I am using selenium/webdriver to testing a web on Chrome,
I want to trace the network activity that happens after I click on all buttons, each clicking opens a new tab(i could not change anything to the buttons for it control by compressed javascript),
i tried Chrome Dev Tools: How to trace network for a link that opens a new tab? but it did not match my expect.
Below is a mock example, in the example i want to capture the new tab request "https://cdn.bootcss.com/jquery/3.2.1/jquery.min.js" but failed
(my actual scenario is that all web page opened in a android app, each click create a new tab/window)
import json
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
caps = {
"browserName": "chrome",
'goog:loggingPrefs': {'performance': 'ALL'}
}
options = Options()
options.add_experimental_option("w3c",False)
driver = webdriver.Chrome(desired_capabilities=caps, options=options)
# access a link
driver.get("https://www.google.com/")
# add a link for open new tab(just mock)
driver.execute_script('a = window.document.createElement("a");a.id="newtab";a.href="https://cdn.bootcss.com/jquery/3.2.1/jquery.min.js";a.target="_blank";a.text="33333";window.document.body.appendChild(a);')
time.sleep(5)
# click a button/link which open a new tab
element = driver.find_element_by_id('newtab')
driver.execute_script("arguments[0].click();", element)
time.sleep(3)
wins = driver.window_handles
driver.switch_to.window(wins[-1])
performance_log = driver.get_log('performance')
for packet in performance_log:
message = json.loads(packet.get('message')).get('message')
if message.get('method') != 'Network.responseReceived':
continue
requestId = message.get('params').get('requestId')
url = message.get('params').get('response').get('url')
try:
resp = driver.execute_cdp_cmd('Network.getResponseBody', {'requestId': requestId})
except BaseException as e:
resp = "error"
print("\n===============")
print(url)
# print(resp)
Related
I am trying to scrape this website using python's BeautifulSoup package and for automating the user flow I am using selenium. As this website requires authentication to access this page, I am trying to log in first using selenium webdriver. Here is my code:
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.common.exceptions import TimeoutException
def configure_driver():
# Add additional Options to the webdriver
chrome_options = Options()
# add the argument and make the browser Headless.
chrome_options.add_argument("--headless")
# Instantiate the Webdriver: Mention the executable path of the webdriver you have downloaded
# For linux/Mac
# driver = webdriver.Chrome(options = chrome_options)
# For windows
driver = webdriver.Chrome(executable_path="/home/<user_name>/Downloads/chromedriver_linux64/chromedriver",
options = chrome_options)
return driver
def getLinks(driver):
# Step 1: Go to pluralsight.com, category section with selected search keyword
driver.get(f"https://www.coursera.org/learn/competitive-data-science/supplement/RrrDR/additional-material-and-links")
# wait for the element to load
try:
WebDriverWait(driver, 5).until(lambda s: s.find_element_by_class_name("_ojjigd").is_displayed())
except TimeoutException:
print("TimeoutException: Element not found")
return None
email = driver.find_element_by_name('email')
print(str(email))
password = driver.find_element_by_name('password')
email.send_keys("username") # provide some actual username
password.send_keys("password") # provide some actual password
form = driver.find_element_by_name('login')
print(form.submit())
WebDriverWait(driver, 10)
print(driver.title)
soup = BeautifulSoup(driver.page_source)
# Step 3: Iterate over the search result and fetch the course
divs = soup.findAll('div', args={'class': 'item-box-content'})
print(len(divs))
# create the driver object.
driver = configure_driver()
getLinks(driver)
# close the driver.
driver.close()
Now after doing form.submit() it is expected to log in and change the page, right? But it is simply staying in the same page, so I cannot access the contents of the authenticated page. Someone please help.
That is because there is no name attribute.
instead of this :
form = driver.find_element_by_name('login')
Use this :
wait.until(EC.element_to_be_clickable((By.XPATH, "//button[text()='Login']"))).click()
I tried this code on my local, seems to be working fine
driver.maximize_window()
wait = WebDriverWait(driver, 30)
driver.get("https://www.coursera.org/learn/competitive-data-science/supplement/RrrDR/additional-material-and-links")
wait.until(EC.element_to_be_clickable((By.ID, "email"))).send_keys("some user name")
wait.until(EC.element_to_be_clickable((By.ID, "password"))).send_keys("some user name")
wait.until(EC.element_to_be_clickable((By.XPATH, "//button[text()='Login']"))).click()
Since login button is in a form so .submit() should work too.
wait.until(EC.element_to_be_clickable((By.XPATH, "//button[text()='Login']"))).submit()
This works too.
I Have this login page, so after pass keys and clicking login button, the webpage should redirect me to a new page with my session, and sometimes it does, but in most case, the driver.title by example, still having the title of the Authentication page and obiously this prevent me to find elements of the page that I'm looking for.
I Already try to driver.get(correct url) but didn't work.
Here are my WebDriver's options.
options = Options()
options.page_load_strategy = 'eager'
options.binary_location = '/opt/headless-chromium'
options.add_argument('--headless')
options.add_argument('--no-sandbox')
options.add_argument('--single-process')
options.add_argument('--disable-dev-shm-usage')
driver = webdriver.Chrome('/opt/chromedriver', options=options)
driver.implicitly_wait(60)
options.page_load_strategy = 'eager'
Remove this, this will not wait for page load to finish . So you might be trying to get title before the page is loaded
I'd like to run an end-to-end test of logging into our website using Selenium. We use Auth0 and the only available login mechanism is through Google social login. I wrote a script using Python Selenium (version 3.141.0), pytest, and selenium/standalone-chrome:87.0 Docker image which works correctly on my local machine, Mac OS 10.15.4.
However, it gets stuck at some point when I try to run it on CircleCI.
