I have created simple automation which will first read the read subdomain folder and then it will get into it and then find for the specific html file. If it will find it (i.e: .html) then edit it and i want to add the specific tag somewhere in that file but i am unable to do it.
staticWord = "Hair"
htmlTag = "<a href='"+ staticRandomPathList[0] + "'>" + staticWord + "</a>"
print(htmlTag)
# Now on we are working statically
folderfound = 0
filefound = 0
for domainNameFolder in range(len(staticRandomPathList)):
subDomainSelectedFilesAddress = driver.find_element(By.XPATH,"//table/tbody/tr[" + str(domainNameFolder + 1) + "]/td[" + str(1) + "]")
subDomainName = new_list[domainNameFolder] + '.' + domain_list[domain_variable]
if subDomainSelectedFilesAddress.text == "logs" or subDomainSelectedFilesAddress.text == "public_html":
continue
else:
if subDomainSelectedFilesAddress.text == "test1.testlab.com":
action = ActionChains(driver)
action.double_click(subDomainSelectedFilesAddress).perform()
time.sleep(1)
for file in range(0, 10):
time.sleep(1)
selectedFile = driver.find_element(By.XPATH, "//table/tbody/tr[" + str(
file + 1) + "]/td[" + str(1) + "]")
if selectedFile.text == "5.html":
selectedFile.click()
editFile = driver.find_element(By.XPATH, "//a[#ng-click='showHTMLEditorModal()']")
editFile.click()
# addHtmlTag = WebDriverWait(driver, 20).until(
# EC.visibility_of_element_located((By.CLASS_NAME, "ace_content")))
# insertAnchorTag = driver.find_element(By.CLASS_NAME, "ace_content")
# insertAnchorTag.click()
#
time.sleep(2)
textinput = driver.find_element(By.CLASS_NAME, "ace_text-layer")
print(textinput.text)
gettingTextFromServer = textinput.text
Html_file = open("HTMLParsing.html", "w")
newHTMLFile = Html_file.write(gettingTextFromServer)
html = newHTMLFile
print(html)
# soup = Soup(html)
# bodyTag = soup.find('body')
# anchor = soup.new_tag('a')
# anchor['href'] = staticRandomPathList[0]
# bodyTag.insert(anchor)
Html_file.close()
# print(insertAnchorTag.text)
# mapHTMLTag = driver.find_element(By.ID, "id='htmlEditorContent'")
# mapHTMLTag.send_keys(htmlTag)
# addHtmlTag.send_keys(htmlTag)
filefound = 1
break
else:
continue
if filefound == 1:
break
folderfound = 1
break
else:
continue
print("Successfully Outside Loop")
I am attaching the picture so you would be able to see where I want to place that tag.
This is nodejs selenium code that works. May be you can reproduce in python. Don't forget to navigate to any page page before editing page html. Good luck.
async navigateToHomePage() {
logger.info(`inside navigateToHomePage`)
await driver.get(this.baseUrl)
}
async insertHtmlIntoDocumentBody(html) {
logger.info(`inside insertHtmlIntoDocumentBody`)
let htmlElement = driver.findElement(By.css('html'))
let headElement = driver.findElement(By.css('head'))
let bodyElement = driver.findElement(By.css('body'))
logger.info(`starting html edition`)
await driver.executeScript(`let div =
document.createElement('html');
div.innerHTML='${JSON.stringify(html)}';
arguments[0].removeChild(arguments[1]);
arguments[0].removeChild(arguments[2]);
arguments[0].appendChild(div)`, htmlElement, headElement,
bodyElement)
logger.info(`completed html edition`)
}
I have developed following code. Normally it works fine. But, sometimes while downloading the records (record()), it fails as server fails to respond or if internet is disconnected. To avoid breaking of code I used 'try-exceptions' but then, I can not break out from record() as well as outer function simultaneously. So, looking for solution. Code around 197th line doesn't help in continuing the code from outer while loop. Code is here:
import glob
import datetime
import cv2
import base64
from PIL import Image
from io import BytesIO
import time
import selenium
import self as self
from pytesseract import pytesseract
from selenium.webdriver.common.keys import Keys
import os
from selenium.webdriver.support import expected_conditions as EC, expected_conditions
from selenium.webdriver.support.select import Select
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException, TimeoutException, StaleElementReferenceException, \
WebDriverException, ElementNotInteractableException, UnexpectedAlertPresentException
main_Directory = r'/home/sangharshmanuski/Documents/e_courts/mha/downloads4'
