::text').get())"

python -c "from scrapling.fetchers import StealthyFetcher; p = StealthyFetcher.fetch('https://quotes.toscrape.com/'); print(p.css('.quote .text::text').get())"

python << 'EOF'
from scrapling.spiders import Spider, Response

class QuotesSpider(Spider):
    name = "quotes"
    start_urls = ["https://quotes.toscrape.com/"]
    
    async def parse(self, response: Response):
        for quote in response.css('.quote'):
            yield {"text": quote.css('.text::text').get()}

result = QuotesSpider().start()
print(f"取得件数: {len(result.items)}")
EOF