Develop Reference

"element is not attached to the page document" Expection thrown after adding the implicit wait for selenium automation

I have added implicit wait in my code and it results in error "Message: stale element reference: element is not attached to the page document"
Below is the code
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
import time
service_obj = Service("C:/Users/divya/Downloads/chromedriver_win32/chromedriver.exe")
chrome_options = Options()
chrome_options.add_experimental_option("detach", True)
driver = webdriver.Chrome(service=service_obj)
driver.implicitly_wait(5)
driver.get("https://rahulshettyacademy.com/seleniumPractise/#/")
driver.find_element(By.CSS_SELECTOR, ".search-keyword").send_keys("ber")
# time.sleep(2)
products = driver.find_elements(By.XPATH, "//div[#class='products']/div")
count = len(products)
assert count > 0
for product in products:
product.find_element(By.XPATH, "div/button").click() #=======ERROR HERE=============
driver.find_element(By.CSS_SELECTOR, ".cart-icon").click()
driver.find_element(By.XPATH, "//button[text()='PROCEED TO CHECKOUT']").click()
# time.sleep(3)
driver.find_element(By.XPATH, "//input[#type='text']").send_keys("rahulshettyacademy")
driver.find_element(By.CSS_SELECTOR, ".promoBtn").click()
Sleep() functions work fine instead of implicit waits.
Anyone having suggestion/reason for the same. Please guide

You need to wait for some time after searching:
driver.get("https://rahulshettyacademy.com/seleniumPractise/#/")
driver.find_element(By.CSS_SELECTOR, ".search-keyword").send_keys("ber")
time.sleep(1)
products = driver.find_elements(By.XPATH, "//div[#class='products']/div")
count = len(products)
assert count > 0
i = 0
for i in range(len(products)):
driver.find_element(By.XPATH, "(//div[#class='products']//button)[" + str(i + 1) + "]").click()
driver.find_element(By.CSS_SELECTOR, ".cart-icon").click()
driver.find_element(By.XPATH, "//button[text()='PROCEED TO CHECKOUT']").click()
time.sleep(1)
driver.find_element(By.XPATH, "//input[#type='text']").send_keys("rahulshettyacademy")
driver.find_element(By.CSS_SELECTOR, ".promoBtn").click()

Webscraping Multiple Pages in Python with Selenium - loop not working

I'm quite new to python and have written a script using selenium to scrape a website. I've tried everything but can't get the loop to cycle through pages. It currently just repeats the data on the first page 5 times. I want to scrape all the pages for 'BR1' any help would be great, currently the script below only scrapes the first page 5 times.
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
with open('rightmove.csv', 'w') as file:
file.write('PropertyCardcontent \n')
PATH = ("/usr/local/bin/chromedriver")
driver = webdriver.Chrome(PATH)
driver.get("https://www.rightmove.co.uk/house-prices.html")
print(driver.title)
elem = driver.find_element(By.NAME, 'searchLocation') # Find the search box
elem.send_keys('BR1' + Keys.RETURN)
try:
content = WebDriverWait(driver, 15).until(
EC.presence_of_element_located((By.ID,'content'))
)
finally:
time.sleep(3)
for p in range(5):
sold = content.find_elements(By.CLASS_NAME, 'sold-prices-content-wrapper ')
for solds in sold:
address = solds.find_elements(By.CLASS_NAME, 'sold-prices-content ')
for addresses in address:
result = addresses.find_elements(By.CLASS_NAME, 'results ')
for results in result:
card = results.find_elements(By.CLASS_NAME,'propertyCard')
for propertyCard in card:
header = propertyCard.find_elements(By.CLASS_NAME,'propertyCard-content')
for propertyCardcontent in header:
road = propertyCardcontent.find_elements(By.CLASS_NAME,'title')
for propertyCardcontent in header:
road = propertyCardcontent.find_elements(By.CLASS_NAME,'subTitle')
for subtitle in road:
bed = subtitle.find_elements(By.CLASS_NAME, 'propertyType')
with open('rightmove.csv', 'a') as file:
for i in range(len(result)):
file.write(header[i].text + '\n')
button = driver.find_element(By.XPATH, '//*[#id="content"]/div[2]/div[2]/div[4]/div[27]/div[3]/div')
button.click()
file.close()
time.sleep(3)
driver.quit()

