Web scraping methodology

Patterns for reliable, ethical web scraping with fallback strategies and anti-bot handling.

Scraping cascade architecture

Implement multiple extraction strategies with automatic fallback:

from abc import ABC, abstractmethod
from typing import Optional
import requests
from bs4 import BeautifulSoup
import trafilatura

#for .py files
from playwright.sync_api import sync_playwright
from playwright_stealth import stealth_sync

#for .ipynb files
import asyncio
from playwright.async_api import async_playwright

class ScrapingResult:
    def __init__(self, content: str, title: str, method: str):
        self.content = content
        self.title = title
        self.method = method  # Track which method succeeded

class Scraper(ABC):
    @abstractmethod
    def fetch(self, url: str) -> Optional[ScrapingResult]: ...

class TrafilaturaСscraper(Scraper):
    """Fast, lightweight extraction for standard articles."""

    def fetch(self, url: str) -> Optional[ScrapingResult]:
        try:
            downloaded = trafilatura.fetch_url(url)
            if not downloaded:
                return None

            content = trafilatura.extract(
                downloaded,
                include_comments=False,
                include_tables=True,
                favor_recall=True
            )

            if not content or len(content) < 100:
                return None

            # Extract title separately
            soup = BeautifulSoup(downloaded, 'html.parser')
            title = soup.find('title')
            title_text = title.get_text() if title else ''

            return ScrapingResult(content, title_text, 'trafilatura')
        except Exception:
            return None

class RequestsScraper(Scraper):
    """HTTP requests with rotating user agents."""

    USER_AGENTS = [
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36',
        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36',
    ]

    def fetch(self, url: str) -> Optional[ScrapingResult]:
        import random

        headers = {
            'User-Agent': random.choice(self.USER_AGENTS),
            'Accept': 'text/html,application/xhtml+xml',
            'Accept-Language': 'en-US,en;q=0.9',
        }

        try:
            response = requests.get(url, headers=headers, timeout=30)
            response.raise_for_status()

            soup = BeautifulSoup(response.text, 'html.parser')

            # Remove script/style elements
            for element in soup(['script', 'style', 'nav', 'footer', 'aside']):
                element.decompose()

            # Find main content
            main = soup.find('main') or soup.find('article') or soup.find('body')
            content = main.get_text(separator='\n', strip=True) if main else ''

            title = soup.find('title')
            title_text = title.get_text() if title else ''

            if len(content) < 100:
                return None

            return ScrapingResult(content, title_text, 'requests')
        except Exception:
            return None

class PlaywrightScraper(Scraper):
    """Heavy JavaScript rendering with stealth mode for anti-bot bypass."""

    def fetch(self, url: str) -> Optional[ScrapingResult]:
        try:
            with sync_playwright() as p:
                browser = p.chromium.launch(headless=True)
                context = browser.new_context(
                    viewport={'width': 1920, 'height': 1080},
                    user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
                )
                page = context.new_page()

                # Apply stealth to avoid detection
                stealth_sync(page)

                page.goto(url, wait_until='networkidle', timeout=60000)

                # Wait for content to load
                page.wait_for_timeout(2000)

                # Extract content
                content = page.evaluate('''() => {
                    const article = document.querySelector('article, main, .content, #content');
                    return article ? article.innerText : document.body.innerText;
                }''')

                title = page.title()

                browser.close()

                if len(content) < 100:
                    return None

                return ScrapingResult(content, title, 'playwright')
        except Exception:
            return None

class PlaywrightScraperAsync:
    """Async Playwright scraper for Jupyter notebooks (.ipynb files).
    
how to use web-scraping
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use web-scraping on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add web-scraping
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/jamditis/claude-skills-journalism --skill web-scrapingcopy
The skills CLI fetches web-scraping from GitHub repository jamditis/claude-skills-journalism and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/web-scraping
Reload or restart Cursor to activate web-scraping. Access the skill through slash commands (e.g., /web-scraping) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?