log_Directory = r'/home/sangharshmanuski/Documents/e_courts/mha/log'
driver = selenium.webdriver.Firefox()
url = r'https://districts.ecourts.gov.in/'
driver.get(url)
# create wait time variable for regular, short and mid
wait = WebDriverWait(driver, 180)
waitShort = WebDriverWait(driver, 3)
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#sateist > option:nth-child(22)")))
select = Select(driver.find_element_by_css_selector('#sateist'))
options = select.options
select.select_by_visible_text('Maharashtra')
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.region')))
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#sateist')))
districtListDropdown = Select(driver.find_element_by_css_selector("#sateist"))
distOptions = districtListDropdown.options
# iterate over each district
i = 1
while i < len(distOptions):
try:
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#sateist')))
newDistDropDown = Select(driver.find_element_by_css_selector("#sateist"))
except:
continue
newDistOptions = newDistDropDown.options
distName = newDistOptions[i].text
print(distName)
newDistDropDown.select_by_index(i)
# for creating directory as per each district.
district_directory = os.path.join(
main_Directory, distName) # create new
if not os.path.exists(district_directory): # if not directory exists, create one
os.mkdir(district_directory)
district_log_directory = os.path.join(log_Directory, distName)
if not os.path.exists(district_log_directory): # if not directory exists, create one
os.mkdir(district_log_directory)
headingDist = driver.find_element_by_css_selector('.heading')
if headingDist.text.lower() == distName.lower():
wait.until(
EC.element_to_be_clickable((By.CSS_SELECTOR, 'button.accordion2:nth-child(2)'))).click()
current = driver.window_handles[0]
wait.until(EC.element_to_be_clickable(
(By.CSS_SELECTOR,
'div.panel:nth-child(3) > ul:nth-child(1) > li:nth-child(6) > a:nth-child(1)'))).click()
# wait until new tab opens.
wait.until(EC.number_of_windows_to_be(2))
# define new tab by differentiating from current tab.
newWindow = [window for window in driver.window_handles if window != current][0]
# switch to the new tab. ref: https://stackoverflow.com/questions/41571217/python-3-5-selenium-how-to-handle-a-new-window-and-wait-until-it-is-fully-lo
driver.switch_to.window(newWindow)
# wait till court complex list appears.
wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#court_complex_code')))
# create list of all court complex.
# 2 approaches - 1 select 2 click.
time.sleep(3)
def complex_and_act():
this = driver.current_window_handle
def imgtotxt():
elem = driver.find_element_by_id("captcha_image")
loc = elem.location
size = elem.size
left = loc['x']
top = loc['y']
width = size['width']
height = size['height']
box = (int(left), int(top), int(left + width), int(top + height))
screenshot = driver.get_screenshot_as_base64()
img = Image.open(BytesIO(base64.b64decode(screenshot)))
area = img.crop(box)
area.save('/home/sangharshmanuski/Documents/e_courts/captcha/file_trial.png', 'PNG')
fullPath = r'/home/sangharshmanuski/Documents/e_courts/captcha'
f = os.listdir(fullPath)
desPath = r"/home/sangharshmanuski/Documents/e_courts/editC"
img = cv2.imread(os.path.join(fullPath, 'file_trial.png'), 0)
ret, thresh1 = cv2.threshold(img, 111, 255, cv2.THRESH_BINARY)
cv2.imwrite('/home/sangharshmanuski/Documents/e_courts/editC/oneDisNoLoop.png', thresh1)
# know the text with pytesseract
captchaText = pytesseract.image_to_string(
Image.open('/home/sangharshmanuski/Documents/e_courts/editC/oneDisNoLoop.png'))
captcha = driver.find_element_by_id('captcha')
captcha.send_keys(captchaText)
driver.find_element_by_css_selector('input.button:nth-child(1)').click()
time.sleep(1)
def proceed():
while True:
try:
waitShort.until(EC.alert_is_present())
driver.switch_to.alert.accept()
driver.switch_to.window(this)
driver.find_element_by_css_selector(
'#captcha_container_2 > div:nth-child('
'1) > div:nth-child(1) > span:nth-child(3) > a:nth-child(7) > img:nth-child(1)').click()
log_file = open(os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('alert was present' + '\n')
print('alert was present')
imgtotxt()
except:
# if the waitmsg is on, wait for 5 sec
log_file = open(os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('no alert' + '\n')