Since the website link has page number on it, I recommend you put the base url as "https://www.rightmove.co.uk/house-prices/br1.html?page=1", and loop through the pages while changing the last index of the url with methods like format string.
One other thing, you don't need to implement all those for loops, you can simply assign each variable to its specific value since everything you need is inside an html block which is easy to navigate on it.
Update:
I'm sorry for being late, had unexpected stuff(...).
I've made some changes as I use Brave, so make sure you select your browser, Chrome I believe, the chromedriver(ver:102) stays the same (or depending your Chrome version).
I've also got the Price and Date and stored them in a tuple.
Every record is stored in a list[Title, propertyType, tupleof(Price_Date)]
At the end, it creates a csv and stores everything inside with a ";" as delimter.
You can if you prefer split the price and date for later use, up to you.
Note: This looping method only applies to websites in which the number of page is included within the URL. In this case, both the key and number of page is included in the URL.
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
import time
import random
import itertools
options = Options()
options.binary_location = r'C:\Program Files\BraveSoftware\Brave-Browser\Application\brave.exe'
driver = webdriver.Chrome(options = options, service = Service("chromedriver.exe"))
key_word = "BR1".lower()
base_url = f"https://www.rightmove.co.uk/house-prices/{key_word}.html?page=1"
driver.get(base_url)
#Number of pages
pages = driver.find_element(By.XPATH, '//span[#class="pagination-label"][2]').text
pages = int(pages.strip('of'))
WebDriverWait(driver, 15).until(
EC.presence_of_element_located((By.CLASS_NAME, 'results '))
)
data = []
pc = 0
for p in range(1,pages+1):
driver.get(f"https://www.rightmove.co.uk/house-prices/{key_word}.html?page={p}")
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, '//div//div[#class="propertyCard"]'))
)
propertyCards = driver.find_elements(By.XPATH, '//div//div[#class="propertyCard"]')
for propertyCard in propertyCards:
title = propertyCard.find_element(By.CLASS_NAME, 'title').text
propertyType = propertyCard.find_element(By.CLASS_NAME, 'propertyType').text
price_list = propertyCard.find_elements(By.CLASS_NAME, 'price')
date_list = propertyCard.find_elements(By.CLASS_NAME, 'date-sold')
data.append([title,propertyType])
for p, d in itertools.zip_longest(price_list, date_list , fillvalue = None):
try:
price = p.text
date = d.text
data[pc].append((price, date))
except Exception as e:
print(e)
pc+=1
time.sleep(random.randint(1,4))
print(data)
with open('rightmove.csv', 'w') as file:
header = "Title;propertyType;Price_Date\n"
file.write(header)
for record in data:
file.write("{};{};{}\n".format(record[0],record[1],record[2:]))
driver.quit()

You don't have to go down to dom elem by elem, you can just use xpath or class_name (if it's unique, otherwise it's better xpath or css-selector) and get the item you are looking for.
Anyway follow this:
import time
import selenium.webdriver as webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome("/usr/local/bin/chromedriver")
driver.get("https://www.rightmove.co.uk/house-prices.html")
# send query
query = "BR1"
search_bar = driver.find_element(By.XPATH, '//input[#class="searchBox ac_input"]')
search_bar.send_keys(query)
search_bar.send_keys(Keys.ENTER)
# wait to result been loaded
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.CLASS_NAME, 'propertyCard'))
)
#get amount of pages
pages = driver.find_element(By.XPATH, '//span[#class="pagination-label"][2]').text
pages = int(pages.replace('of ', ''))
data = []
i = 1
while i <= pages:
WebDriverWait(driver, 10).until(
EC.element_to_be_clickable((By.XPATH, '//div[contains(text(), "Next")]'))
).click()
# wait page load result
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, '//div//div[#class="propertyCard"]'))
)
propertyCards = driver.find_elements(By.XPATH, '//div//div[#class="propertyCard"]')
# loop over result and store data
for propertyCard in propertyCards:
title = propertyCard.find_element(By.CLASS_NAME, 'title').text
propertyType = propertyCard.find_element(By.CLASS_NAME, 'propertyType').text
data.append((title, propertyType))
time.sleep(1)
i += 1
print("you reach the last page")
#get number of results
printf(data)
driver.close()
I use a list of tuple cause in your example you want store 2 item, if you want store more data you can use a dict and then convert into csv with Dictwriter directly. Enjoy.

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.

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()

Scroll in Selenium Webdriver (Python)

