Develop Reference

How to solve invisible captcha on Selenium

Hi I am trying to write a sign-up bot for UEFA.com using Selenium as requests I find to be too difficult for me to try so I am just working on automating the sign-up process even if it is a lot slower.
I am able to get to the final stage where I click on Create an Account, but faced with a reCaptcha which only appears after clicking on Create an Account. And after solving the captcha there is no 'Submit' button but it will automatically submit the details for you.
I am able to get the captcha token returned from 2captcha solving service, and inputted it into the innerHTML of the g-response-token field using javascript. However I do not know how to submit the captcha and the form.
import requests
import time
from selenium.webdriver.support.ui import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from seleniumwire import webdriver
import pyautogui
from twocaptcha import TwoCaptcha
import random
import os
from random import randint
import sys
firstnames = []
lastnames = []
API_Key = '6LehfZUbAAAAAJhue_6BVqqxLulLiXLP0rEgpdRH'
# Open Names File
with open('firstnames.txt', 'r') as f:
for name in f:
name = name.strip()
firstnames.append(name)
with open('lastnames.txt', 'r') as e:
for name in e:
name = name.strip()
lastnames.append(name)
with open('proxies.txt') as f:
proxy = f.readlines()
proxy_rand = randint(1, 35)
s_proxy = str(proxy[proxy_rand])
p_strip = s_proxy.rstrip()
# Proxy Input and Format
bare_proxy = p_strip.split(':')
username = bare_proxy[2]
password = bare_proxy[3]
ip = bare_proxy[0]
port = bare_proxy[1]
options = {
'proxy': {
'http': f'http://{username}:{password}#{ip}:{port}',
'https': f'https://{username}:{password}#{ip}:{port}',
'no_proxy': 'localhost,127.0.0.1'
}
}
os.environ['PATH'] += 'C:/SeleniumDrivers'
homepage_URL = 'https://www.uefa.com/tickets/'
driver = webdriver.Chrome(seleniumwire_options=options)
driver.get(homepage_URL)
# Accessing Register Page
reject_cookies = driver.find_element(By.ID, 'onetrust-reject-all-handler')
reject_cookies.click()
time.sleep(1)
login_button = driver.find_element(By.CSS_SELECTOR, "a[class='btn btn-secondary tickets__btn js-tracking-card']")
login_button.click()
time.sleep(10)
create_account = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[4]/a')
create_account.click()
time.sleep(10)
# Inputting SignUp Details
letters = 'abcdefghijklmnopqrstuvwxyz'
a = random.choice(letters)
b = random.choice(letters)
c = random.choice(letters)
d = random.choice(letters)
email = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[1]/div[6]/input')
email.send_keys(f'{a}{b}{c}{d}#nottingham.pro')
time.sleep(2)
password = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[1]/div[7]/input')
password.send_keys('19741002Rw!')
time.sleep(2)
first_name = driver.find_element(By.XPATH, '//*[#id="gigya-textbox-130722358975432270"]')
first_range = len(firstnames) - 1
random_first = randint(1, first_range)
f_name = firstnames[random_first]
first_name.send_keys(f'{f_name}')
time.sleep(2)
last_name = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[1]/div[9]/input')
last_range = len(lastnames) - 1
random_last = randint(1, first_range)
l_name = lastnames[random_last]
last_name.send_keys(f'{l_name}')
time.sleep(2)
day_of_birth = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[1]/div[10]/div[1]/input')
day = randint(1, 28)
day_of_birth.send_keys(f'{day}')
time.sleep(2)
month_of_birth = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[1]/div[10]/div[2]/input')
month = randint(1, 12)
month_of_birth.send_keys(f'{month}')
time.sleep(2)
year_of_birth = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/div/form/div[1]/div[10]/div[3]/input')
year = randint(1940, 2000)
year_of_birth.send_keys(f'{year}')
driver.execute_script("window.scrollTo(0, 500)")
time.sleep(2)
pyautogui.moveTo(353, 619)
time.sleep(2)
pyautogui.click()
time.sleep(5)
current_url = driver.current_url
print(current_url)
g_key = '6LehfZUbAAAAAJhue_6BVqqxLulLiXLP0rEgpdRH'
def SolveCaptcha():
sys.path.append(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))
api_key = os.getenv(g_key, 'a733edea49a8327795d56edc9f06d391')
solver = TwoCaptcha(api_key)
try:
result = solver.recaptcha(
sitekey=g_key,
url=current_url)
except Exception as e:
print(e)
else:
return result
result = SolveCaptcha()
code = result['code']
print(code)
token = f'document.getElementById("g-recaptcha-response").innerHTML="{code}";'
driver.execute_script(token)
time.sleep(10000)
As you can see by the end of the code I have managed to input the captcha token but not sure how to submit as there is no submit button
I have tried to look for a callback function but can't seem to find it when I inspect the page.