print('no alert')
waitmsg = 0
while driver.find_element_by_css_selector('#waitmsg').is_displayed():
if waitmsg < 7:
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('wait' + '\n')
print('waitmsg')
time.sleep(1)
waitmsg += 1
else:
log_file = open(os.path.join(
log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('waiting finished' + '\n')
print('waiting finished')
break
invalidCaptcha = "Invalid Captcha"
norecord = "Record Not Found"
try:
waitShort.until(
EC.presence_of_element_located((By.CSS_SELECTOR, '#errSpan > p:nth-child(1)')))
incorrect = driver.find_element_by_css_selector('#errSpan > p:nth-child(1)').text
if incorrect == invalidCaptcha:
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('Invalid Captcha' + '\n')
print('invalid captcha')
imgtotxt()
continue
else:
if incorrect == norecord:
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('Record not Found' + '\n')
return print('record not found')
except:
pass
def record():
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('Record Found' + '\n')
print('record fun started')
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, 'a.someclass')))
listAllView = driver.find_elements_by_css_selector(
'a.someclass')
# make new dirctory by name of Court Complex
distDir2 = os.path.join(
main_Directory, distName, nameCourtComp)
if not os.path.exists(distDir2):
os.makedirs(distDir2)
x = 0
for view in listAllView:
try:
view.click()
wait.until(EC.presence_of_element_located((By.ID, 'back_top')))
openFile = open(
os.path.join(distDir2, "file_" + str(x) + ".html"), "w")
openFile.write(driver.page_source)
openFile.close()
back = driver.find_element_by_id('back_top')
back.click()
x += 1
except (TimeoutException, ElementNotInteractableException):
driver.refresh()
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write(
'While Downloading record for '
+ nameCourtComp + ' error occured, retrying now...' + '\n')
nonlocal courtComp
courtComp -= 1
return print(
'While Downloading record for '
+ nameCourtComp + ' error occured, retrying now...')
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('record completed, ' + str(x) + ' records found' + '\n')
print('record completed, ' + str(x) + ' records found')
return
record()
return
courtComp = 1
courtComplexDownload = Select(
driver.find_element_by_css_selector('#court_complex_code'))
courtComplexDownloadList = courtComplexDownload.options
courtComplexLen = len(courtComplexDownloadList)
while courtComp < courtComplexLen:
nameCourtComp = courtComplexDownloadList[courtComp].text
log_file = open(os.path.join(log_Directory, nameCourtComp + '.txt'), 'w')
log_file.write(nameCourtComp + '\n' + '\n')
print(nameCourtComp)
courtComplexDownload.select_by_index(courtComp)
acts = Select(driver.find_element_by_css_selector('#actcode'))
actsOpt = acts.options
act = 0
while len(actsOpt) < 2:
if act < 10:
time.sleep(1)
act += 1
else:
#if there is no list to populate break out of this loop & go to next complex
raise Exception()
try:
acts.select_by_value('33')
except NoSuchElementException:
print('PoA not applicable')
log_file = open(
os.path.join(log_Directory, nameCourtComp + '.txt'), 'a')
log_file.write('No PoA' + '\n')
courtComp += 1
continue
imgtotxt()
proceed()
courtComp += 1
complex_and_act()
driver.close()
print("all court complexes in " + distName + " completed")
driver.switch_to.window(current)
driver.back()
else:
time.sleep(5)
continue
i += 1
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#sateist > option:nth-child(22)")))
select = Select(driver.find_element_by_css_selector('#sateist'))
options = select.options
select.select_by_visible_text('Maharashtra')
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.region')))
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#sateist')))
This is exactly what exceptions are for. Whenever you raise an exception, it's going to go to the containing scope, and if that scope doesn't catch it, it'll stop whatever it's doing and the exception will go up to the next scope, et cetera. It's a very easy way to make sure that if something goes wrong, you can break out of multiple levels of loop or multiple levels of function call without having to have each level check a return value.
