scraper.py

# scraper.py

import asyncio
from playwright.async_api import async_playwright
from bs4 import BeautifulSoup
import requests
import time

class Scraper:
    @staticmethod
    async def power_scrapper_2(url):
        async with async_playwright() as p:
            #browser = await p.chromium.launch(headless=True)
            browser = await p.webkit.launch(headless=True)  # Switch to WebKit
            # Create a new browser context with a realistic user-agent
            context = await browser.new_context(
                user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
            )
    
            # Set additional headers to force HTTP/1.1 and avoid detection
            await context.set_extra_http_headers({
                "Accept-Language": "en-US,en;q=0.9",
                "Upgrade-Insecure-Requests": "1",
                "Connection": "keep-alive"  # Force HTTP/1.1 instead of HTTP/2
            })
            
            # Open a new page
            page = await context.new_page()
    
            # Route to block images, videos, and CSS to speed up page load
            await page.route("**/*", lambda route: route.abort() if route.request.resource_type in ["image", "media", "stylesheet", "font", "xhr"] else route.continue_())
    
            # Navigate to the page with an extended timeout and alternate loading strategy
            await page.goto(url, wait_until='domcontentloaded', timeout=60000)
            # Wait for a specific element (like the title or an H1 header) to ensure the page is loaded
    
            # Get the title
            title = await page.title()
    
            # Get all links
            page_url = await page.evaluate("""() => {
                return Array.from(document.querySelectorAll('a')).map(a => a.href);
            }""")
    
            # Get page content (text from paragraphs and headers)
            page_content = await page.evaluate("""() => {
                let elements = Array.from(document.querySelectorAll('body *'));
                return elements
                    .filter(element => element.tagName.match(/^(P|H1|H2|H3|H4|H5|H6|LI|DIV|SPAN)$/i) && element.innerText.trim().length > 0)
                    .map(element => element.innerText.trim())
                    .join('\\n');
            }""")

            
            await browser.close()
            return title,page_url, page_content
    
    @staticmethod
    async def power_scrapper(url):
        async with async_playwright() as p:
            browser = await p.chromium.launch(headless=True)
            page = await browser.new_page()

            # Block unnecessary resources to speed up loading
            await page.route("**/*", lambda route: route.continue_() if route.request.resource_type in ["document", "script"] else route.abort())

            # Open the target website
            await page.goto(url, wait_until='domcontentloaded')

            # Wait for a short time to ensure dynamic content is loaded
            await page.wait_for_timeout(1000)

            # Extract all links
            links = await page.query_selector_all('a')
            page_url = []
            page_content = []
            for link in links:
                href = await link.get_attribute('href')
                page_url.append(href)

            # Extract all text content
            elements = await page.query_selector_all('body *')
        
            for element in elements:
                text_content = await element.text_content()
                if text_content and text_content.strip():
                    page_content.append(text_content.strip())

            await browser.close()
            return page_url, page_content

    @staticmethod
    def get_links(soup):
        links = []
        for link in soup.find_all('a'):
            href = link.get('href')
            links.append(href)
        return links

    @staticmethod
    def get_text_content(soup):
        text_elements = []
        for tag in ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'span']:
            elements = soup.find_all(tag)
            for element in elements:
                text_elements.append(element.get_text())
        return text_elements

    @staticmethod
    def get_title(soup):
        title = soup.find('title').get_text()
        return title

    @staticmethod
    async def scrape(url):
        try:
            headers = {'User-Agent': 'Mozilla/5.0'}
            response = requests.get(url,timeout=3)
            soup = BeautifulSoup(response.content, 'html.parser')
    
            title = Scraper.get_title(soup)
            links = Scraper.get_links(soup)
            text_content = Scraper.get_text_content(soup)
    
            if not links:
                print("Running alternative scrapper")
                links, text_content = await Scraper.power_scrapper_2(url)
    
            return {"title": title, "URL": links, "Content": text_content}
        except:
            title,links, text_content = await Scraper.power_scrapper_2(url)
            return {"title": title, "URL": links, "Content": text_content}