Prerequisites.
You need an account at Instagram to use this script.
Setup a test environment:
Log in, open the needed list(works correctly):
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep
driver = webdriver.Chrome(
# driver = webdriver.Firefox(
# driver = webdriver.PhantomJS(
service_args=['--ignore-ssl-errors=true', '--ssl-protocol=any'])
driver.get("https://instagram.com/accounts/login")
username = driver.find_element_by_name("username")
password = driver.find_element_by_name("password")
username1 = 'instagram' # change it!
password1 = 'instagrampassword1' # change it!
username.send_keys(username1)
password.send_keys(password1)
submit_button = driver.find_element_by_css_selector(
'#react-root > div > article > div > div:nth-child(1) > div > form > span > button')
submit_button.click()
sleep(2)
link = 'https://www.instagram.com/youtube/'
driver.get(link)
driver.implicitly_wait(2)
driver.find_elements_by_class_name("_218yx")[2].click()
Wrong scroll.
How to fix this block?
How to focus and scroll correctly on this page?
My attempts:
driver.find_element_by_class_name("_cx1ua").send_keys(Keys.NULL) # focus
#The element has been deleted entirely or
#The element is no longer attached to the DOM.
driver.find_element_by_class_name("_q44m8").send_keys(Keys.NULL)
# cannot focus element
driver.find_element_by_class_name("_qjr85").send_keys(Keys.NULL)
# cannot focus element
for i in range(5):
driver.find_element_by_class_name("_cx1ua").send_keys(Keys.END)
=============================================================
to #Moshisho :
We need to focus on some element to activate it.
The question is what the element we need to choose to focus and how?
This is not a "body":
something like that, but not this:
background = driver.find_element_by_css_selector("body")
# background = driver.find_element_by_css_selector("div._2uju6")
for i in range(5):
background.send_keys(Keys.SPACE)
time.sleep(1)
Without it this command do not work.
to #Naveen :
print(driver.find_element_by_css_selector("div._a1rcs").location_once_scrolled_into_view) # {'x': 0, 'y': 0}
print(driver.find_element_by_class_name("_cx1ua").location_once_scrolled_into_view) # {'x': 376, 'y': 229}
print(driver.find_element_by_class_name("_q44m8").location_once_scrolled_into_view) # {'x': 376, 'y': 180}
print(driver.find_element_by_class_name("_qjr85").location_once_scrolled_into_view) # {'x': 376, 'y': 180}
And what's next?
driver.execute_script("window.scrollTo(0, 3000);") # do not working

Try the following code:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep
from selenium.webdriver.support.ui import Select
driver = webdriver.Chrome(
# driver = webdriver.Firefox(
# driver = webdriver.PhantomJS(
service_args=['--ignore-ssl-errors=true', '--ssl-protocol=any'])
driver.maximize_window()
driver.get("https://instagram.com/accounts/login")
username = driver.find_element_by_name("username")
password = driver.find_element_by_name("password")
username1 = 'instagramlogin1' # change it!
password1 = 'instagrampassword1' # change it!
username.send_keys(username1)
password.send_keys(password1)
submit_button = driver.find_element_by_css_selector(
'#react-root > div > article > div > div:nth-child(1) > div > form > span > button')
submit_button.click()
sleep(2)
link = 'https://www.instagram.com/youtube/'
driver.get(link)
driver.implicitly_wait(2)
following = driver.find_element_by_xpath("//a[#href='/youtube/following/']/span")
total_following = int(following.text)
print "total no. of users following: ", total_following
# click on 239 following, displays 10 users
following.click()
loaded_following = driver.find_elements_by_xpath("//ul[#class='_539vh _4j13h']/li")
loaded_till_now = len(loaded_following)
while(loaded_till_now<total_following):
print "following users loaded till now: ", loaded_till_now
print loaded_following[loaded_till_now-1]
loaded_following[loaded_till_now-1].location_once_scrolled_into_view
# driver.execute_script("arguments[0].focus();", loaded_following[loaded_till_now-1])
driver.find_element_by_tag_name('body').send_keys(Keys.END) # triggers AJAX request to load more users. observed that loading 10 users at a time.
sleep(1) # tried wihtout sleep but throws StaleElementReferenceException. As it takes time to get the resposne and update the DOM
loaded_following = driver.find_elements_by_xpath("//ul[#class='_539vh _4j13h']/li")
loaded_till_now = len(loaded_following)
# All 239 users are loaded.
driver.quit()
Observed that browser is sending AJAX request to load more users. this action is triggered when you scroll using mouse or enter Space or End keys

In order to scroll in the window, you need to execute JavaScript, try this:
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
EDIT: in order to focus an element (it needs to be able to get the focus e.g. an anchor, input, button etc...) you also need to use JavaScript executor:
elementToFocus = driver.find_element_by_id("yourID")
driver.execute_script("arguments[0].focus();", elementToFocus)

I'm working with a dynamic React app, I need to scroll to the pages bottom to make react render all the data.
For unknown reasons, solutions based on JS execute_script didn't work. However I got send_keys solution working:
# scroll to bottom to load all
WebDriverWait(driver, 5).until(
EC.presence_of_element_located((By.XPATH, "//body"))
)
attempt_num = 2
while attempt_num > 0:
try:
elem = driver.find_element_by_xpath("//body")
elem.click()
elem.send_keys(Keys.END)
except StaleElementReferenceException as e:
print(e)
attempt_num = attempt_num - 1
The click() on body and the retry for StaleElementReferenceException are crucial. I haven't found a more elegant way than to retry.
See top answer of How to avoid "StaleElementReferenceException" in Selenium?