When you swallow an exception, as you're doing here:
except (TimeoutException, ElementNotInteractableException):
...
return print(
'While Downloading record for '
+ nameCourtComp + ' error occured, retrying now...')
you're thwarting that process. (Note that you're returning None, so the caller gets no information whatsoever!) Instead, maybe do something like:
except (TimeoutException, ElementNotInteractableException):
...
print(
'While Downloading record for '
+ nameCourtComp + ' error occured, retrying now...')
raise
The raise will just re-raise the same exception up to the next level, where they can do their own handling. Alternatively, you could create your own exception (maybe with more information) and raise that instead; it's completely valid to catch an exception and then raise a different type of exception as a way of translating it for the caller.
I have written an Instagram Liking bot with python. The Liking function is:
Liking photos
unique_photos = len(pic_hrefs)
for pic_href in pic_hrefs:
driver.get(pic_href)
time.sleep(2)
try:
time.sleep(random.randint(4, 15))
like_button = lambda: driver.find_element_by_class_name("_8-yf5 ").click()
like_button().click()
for second in reversed(range(0, random.randint(18, 28))):
print_same_line("#" + hashtag + ': unique photos left: ' + str(unique_photos)
+ " | Sleeping " + str(second))
time.sleep(2)
except Exception as e:
time.sleep(2)
unique_photos -= 1
I want to add now a Likecount with alike limit. I also want to check if I already liked a picture and skip that one. How can I do that?
I have a table with multiple pages. I want to select say 5 elements from the table and click on the checkbox corresponding to those at a time. How is that possible through selenium python automation
def __init__(self, env):
self.driver = webdriver.Firefox()
self.driver.maximize_window()
if env == 'Staging':
self.driver.get("https://serviceconsole-stg.tivo.com/serviceconsole/login.action")
elif env == 'QE':
self.driver.get("http://serviceconsolese01.tivo.com:9090/serviceconsole")
else:
print "Environment is not available", env
print "\n Supported Environments are Staging and QE"
self.driver.quit()
raise SystemExit("Program Exited")
with open('config.json','r') as user_credentials:
config = json.load(user_credentials)
self.driver.find_element_by_id('username').send_keys(config['user']['name'])
self.driver.find_element_by_id('password').send_keys(config['user']['password'])
self.driver.find_element_by_id("signIn").click()
try:
self.driver.find_element_by_xpath('// *[ # id = "loginValidationError"]')
print "Login Not successful"
self.driver.quit()
raise SystemExit("Program Exited")
except NoSuchElementException:
print "Login Successful"
def addnewlinearpackage(self, title, enddate_days_from_today):
try:
# Select Manage
self.driver.find_element_by_xpath("//*[#id='configuration-tab']").click()
# Creating new Linear Package
self.driver.find_element_by_id("linearpublishing").click()
self.driver.find_element_by_id("linpub").click()
self.driver.find_element_by_id("addLinearPackage").click()
self.driver.find_element_by_id("linearpackageTitle").send_keys(title)
self.driver.find_element_by_id('tempPackageId').send_keys(
datetime.strftime(datetime.now(), '%Y%m%d%H%M'))
self.driver.find_element_by_id("inlineLinearPackageCheckbox").click()
start_time = self.driver.find_element_by_id('startDate')
execute = start_time.find_element_by_xpath("*//span[#class='fa fa-calendar']")
self.driver.execute_script("arguments[0].click();", execute)
time.sleep(7)
end_time = self.driver.find_element_by_id('endDate')
end_time.find_element_by_xpath("*//span[#class='fa fa-calendar']").click()
end_date = (datetime.now() + timedelta(days=enddate_days_from_today)).strftime('%m/%d/%Y')
self.driver.find_element_by_xpath("*//td[#data-day='" + end_date + "']").click()
time.sleep(7)
except NoSuchElementException as exp:
