Add files via upload

Author: fabiocavalcantti

email_filter.py

@@ -0,0 +1,2 @@
+def filter_emails(emails, domain):
+    return {email for email in emails if email.endswith(domain)}

email_saver.py

@@ -0,0 +1,8 @@
+import csv
+
+def save_emails_to_csv(emails, filename):
+    with open(filename, mode='w', newline='') as file:
+        writer = csv.writer(file)
+        for email in emails:
+            writer.writerow([email])
+    print(f"E-mails salvos com sucesso em {filename}")

email_scraper.py

@@ -0,0 +1,36 @@
+import requests
+from bs4 import BeautifulSoup
+import re
+import time
+
+class EmailScraper:
+    def __init__(self, urls_file):
+        self.urls_file = urls_file
+        self.email_regex = re.compile(r'''
+            ([a-zA-Z0-9_.+]+
+            @
+            [a-zA-Z0-9_.+]+)
+            ''', re.VERBOSE)
+
+    def scrape_emails_from_url(self, url):
+        try:
+            headers = {'User-Agent': 'Mozilla/5.0'}
+            response = requests.get(url, headers=headers)
+            emails = set(self.email_regex.findall(response.text))
+            return emails
+        except requests.exceptions.RequestException as e:
+            print(f"Erro ao acessar {url}: {e}")
+            return set()
+
+    def run(self, output_file):
+        with open(self.urls_file, 'r') as urls, open(output_file, 'a') as email_file:
+            for i, url in enumerate(urls, 1):
+                url = url.strip()
+                emails = self.scrape_emails_from_url(url)
+                for email in emails:
+                    email_file.write(f"{email}\n")
+                print(f"{i}. Processed {url} with {len(emails)} emails found.")
+
+# Uso da classe
+# scraper = EmailScraper('urls.txt')
+# scraper.run('emails.txt')

main.py

@@ -0,0 +1,42 @@
+from email_scraper import EmailScraper
+from email_filter import filter_emails
+from email_saver import save_emails_to_csv
+
+def print_banner():
+    banner = """
+    ██████╗ ███████╗███████╗██████╗ ███╗   ██╗████████╗ █████╗ ██╗  ██╗███████╗
+    ██╔══██╗██╔════╝██╔════╝██╔══██╗████╗  ██║╚══██╔══╝██╔══██╗██║ ██╔╝██╔════╝
+    ██████╔╝█████╗  █████╗  ██████╔╝██╔██╗ ██║   ██║   ███████║█████╔╝ █████╗  
+    ██╔═══╝ ██╔══╝  ██╔══╝  ██╔══██╗██║╚██╗██║   ██║   ██╔══██║██╔═██╗ ██╔══╝  
+    ██║     ███████╗███████╗██║  ██║██║ ╚████║   ██║   ██║  ██║██║  ██╗███████╗
+    ╚═╝     ╚══════╝╚══════╝╚═╝  ╚═╝╚═╝  ╚═══╝   ╚═╝   ╚═╝  ╚═╝╚═╝  ╚═╝╚══════╝
+    """
+    print(f"\033[92m{banner}\033[0m")  # 92 é o código para a cor verde no terminal
+
+def main_menu():
+    print("1. Raspagem de e-mails brasileiros")
+    print("2. Raspagem de e-mails do Gmail")
+    print("3. Raspagem de e-mails em massa de arquivo de URLs")
+    choice = input("Escolha uma opção: ")
+    return choice
+
+def main():
+    print_banner()
+    choice = main_menu()
+    if choice == '3':
+        urls_file = input("Digite o caminho do arquivo com as URLs: ")
+        output_file = input("Digite o nome do arquivo de saída para os e-mails: ")
+        scraper = EmailScraper(urls_file)
+        scraper.run(output_file)
+    else:
+        url = input("Digite a URL para fazer o scraping de e-mails: ")
+        scraper = EmailScraper(url)
+        emails = scraper.scrape_emails_from_url(url)
+        if choice == '1':
+            filtered_emails = filter_emails(emails, '.br')
+        elif choice == '2':
+            filtered_emails = filter_emails(emails, 'gmail.com')
+        save_emails_to_csv(filtered_emails, f'emails_{choice}.csv')
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,2 @@
+requests
+beautifulsoup4