Conekta Scraper

requirements.txt

pip install selenium

scraper.py

#!/usr/bin/env python

import re as regex
from time import sleep
from getpass import getpass
from selenium import webdriver
from __future__ import print_function

def login(username, password):
    browser.get('https://auth.conekta.com/login')
    browser.find_element_by_id('user_email').send_keys(username)
    browser.find_element_by_id('user_password').send_keys(password)
    getpass('=> Press enter after you are done logging in\n')

def get_customer_id(link):
    href = link.get_attribute('href')
    matches = regex.search(r'/?customers/(cus_\w+)/?$', href)
    return matches.group(1) if matches else ''

def get_customer_information(email):
    browser.implicitly_wait(5)
    browser.get('https://admin.conekta.com/customers?search={query}'.format(query=email))
    try:
        customer_links = browser.find_elements_by_xpath('//a[contains(@href,"/customers/cus_")]')

        for link in customer_links:
            if (link.get_attribute('text').lower() == email.lower()):
                customer_id = get_customer_id(link)
                print('{email}, {id}'.format(email=email, id=customer_id))
    except Exception as exception:
        print(email, str(exception))

if __name__ == '__main__':
    print('=> Opening web browser...')
    browser = webdriver.Chrome()
    print('=> Logging in to the website...')
    login('raguilar@datacreativa.rocks', 'secret')

    emails = [
        'testversion3@mediakey.com.mx',
        'carlosav98@outlook.com',
        'testversion1@mediakey.com.mx',
        'paydiyispi@desoz.com',
    ]

    print('email,customer_id')
    for email in emails: get_customer_information(email)

    print('\n=> Closing web browser...')
    browser.close()