print exp
self.driver.quit()
raise SystemExit("Program Exited")
def addlinearservice(self, serviceId):
try:
self.driver.find_element_by_id("linearServiceSection").click()
time.sleep(10)
self.driver.find_element_by_id("publishLinearPackageBtn").click()
time.sleep(30)
self.driver.find_element_by_class_name("sorting_1")
linear_service_found = False
# Searching existing linear service
if linear_service_found == False:
try:# Search in first page
self.driver.find_element_by_xpath(
"/html/body/div[4]/div/div/div[2]/div/div/div/div[2]/div[2]/div/ul/li[9]/a").click()
if self.driver.find_element_by_link_text(serviceId).is_displayed():
self.driver.find_element_by_xpath(
"//a[contains(text(),'" + serviceId + "')]/following::td/input[#type='checkbox']").click()
linear_service_found = True
print "Linear service found"
except NoSuchElementException:
print"No such Element found in page 1"
try:
while linear_service_found == False: # loop to navigate to next page till finding the service ID
try: # Search till last page is reached and next button is disabled
self.driver.find_element_by_xpath(
"// *[#id = 'associatedLinearServicesTable1_next']/../li[#class ='paginate_button next disabled']")
print 'No further Page available to search'
break
except NoSuchElementException:
try:
self.driver.find_element_by_xpath(
'/html/body/div[4]/div/div/div[2]/div/div/div/div[2]/div[2]/div/ul/li[9]/a').click()
if self.driver.find_element_by_link_text(serviceId).is_displayed():
# click the checkbox of Service ID
self.driver.find_element_by_xpath(
"//a[contains(text(),'" + serviceId + "')]/following::td/input[#type='checkbox']").click()
linear_service_found = True
print "Linear Service found"
break
except NoSuchElementException:
print "No such Element found in current page"
except NoSuchElementException:
print"No such Element found"
if linear_service_found == True:
time.sleep(10)
#Click on Save button
self.driver.find_element_by_xpath('/ html / body / div[4] / div / div / div[3] / button[1]').click()
time.sleep(10)
except NoSuchElementException as exp:
print exp
self.driver.quit()
raise SystemExit("Program Exited")
def publish(self):
try:
self.driver.find_element_by_xpath('//button[contains(text(), "Publish")]').click()
time.sleep(5)
self.driver.find_element_by_xpath('//*[#id="confirmDialogOk"]').click()
time.sleep(10)
try:
self.driver.find_element_by_xpath('//*[#id="appSuccessMsg"]')
print("Linear Package Published Successfully")
except NoSuchElementException:
print ("Linear Package NOT PUBLISHED.. check the Error Message in Service console webpage")
time.sleep(60)
self.driver.quit()
raise SystemExit("Program Exited")
except NoSuchElementException as exp:
print exp
self.driver.quit()
raise SystemExit("Program Exited")
def exit(self):
print("Exiting.....")
time.sleep(5)
self.driver.quit()
Please find the full code. This code works only for selecting one element. I have to select multiple elements.
image
If the checkboxes have a common locator, you can use find_elements_by_xpath instead of find_element_by_xpath. This will return a list of WebElements, which you can then iterate over to click the boxes.
I currently have the program find the element and click it, but sometimes the element will not be there because the item has not been released yet. So i would want to the script to check if the item is there and if it is click, if not refresh the page and check again.
Here is the product finding script:
def select_product(keyword, color):
driver.find_element_by_xpath("//article//a[contains(., '" + keyword + "')]/../../p/a[contains(., '" + color + "')]").click()
Thanks!
Have you tried something like this?
def select_product(keyword, color):
xpath = "//article//a[contains(., '" + keyword + "')]/../../p/a[contains(., '" + color + "')]"
while True:
try:
driver.find_element_by_xpath(xpath).click()
return
except NoSuchElementException:
sleep(2)
driver.refresh()