I am scraping a website with selenium and send an alert, if something specific happens. Generally, my code works fine, but sometimes the website doesn't load the elements or the website has an error message like: "Sorry, something went wrong! Please refresh the page and try again!" Both times, my script waits until elements are loaded, but they don't and then my program doesn't do anything. I usually use requests and Beautifulsoup for web scraping, so I am not that familiar with selenium and I am not sure how to handle these errors, because my code doesn't send an error message and just waits, until the elements load, which will likely never happen. If I manually refresh the page, the program continues to work. My idea would be something like: If it takes more than 10 seconds to load, refresh the page and try again. My code looks somewhat like this:
def get_data():
data_list = []
while len(data_list) < 3:
try:
data = driver.find_elements_by_class_name('text-color-main-secondary.text-sm.font-bold.text-left')
count = len(data)
data_list.append(data)
driver.implicitly_wait(2)
time.sleep(.05)
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
WebDriverWait(driver, 3).until(EC.visibility_of_element_located((By.CLASS_NAME,
'text-color-main-secondary.text-sm.font-bold.text-left'.format(
str(
count + 1)))))
except TimeoutException:
break
text = []
elements = []
for i in range(len(data_list)):
for j in range(len(data_list[i])):
t = data_list[i][j].text
elements.append(data_list[i][j])
for word in t.split():
if '#' in word:
text.append(word)
return text, elements
option = webdriver.ChromeOptions()
option.add_extension('')
path = ''
driver = webdriver.Chrome(executable_path=path, options=option)
driver.get('')
login(passphrase)
driver.switch_to.window(driver.window_handles[0])
while True:
try:
infos, elements = get_data()
data, message = check_data(infos, elements)
if data:
send_alert(message)
time.sleep(600)
driver.refresh()
except Exception as e:
exception_type, exception_object, exception_traceback = sys.exc_info()
line_number = exception_traceback.tb_lineno
print("an exception occured - {}".format(e) + " in line: " + str(line_number))