Realiza web scrapping para coletar todos os e-mails de determinado conjunto de páginas web

mail_web_scrapping.py

#!pip install requests
#!pip install beautifulsoup4

# https://stackoverflow.com/questions/63533115/extract-valid-email-address-using-regular-expression-and-beautifulsoup

import requests
import re
from bs4 import BeautifulSoup

email = re.compile(r'([a-zA-Z0-9._-]+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9_-]+){0,}')
email_list = set()

for i in range(1,7):
  url = f"http://www.eeffto.ufmg.br/eeffto/graduacao/educacao_fasica_graduacao/corpo_docente/lista/{i}"
  response = requests.get(url)

  soup = BeautifulSoup(response.content, "html.parser")

  email_list = email_list.union(set(email.findall(soup.get_text())))

#print(email_list)

for mail in email_list:
  print(f"{mail};")