scrape_playwright.py

from playwright.sync_api import sync_playwright
import json

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page(viewport={"width": 1920, "height": 1080})

    base_url = "https://quotes.toscrape.com/js/page/{}/"
    all_quotes = []

    for page_num in range(1, 11):
        url = base_url.format(page_num)
        page.goto(url)
        page.locator(".quote").first.wait_for()

        quotes = page.locator(".quote").all()

        for quote in quotes:
            text = quote.locator(".text").text_content().strip()
            text = text.strip("\u201c\u201d")

            author = quote.locator(".author").text_content().strip()

            tags = [tag.text_content() for tag in quote.locator(".tag").all()]

            all_quotes.append({
                "text": text,
                "author": author,
                "tags": tags
            })

        print(f"Page {page_num}: scraped {len(quotes)} quotes")

    browser.close()

with open("quotes_playwright.json", "w") as f:
    json.dump(all_quotes, f, indent=2)

print(f"\nSaved {len(all_quotes)} quotes to quotes_playwright.json")

print("\nFirst 3 quotes:")
for i, q in enumerate(all_quotes[:3], 1):
    print(f'{i}. "{q["text"][:60]}..."')
    print(f'   Author: {q["author"]} | Tags: {", ".join(q["tags"])}')

print(f"\nLast 3 quotes (#{len(all_quotes)-2} - #{len(all_quotes)}):")
for i, q in enumerate(all_quotes[-3:], len(all_quotes) - 2):
    print(f'{i}. "{q["text"][:60]}..."')
    print(f'   Author: {q["author"]} | Tags: {", ".join(q["tags"])}')