I am trying to find a particular class on a website. The class is sometimes present and sometimes it is absent.
So when the class is present, it takes a few seconds for the script to locate the element(logo). When the class is not present,the script runs for a long time and then end.
Why is that? is there any way to speed it up when the class doesn't exist?
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep
chrome_path = r"C:\Users\peter\Desktop\chromedriver.exe"
driver = webdriver.Chrome(executable_path=r"C:\Users\peter\Desktop\chromedriver.exe")
driver.get("https://example.com/app/login")
driver.minimize_window()
driver.implicitly_wait(300)
input_email = driver.find_element_by_xpath("//input[#type='email']")
input_email.send_keys('example#gmail.com')
input_password = driver.find_element_by_xpath("//input[#type='password']")
input_password.send_keys('example')
click_login = driver.find_element_by_xpath("//button[#type='submit']")
click_login.click()
driver.find_element_by_id("schedule-today").click()
sleep(2)
logo = driver.find_elements_by_xpath( "//*[contains(#class, 'lbl_lesson_status label label-info lbl_lesson_open')]" );
if not logo:
print("empty")
f = open("reserved_date", "a+")
for i in logo:
opendate = i.get_attribute("data-t-start-local");
f.write((opendate)+'\n')
print(opendate)
driver.close()
You Need To Add Wait And Add Try Except for example if element not found throw message and quit that script
I Simply Code For You!
Try This Code:
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.common.exceptions import *
from selenium.webdriver.common.keys import Keys
import time
chrome_path = r"C:\Users\peter\Desktop\chromedriver.exe"
driver = webdriver.Chrome(executable_path=r"C:\Users\peter\Desktop\chromedriver.exe")
driver.get("https://example.com/app/login")
driver.minimize_window()
try:
input_email = WebDriverWait(driver,20).until(EC.element_to_be_clickable((By.XPATH,"//input[#type='email']")))
input_email.send_keys('example#gmail.com')
except (TimeoutException,NoSuchElementException):
print('There is No Email Input!')
quit()
try:
input_password = WebDriverWait(driver,20).until(EC.element_to_be_clickable((By.XPATH,"//input[#type='password']")))
input_password.send_keys('example')
except (TimeoutException,NoSuchElementException):
print('There is No Password Input!')
quit()
try:
click_login = WebDriverWait(driver,20).until(EC.element_to_be_clickable((By.XPATH,"//button[#type='submit']")))
click_login.click()
except (TimeoutException,NoSuchElementException):
print('There is No Login Button!')
quit()
try:
WebDriverWait(driver,20).until(EC.element_to_be_clickable((By.CSS_SELECTOR,"#schedule-today")))
time.sleep(2)
except (TimeoutException,NoSuchElementException):
print("Can't Find schedule-today id!")
quit()
try:
logo = WebDriverWait(driver,20).until(EC.element_to_be_clickable((By.XPATH,"//*[contains(#class, 'lbl_lesson_status label label-info lbl_lesson_open')]")))
f = open("reserved_date", "a+")
for i in logo:
opendate = i.get_attribute("data-t-start-local");
f.write((opendate)+'\n')
print(opendate)
except (TimeoutException,NoSuchElementException):
print("Can't Find Logo Button!")
quit()
driver.close()
Related
Ok this is a bit embarrassing because I've asked a similar question on here sometime ago, but I tried the suggested solution ie (wait till element clickable), but it didn't work. So here's my code snipped.
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.common.exceptions import ElementClickInterceptedException, ElementNotInteractableException, TimeoutException, WebDriverException, NoSuchElementException
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from time import sleep
import re
import pandas as pd
def get_links(link):
driver = webdriver.Firefox()
driver.get(link)
driver.implicitly_wait(50)
sleep(5)
_flag = True
knt = 0
while _flag:
try:
WebDriverWait(driver, 50).until(EC.invisibility_of_element((By.XPATH, "//a[contains(class='ot-buttons-fw')]")))
WebDriverWait(driver, 50).until(EC.element_to_be_clickable((By.XPATH, "//a[#class='event__more event__more--static']")))
driver.find_element_by_xpath("//*[contains(text(), 'Show more matches')]").click()
print("works here!")
print("clicked....................................")
sleep(5)
_flag = True
#tmp = driver.find_elements_by_xpath("//span[contains(text(), 'NBA - Pre-season')]")
#if len(tmp) > 0:
#print("Found them!")
#_flag = False
if knt > 5: # For testing
print("Nuff clicked")
_flag = False
except(ElementNotInteractableException):
print("Error!")
_flag = False
driver.close()
return None
link = "https://www.flashscore.com/basketball/usa/nba/results/"
_ = get_links(link)
For some reason I keep getting an ElementClickInterceptedException Error at the driver.find_element_by_xpath("//*[contains(text(), 'Show more matches')]").click() line. Any help can do please
Your element overlap with other element, it cause the ElementClickInterceptedException error appear.
Before perform you code, please close the cookies popup with this code snippet:
def get_links(link):
driver = webdriver.Firefox()
driver.get(link)
driver.implicitly_wait(50)
sleep(5)
#here, close popup
if(len(driver.find_elements_by_id('onetrust-accept-btn-handler'))>0):
driver.find_element_by_id('onetrust-accept-btn-handler').click()
_flag = True
knt = 0
while _flag:
....
