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)
            page = await browser.new_page()
    
            # Route to block images, videos, and CSS
            await page.route("**/*", lambda route: route.abort() if route.request.resource_type in ["image", "media", "stylesheet", "font", "xhr"] else route.continue_())
    
            await page.goto(url)
    
            # 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.map(element => element.innerText).join('\\n');
            }""")

            
            await browser.close()
            return 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):
        headers = {'User-Agent': 'Mozilla/5.0'}
        response = requests.get(url)
        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}