submit the first form on the page:
driver.execute_script('document.forms[0].submit()')

How to handle StaleElementReferenceException in Selenium Python?

I am trying to scrape Twitter followers and the bio of the followers from a certain Twitter account.
The account has more than 10000 followers. I have ran the code many times but it scrapes like 5000,7000 sometimes 9000 followers and then throws StaleElementRefrenceException.
I am a beginner, so it would be of great help if you suggest where to make what changes in the code, so it won't throw the exception.
import csv
from getpass import getpass
from time import sleep
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import Chrome
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
def get_followers_and_bio(cardd):
screen_name = cardd.find_element_by_xpath('./div//span').text
username = cardd.find_element_by_xpath('.//span[contains(text(), "#")]').text
i = cardd.text.split("\n").index('Follow')
bio = cardd.text.split("\n")[i+1:]
user = (screen_name, username, bio)
return user
# Create instance of the web driver
driver = webdriver.Chrome(ChromeDriverManager().install())
# Navigate to login screen
driver.get('https://www.twitter.com/login')
driver.maximize_window()
sleep(5)
username = driver.find_element_by_xpath('//input[#name="text"]')
username.send_keys('myemail#gmail.com')
username.send_keys(Keys.RETURN)
sleep(10)
username1 = driver.find_element_by_xpath('//input[#name="text"]')
username1.send_keys('myusername')
username1.send_keys(Keys.RETURN)
my_password = getpass()
password = driver.find_element_by_xpath('//input[#name="password"]')
password.send_keys(my_password)
password.send_keys(Keys.RETURN)
sleep(5)
# Find search input and search for term or user
search_input = driver.find_element_by_xpath('//input[#aria-label="Search query"]')
search_input.send_keys('#username')
search_input.send_keys(Keys.RETURN)
sleep(5)
driver.find_element_by_link_text('People').click()
sleep(5)
driver.find_element_by_link_text('#username').click()
sleep(5)
# Opening user's followers list
driver.find_element_by_xpath("//a[#href='/username/followers']").click()
sleep(5)
# Get all followers and their bio on the page
followers_list = []
last_position = driver.execute_script("return window.pageYOffset;")
scrolling = True
while scrolling:
cards = driver.find_elements_by_xpath('//div[#data-testid="UserCell"]')
for card in cards:
data = get_followers_and_bio(card)
if data:
followers_list.append(data)
scroll_attempt = 0
while True:
# Check scroll position
driver.execute_script('window.scrollTo(0, document.body.scrollHeight);')
sleep(2)
curr_position = driver.execute_script("return window.pageYOffset;")
if last_position == curr_position:
scroll_attempt += 1
# End of scroll region
if scroll_attempt >= 5:
scrolling = False
break
else:
sleep(3) # Attempt to scroll again
else:
last_position = curr_position
break

