[ESP-ENG] Titulos y enlaces en goodoldgeek || Titles and links in goodoldgeek

in #siteslast year


Imagen diseñada con canva || Image designed with canva

import asyncio
import aiohttp
from selectolax.parser import HTMLParser

headers={'user-agent': 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_5 rv:3.0; sl-SI) AppleWebKit/534.49.1 (KHTML, like Gecko) Version/4.0.1 Safari/534.49.1'}

async def parsing_page():

async with aiohttp.ClientSession() as session:

    for idx in range(1,6): 
        
        async with session.get(f'https://www.goodoldgeek.com/blogs/page/{idx}/',headers=headers) as page:
            
            goodoldgeek=await page.text()
            goodoldgeek_html=HTMLParser(goodoldgeek)
             
            for get_hl in goodoldgeek_html.css('div.fusion-post-content.post-content > h2 > a'):
                
                h=get_hl.text(strip=True)
                l=get_hl.attributes['href']

                print(f'headlines: {h} links: {l}')

asyncio.run(parsing_page())