モダンなウェブサイトから何千ものデータを数行のPythonコードでスクレイピングできるフレームワークです。

pip install scrapling

python -c "from scrapling.fetchers import Fetcher; page = Fetcher.get('https://quotes.toscrape.com/'); print(page.css('.quote .text::text').getall()[:2])"

cat > scrape_example.py << 'EOF'
from scrapling.fetchers import FetcherSession

with FetcherSession(impersonate='chrome') as session:
    page = session.get('https://quotes.toscrape.com/', stealthy_headers=True)
    quotes = page.css('.quote .text::text').getall()
    print(f'取得した引用句: {len(quotes)}件')
EOF
python scrape_example.py

cat > spider_example.py << 'EOF'
from scrapling.spiders import Spider, Response

class QuotesSpider(Spider):
    name = "quotes"
    start_urls = ["https://quotes.toscrape.com/"]
    concurrent_requests = 10
    
    async def parse(self, response: Response):
        for quote in response.css('.quote'):
            yield {
                "text": quote.css('.text::text').get(),
                "author": quote.css('.author::text').get(),
            }

result = QuotesSpider().start()
print(f'取得件数: {len(result.items)}')
EOF
python spider_example.py

cat > stealth_example.py << 'EOF'
from scrapling.fetchers import StealthyFetcher

page = StealthyFetcher.fetch('https://nopecha.com/demo/cloudflare')
data = page.css('#padded_content a').getall()
print(f'取得: {len(data)}件')
EOF
python stealth_example.py

python spider_example.py  # Ctrl+Cで中断、同じコマンドで再開