how to save data from multiple pages using webdriver into a single csv

so i'm trying to save data from googlescholar using selenium (webdriver) and so far i can print the data that i want, but i when i saved it into a csv it only saves the first page
from selenium import webdriver
from selenium.webdriver.common.by import By
# Import statements for explicit wait
from selenium.webdriver.support.ui import WebDriverWait as W
from selenium.webdriver.support import expected_conditions as EC
import time
import csv
from csv import writer
exec_path = r"C:\Users\gvste\Desktop\proyecto\chromedriver.exe"
URL = r"https://scholar.google.com/citations?view_op=view_org&hl=en&authuser=2&org=8337597745079551909"
button_locators = ['//*[#id="gsc_authors_bottom_pag"]/div/button[2]', '//*[#id="gsc_authors_bottom_pag"]/div/button[2]','//*[#id="gsc_authors_bottom_pag"]/div/button[2]']
wait_time = 3
driver = webdriver.Chrome(executable_path=exec_path)
driver.get(URL)
wait = W(driver, wait_time)
#driver.maximize_window()
for j in range(len(button_locators)):
button_link = wait.until(EC.element_to_be_clickable((By.XPATH, button_locators[j])))
address = driver.find_elements_by_class_name("gsc_1usr")
#for post in address:
#print(post.text)
time.sleep(4)
with open('post.csv','a') as s:
for i in range(len(address)):
addresst = address
#if addresst == 'NONE':
# addresst = str(address)
#else:
addresst = address[i].text.replace('\n',',')
s.write(addresst+ '\n')
button_link.click()
time.sleep(4)
#driver.quit()

You only get one first page data because your program stops after it clicks next page button. You have to put all that in a for loop.
Notice i wrote in range(7), because I know there are 7 pages to open, in reality we should never do that. Imagine if we have thousands of pages. We should add some logic to check if the "next page button" exists or something and loop until it doesn't
exec_path = r"C:\Users\gvste\Desktop\proyecto\chromedriver.exe"
URL = r"https://scholar.google.com/citations?view_op=view_org&hl=en&authuser=2&org=8337597745079551909"
button_locators = "/html/body/div/div[8]/div[2]/div/div[12]/div/button[2]"
wait_time = 3
driver = webdriver.Chrome(executable_path=exec_path)
driver.get(URL)
wait = W(driver, wait_time)
time.sleep(4)
# 7 pages. In reality, we should get this number programmatically
for page in range(7):
# read data from new page
address = driver.find_elements_by_class_name("gsc_1usr")
# write to file
with open('post.csv','a') as s:
for i in range(len(address)):
addresst = address[i].text.replace('\n',',')
s.write(addresst+ '\n')
# find and click next page button
button_link = wait.until(EC.element_to_be_clickable((By.XPATH, button_locators)))
button_link.click()
time.sleep(4)
also in the future you should look to change all these time.sleeps to wait.until. Because sometimes your page loads quicker, and the program could do it's job faster. Or even worse, your network might get a lag and that would screw up your script.