I use ubuntu-1604:202007-01 image in CircleCI
How I set up remote driver (tried a lot of arguments/commands..):
#pytest.fixture(scope="function")
def browser(remote_webdriver_url):
options = webdriver.ChromeOptions()
options.add_argument('--disable-popup-blocking')
options.add_argument('--disable-web-security')
options.add_argument('--allow-running-insecure-content')
options.add_argument('--start-maximized')
options.add_argument('-incognito')
options.add_experimental_option("useAutomationExtension", False)
options.add_experimental_option("excludeSwitches", ["enable-automation"])
browser = webdriver.Remote(
command_executor=remote_webdriver_url,
desired_capabilities=DesiredCapabilities.CHROME,
options=options)
return browser
My docker-compose.yml
version: '3.1'
services:
selenium-chrome:
image: selenium/standalone-chrome:87.0
# added the envvar as I found something about this in Selenium forums, it has no effect.
environment:
DBUS_SESSION_BUS_ADDRESS: /dev/null
shm_size: 2g
restart: 'no'
ports:
- "4444:4444"
My test code:
import os
from selenium.webdriver.common.by import By
from selenium.webdriver.remote.webelement import WebElement
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
def test_logging_in(browser: WebElement, url):
auth0_title = "Sign In with Auth0"
browser.get(url)
assert browser.title == auth0_title
# Log in
auth_login_button_class_name = 'auth0-lock-social-button-text'
_ = WebDriverWait(browser, 20).until(EC.presence_of_element_located((By.CLASS_NAME, auth_login_button_class_name)))
sign_in_button = browser.find_element_by_class_name(auth_login_button_class_name)
browser.implicitly_wait(5)
#
sign_in_button.click()
# Wait until we're redirected to Google's login page
_ = WebDriverWait(browser,20).until(EC.title_contains('Google'))
# Type in the email address and go to the next page
email_input = browser.find_element_by_tag_name('input')
email_input.send_keys(os.environ.get('E2E_TEST_DEVELOPMENT_USER_EMAIL'))
first_next_button = browser.find_element_by_id("identifierNext")
first_next_button.click()
# Wait until the password entry screen is loaded
browser.get_screenshot_as_file('/tmp/scr.png')
_ = WebDriverWait(browser, 20).until(EC.presence_of_element_located((By.ID, "forgotPassword"))) ##### THIS IS WHERE I GET THE TIMEOUT
# Put the password in
password_input = browser.find_element_by_xpath("//input[#name='password']")
password_input.send_keys(os.environ.get('E2E_TEST_DEVELOPMENT_USER_PASSWORD'))
second_next_button = browser.find_element_by_id("passwordNext")
second_next_button.click()
# Wait until the login is successful by observing the logout button
logout_icon_class_name = "bp3-icon-log-out"
_ = WebDriverWait(browser, 20).until(EC.presence_of_element_located((By.CLASS_NAME, logout_icon_class_name)))
assert browser.title == 'My page title'
sign_out_button = browser.find_element_by_class_name(logout_icon_class_name)
sign_out_button.click()
def test_teardown(browser):
browser.close()
browser.quit()
The test times out after clicking on the first button after typing in the email. I got screenshots from the run in CI, and it does seem to be stuck loading (see the Google's progress bar at the top, and the fact that it's more white-ish color), see the screenshot:
I also took a screenshot before clicking on the "Next" button, to show the contrast:
After having spent a long time on this and trying many things, I'm about to give up. Any ideas why this works locally but not in CI environment?
I am making a simple crawler that can open a site and when a pop up appears, it should close it. but the following command isn't working.
from selenium import webdriver
browser = webdriver.Chrome(executable_path=r"C:\Program Files\chromedriver.exe")
url = "https://www.bnbaccessories.com/"
browser.get(url)
alert = webdriver.switch_to_alert().dismiss()
innerHTML = browser.execute_script("return document.body.innerHTML")
browser.implicitly_wait(50)
browser.close()
Use this
alert = browser.switch_to.alert.dismiss()
instead
webdriver.switch_to_alert().dismiss()
driver instance name is browser not webdriver
I'm trying to set MutationObserver for observing page mutation while loading.
In order to do that, MutationObserver should be configured before page loading.
With selenium-chromedriver, couldn't find the way to inject JS for such purpose.
I know chrome extension can do that but extensions won't work on headless mode.
That's the problem.
It's possible via the DevTool API by calling Page.addScriptToEvaluateOnNewDocument
from selenium import webdriver
from selenium.webdriver.remote.webdriver import WebDriver
import json
def send(driver, cmd, params={}):
resource = "/session/%s/chromium/send_command_and_get_result" % driver.session_id
url = driver.command_executor._url + resource
body = json.dumps({'cmd': cmd, 'params': params})
response = driver.command_executor._request('POST', url, body)
if response['status']:
raise Exception(response.get('value'))
return response.get('value')
def add_script(driver, script):
send(driver, "Page.addScriptToEvaluateOnNewDocument", {"source": script})
WebDriver.add_script = add_script
# launch Chrome
driver = webdriver.Chrome()
# add a script which will be executed when the page starts loading
driver.add_script("""
if (window.self === window.top) { // if main document
console.log('add script');
}
""")
# load a page
driver.get("https://stackoverflow.com/questions")
We can now use execute_cdp_cmd(cmd, cmd_args) to execute Chrome Devtools Protocol command in Selenium
from selenium import webdriver
driver = webdriver.Chrome()
driver.execute_cdp_cmd(
"Page.addScriptToEvaluateOnNewDocument",
{
"source": """// Your JavaScript here"""
}
)
driver.get("https://stackoverflow.com")
driver.quit()
The argument for "source" is just a string. So you can actually write your script in a .js file (for syntax highlighting) and read it using Python