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

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 index in range(1,6): 
        
        async with session.get(f'https://blog.bigdataboutique.com/page/{index}',headers=headers) as page:
            
            bigdataboutique=await page.text()
            bigdataboutique_html=HTMLParser(bigdataboutique)
             
            for hl in bigdataboutique_html.css('div.post-box__content-header > a'):
                h=hl.text(strip=True)
                l=hl.attributes['href']

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

asyncio.run(parsing_page())