Absolute Path: Selenium Xpath Can't Identify Element

I am attempting to identify an HTML Button with Xpath and have attempted both the relative and absolute Xpath without success. I am attempting to click the button.
The relative path:
click = webdriver.find.element_by_xpath("//onboarding-mobile-fixed-bottom-container/div[1]/div/sprout-button/button").click()
Absolute path: /html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-business-phone/section/form/onboarding-next-button/onboarding-mobile-fixed-bottom-container/div[2]/sprout-button/button
absolute = webdriver.find.element_by_xpath("/html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-business-phone/section/form/onboarding-next-button/onboarding-mobile-fixed-bottom-container/div[2]/sprout-button/button").click()
Even when using the absolute xpath (I know, frowned upon practice) I can't get the button to click.
For reference, I am automating: site: https://account.kabbage.com/onboarding/data/number-of-employees; Username: testingoverflow#aol.com; Pw: Kabbage123
(click finish applying; finish applying; working on the continue box)
Any help is much appreciated!!
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep, strftime
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
import csv
import xlrd
info = "info.xlsx"
openwb = xlrd.open_workbook(info)
inputws = openwb.sheet_by_index(0)
print(inputws.nrows)
print(inputws.ncols)
print(inputws.cell_value(1,0))
email_log = inputws.cell_value(2,0)
businesslog = inputws.cell_value(2,1)
firstname = inputws.cell_value(2,2)
lastname = inputws.cell_value(2,3)
phone = int(inputws.cell_value(2,4))
employees = int(inputws.cell_value(2,5))
business_types = inputws.cell_value(2,6)
print(email_log)
print(businesslog)
print(firstname)
print(lastname)
print(phone)
sleep(1)
chromedriver_path = 'C:/Users/Documents/Scale/Programs/chromedriver.exe'
webdriver = webdriver.Chrome(executable_path=chromedriver_path)
webdriver.get('https://app.kabbage.com/signup/create_account')
sleep(1)
#input email
input_emails = webdriver.find_element_by_xpath('//*[#id="CreateAccount.EmailAddress_inner"]').send_keys(email_log)
sleep(1)
#re-input email
reinput = webdriver.find_element_by_xpath('//*[#id="CreateAccount.ConfirmEmail_inner"]').send_keys(email_log)
# Password
passwrd = webdriver.find_element_by_xpath('//*[#id="CreateAccount.CreatePassword"]')
sleep(1)
passwrd.send_keys('Paycheck11!!')
sleep(1)
button_started = webdriver.find_element_by_class_name("btn-full-width").click()
sleep(5)
#ApplyNow
#apply = webdriver.find_element_by_class_name('spr-btn spr-btn-primary')
#apply = webdriver.find_elements_by_class_name("spr-btn-primary").click()
#xpath("//div[#class='fc-day-content' and text()='15']")
applynow = webdriver.find_element_by_xpath("//sprout-button/button[contains(#class, 'spr-btn-primary')]").click()
sleep(5)
applyfinal = webdriver.find_element_by_xpath("//sprout-button/button[contains(#class, 'spr-btn-primary')]").click()
sleep(5)
business_name = webdriver.find_element_by_xpath('//*[#id="businessName-input"]').send_keys(businesslog)
business_send = webdriver.find_element_by_xpath("/html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-business-name/section/form/onboarding-next-button/onboarding-mobile-fixed-bottom-container/div[2]/sprout-button/button").click()
sleep(5)
first_name = webdriver.find_element_by_xpath('//*[#id="lastName-input"]').send_keys(lastname)
last_name = webdriver.find_element_by_xpath('//*[#id="firstName-input"]').send_keys(firstname)
names_send = webdriver.find_element_by_xpath("/html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-personal-name/section/form/onboarding-next-button/onboarding-mobile-fixed-bottom-container/div[2]/sprout-button/button").click()
sleep(5)
phone_num = webdriver.find_element_by_xpath('//*[#id="businessPhone-input"]').send_keys(phone)
phone_check = webdriver.find_element_by_xpath('//html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-business-phone/section/form/kbg-consent-box/div/sprout-checkbox/div/label').click()
#phone_send = names_send = webdriver.find_element_by_xpath("/html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-personal-name/section/form/onboarding-next-button/onboarding-mobile-fixed-bottom-container/div[2]/sprout-button/button").click()
phone_submits = webdriver.find_element_by_xpath("/html/body/cfapp-root/main/cfapp-spa-host/main/onboarding-root/div/div[1]/main/onboarding-business-phone/section/form/onboarding-next-button/onboarding-mobile-fixed-bottom-container/div[2]/sprout-button/button").click()
sleep(5)
num_empl = webdriver.find_element_by_xpath('//*[#id="numberOfEmployees-input"]').send_keys(employees)
#emp_submit = webdriver.find_element_by_xpath("//sprout-button/button[contains(#class, 'spr-btn-block')][2]").click()
sending = webdriver.find.element_by_xpath("//button[#class='spr-btn spr-btn-primary' and contains(text(),'Continue')]").click()

You can use any of these Xpaths:
Correct relative XPath for Continue button
Xpath 1:
*//onboarding-next-button//onboarding-mobile-fixed-bottom-container//div[2]//sprout-button//button[contains(text(),Continue)]
Xpath 2:
*//sprout-button[#class='desktop-button']//button[contains(text(),Continue)]

