periksa data / data breach checker with python credit : https://periksadata.com/

main.py

import requests, time
from bs4 import BeautifulSoup

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/119.0',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
    'Accept-Language': 'id,en-US;q=0.7,en;q=0.3',
    'Content-Type': 'application/x-www-form-urlencoded',
    'Origin': 'https://periksadata.com',
    'Alt-Used': 'periksadata.com',
    'Connection': 'keep-alive',
    'Referer': 'https://periksadata.com/',
    'Upgrade-Insecure-Requests': '1',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'same-origin',
    'Sec-Fetch-User': '?1',
}

e_mail = str(input("Masukan email : "))

data = 'email='+e_mail

while True:
    #response = requests.post('https://periksadata.com/', cookies=cookies, headers=headers, data=data)
    response = requests.post('https://periksadata.com/', headers=headers, data=data)

    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        paragraf = soup.find_all('div', class_='col-md-6')
        
        if any(paragraf):
            for p in paragraf:
                title_element = p.find('h5')
                if title_element is not None:
                    title = title_element.text.strip()
                    paragraphs = p.find_all('p')
                    print(title)
                    #print("https://periksadata.com" + p.find('a')['href'])
                    link2 = "https://periksadata.com" + p.find('a')['href']
                    print(link2)
                    response2 = requests.get(link2, headers=headers)
                    soup2 = BeautifulSoup(response2.text, 'html.parser')
                    # paragraphs2 = soup2.find('div', class_='col-md-10 col-lg-8')

                    #print(soup2.find('p', class_='lead'))

                    lead_paragraph = soup2.find('p', class_='lead')
                    if lead_paragraph is not None:
                        print("Deskripsi : "+lead_paragraph.text.strip()[:-45])
                    else:
                        print('No lead paragraph found')
                    # print(paragraphs2)
                    # print(soup2.find('span', class_='label label--inline text-center rounded').text.strip())
                    # data_leaked = soup2.find('span').text.strip()
                    # for leak in data_leaked:
                    #     print(leak)

                    data_leaked = soup2.find_all('span', class_='label label--inline text-center rounded')
                    # for leak in data_leaked:
                    #     print(leak.text.strip())

                    data_leaked_text = ' '.join(leak.text.strip() for leak in data_leaked)
                    # print(f'Data yang bocor: {data_leaked_text}')
                    for para in paragraphs:
                        parts = para.find_all('b')
                        if len(parts) >= 2:
                            label = parts[0].text.strip()
                            # value = parts[1].text.strip()
                            datas = parts[2].text.strip()
                            print(f'Tanggal Kejadian: {label}\nData yang bocor: {data_leaked_text}\nTotal keseluruhan data yang bocor: {datas}')
                    print()
            break

    print(f"Request failed, waiting for 5 seconds before retrying...")
    time.sleep(5)

website.py

from flask import Flask, request, jsonify
import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
from email_validator import validate_email, EmailNotValidError

app = Flask(__name__)

user_agent = UserAgent()

random_user_agent = user_agent.random

@app.route('/checkdata', methods=['GET'])
def check_data():
    email = request.args.get('email')
    if not email:
        return jsonify({'error': 'Email is required',
                        'path': request.host_url + '[email protected]'
                        })

    try:
        valid = validate_email(email)
        email = valid.email
    except EmailNotValidError as e:
        # return jsonify({'error': "Invalid email address"})
        pass

    headers = {
        'User-Agent': random_user_agent,
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
        'Accept-Language': 'id,en-US;q=0.7,en;q=0.3',
        'Content-Type': 'application/x-www-form-urlencoded',
        'Origin': 'https://periksadata.com',
        'Alt-Used': 'periksadata.com',
        'Connection': 'keep-alive',
        'Referer': 'https://periksadata.com',
        'Upgrade-Insecure-Requests': '1',
        'Sec-Fetch-Dest': 'document',
        'Sec-Fetch-Mode': 'navigate',
        'Sec-Fetch-Site': 'same-origin',
        'Sec-Fetch-User': '?1',
    }

    data = f'email={email}'
    response = requests.post('https://periksadata.com', headers=headers, data=data)
    data_json = {'results': []}

    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        paragraphs = soup.find_all('div', class_='col-md-6')

        for p in paragraphs:
            title_element = p.find('h5')
            if title_element:
                title = title_element.text.strip()
                link = 'https://periksadata.com' + p.find('a')['href']
                response2 = requests.get(link, headers=headers)
                soup2 = BeautifulSoup(response2.text, 'html.parser')
                lead_paragraph = soup2.find('p', class_='lead')
                if lead_paragraph:
                    description = lead_paragraph.text.strip()[:-45]
                else:
                    description = 'No lead paragraph found'

                data_leaked = soup2.find_all('span', class_='label label--inline text-center rounded')
                data_leaked_text = ' , '.join(leak.text.strip() for leak in data_leaked)

                paragraphs = p.find_all('p')
                data = []

                for para in paragraphs:
                    parts = para.find_all('b')
                    if len(parts) >= 2:
                        label = parts[0].text.strip()
                        datas = parts[2].text.strip()
                        data.append({'Tanggal Kejadian': label, 'Data yang bocor': data_leaked_text, 'Total keseluruhan data yang bocor': datas})

                result = {
                    'title': title,
                    'link': link,
                    'description': description,
                    'data': data,
                }
                data_json['results'].append(result)

        return jsonify({"User-Agent": random_user_agent, "Email": email, "Data": data_json})
    else:
        return jsonify({'error': 'Request failed'})

if __name__ == '__main__':
    app.run(debug=True)