Give this a go:
webdriver.find_element_by_xpath("//button[#class="spr-btn spr-btn-primary" and contains(text(),'Continue')]").click()

How to choose a secondary hidden menu

I want to use selenium automatically export documents
# -*- coding: utf-8 -*-
from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support.ui import Select
import time
# Configuration information
email = "my_email"
password = "my_password"
def work_on():
driver = webdriver.Chrome()
index_url = "https://quip.com/"
driver.get(url=index_url)
time.sleep(1)
driver.find_element_by_xpath('//*[#id="header-nav-collapse"]/ul/li[9]/a').click() # click login
time.sleep(1)
driver.find_element_by_xpath('/html/body/div[2]/div[1]/div[1]/form/div/input').send_keys(email) # input email
driver.find_element_by_xpath('//*[#id="email-submit"]').click()
time.sleep(1)
driver.find_element_by_xpath('/html/body/div/div/form/div/input[2]').send_keys(password) # input password
driver.find_element_by_xpath('/html/body/div/div/form/button').click()
time.sleep(2)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[1]/div/div/div[3]/div[1]/a[2]/div/div').click() # click file
time.sleep(2)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[3]/div[2]/div/div/div/div[1]/div[2]/div[1]/a').click() # select test
time.sleep(2)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[3]/div[2]/div/div/div/div/div[2]/div/a').click() # select test
time.sleep(2)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[3]/div[1]/div[1]/div[1]/div[2]/button[1]').click() # select document
time.sleep(2)
ele = driver.find_element_by_id('id-7-export') # Determine the position of the element
actions = ActionChains(driver)
actions.move_to_element(ele)
actions.click(ele) # Export to html
actions.perform()
time.sleep(5)
driver.close()
if __name__ == '__main__':
work_on()
Error message
ele = driver.find_element_by_id('id-7-export') # Determine the position of the element
Cannot find label can't be exported
This code contains the account and password.Please test use
Automatic login may be incorrect, please try again

Not found this locator: .find_element_by_id('id-7-export') in the web page, instead you can use xpath:
//div[#class="parts-menu-label" and text()="Export"] -> to export
//div[#class="parts-menu-label" and text()="HTML"] -> to HTML
Try the bellow:
def work_on():
driver = webdriver.Chrome()
index_url = "https://quip.com/"
driver.get(url=index_url)
time.sleep(1)
driver.find_element_by_xpath('//*[#id="header-nav-collapse"]/ul/li[9]/a').click() # click login
time.sleep(1)
driver.find_element_by_xpath('/html/body/div[2]/div[1]/div[1]/form/div/input').send_keys(email) # input email
driver.find_element_by_xpath('//*[#id="email-submit"]').click()
time.sleep(1)
driver.find_element_by_xpath('/html/body/div/div/form/div/input[2]').send_keys(password) # input password
driver.find_element_by_xpath('/html/body/div/div/form/button').click()
time.sleep(2)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[1]/div/div/div[3]/div[1]/a[2]/div/div').click() # click file
time.sleep(5)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[3]/div[2]/div/div/div/div[1]/div[2]/div[1]/a').click() # select test
time.sleep(2)
driver.find_element_by_xpath('//h1[text()="test11"]').click() # select test
time.sleep(2)
driver.find_element_by_xpath('//*[#id="app"]/div/div/div/div[3]/div[1]/div[1]/div[1]/div[2]/button[1]').click() # select document
time.sleep(2)
ele = driver.find_element_by_xpath('//div[#class="parts-menu-label" and text()="Export"]') # Determine the position of the element
actions = ActionChains(driver)
actions.move_to_element(ele).perform()
time.sleep(1)
html = driver.find_element_by_xpath('//div[#class="parts-menu-label" and text()="HTML"]')
actions.move_to_element(html).click(html).perform()
time.sleep(5)
driver.close()