....
And remove this line:
WebDriverWait(driver, 50).until(EC.invisibility_of_element((By.XPATH, "//a[contains(class='ot-buttons-fw')]")))
This is invalid xpath expression, and no needed, have handled by if(popup accept) condition the above.
I'm working on a project that can scrape comments off posts on instagram and write them into an excel file.
Here's my code:
from selenium.webdriver.common.by import By
from selenium import webdriver
import time
import sys
import pandas as pd
from pandas import ExcelWriter
import os.path
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
url = [
"https://www.instagram.com/p/CcVTqRtJ2gj/",
"https://www.instagram.com/p/CcXpLHepve-/",
]
user_names = []
user_comments = []
driver = driver = webdriver.Chrome("C:\chromedriver.exe")
driver.get(url[0])
time.sleep(3)
username = WebDriverWait(driver, 30).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "input[name='username']")))
password = WebDriverWait(driver, 30).until(EC.element_to_be_clickable((By.CSS_SELECTOR,"input[name='password']")))
username.clear()
username.send_keys("username")
password.clear()
password.send_keys("pwd")
Login_button = (
WebDriverWait(driver, 2)
.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "button[type='submit']")))
.click()
)
time.sleep(4)
not_now = (
WebDriverWait(driver, 30)
.until(
EC.element_to_be_clickable((By.XPATH, '//button[contains(text(), "Not Now")]'))
)
.click()
)
for n in url:
try:
driver.get(n)
time.sleep(3)
load_more_comment = driver.find_element_by_xpath("//button[class='wpO6b ']")
print("Found {}".format(str(load_more_comment)))
i = 0
while load_more_comment.is_displayed() and i < 10:
load_more_comment.click()
time.sleep(1.5)
load_more_comment = driver.find_element_by_xpath(
"//button[class='wpO6b ']"
)
print("Found {}".format(str(load_more_comment)))
i += 1
user_names.pop(0)
user_comments.pop(0)
except Exception as e:
print(e)
pass
comment = driver.find_elements_by_class_name("gElp9 ")
for c in comment:
container = c.find_element_by_class_name("C4VMK")
name = container.find_element_by_class_name("_6lAjh ").text
content = container.find_element_by_class_name("MOdxS ").text
content = content.replace("\n", " ").strip().rstrip()
user_names.append(name)
user_comments.append(content)
print(content)
user_names.pop(0)
user_comments.pop(0)
# export(user_names, user_comments)
driver.close()
df = pd.DataFrame(list(zip(user_names, user_comments)), columns=["Name", "Comments"])
# df.to_excel("Anime Content Engagement.xlsx")
print(df)
And the load-more-comments part, doesn't seem to work.
Since there are more than one buttons with the same class name, I"m not able to choose the right button to click on. And I'm a beginner so if there's anyone with any solution to how I can solve this it would be great.
you can select by aria-label text:
driver.find_element_by_css_selector("svg._8-yf5[aria-label='TEXT']")
i believe the text inside changes according to instagram language, put it according to what appears on your
I've rceated a script to scrape different collection names from a webpage traversing multiple pages. The script can parse first 13 names from each page out of 100 names. One such collection name looks like Pudgy Penguins. How can I capture 100 names instead of only 13 from different pages of that site using selenium?
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
link = "https://opensea.io/rankings"
def scroll_to_the_bottom():
check_height = driver.execute_script("return document.body.scrollHeight;")
while True:
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
try:
WebDriverWait(driver,5).until(lambda driver: driver.execute_script("return document.body.scrollHeight;") > check_height)
check_height = driver.execute_script("return document.body.scrollHeight;")
except TimeoutException:
break
def get_collection_names(link):
driver.get(link)
while True:
scroll_to_the_bottom()
for item in WebDriverWait(driver,10).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR,"[role='listitem'] [class$='Ranking--row']"))):
collection_name = WebDriverWait(item,10).until(EC.visibility_of_element_located((By.CSS_SELECTOR,"[class$='Ranking--collection-name']"))).text
yield collection_name
try:
button = WebDriverWait(driver,10).until(EC.presence_of_element_located((By.XPATH,"//button[contains(#class,'Buttonreact__StyledButton')][./i[contains(.,'arrow_forward')]]")))
driver.execute_script('arguments[0].click();',button)
WebDriverWait(driver,10).until(EC.staleness_of(item))
except Exception as e:
return
if __name__ == '__main__':
driver = webdriver.Chrome()
for collection_name in get_collection_names(link):
print(collection_name)
Scrolling to the bottom of every page seems not to have any effect on the number of results the script produces.
I have checked your description and source code and I think there are many elements. So it doesn't load at one time. For solving this, scroll down to the bottom step by step. So, I have changed function scroll_to_the_bottom as below :
def scroll_to_the_bottom() :
H = driver.execute_script('return document.body.scrollHeight;')
h = 0
while True :
h += 300
if h >= H :
break
driver.execute_script("window.scrollTo({}, {});".format(0, h))
time.sleep(1)
So, embed above code into your code, we can change it as below :
import time
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
link = "https://opensea.io/rankings"
def get_collection_names(link):
driver.get(link)
unique_items = set()
while True:
item = WebDriverWait(driver,10).until(EC.presence_of_element_located((By.CSS_SELECTOR,"[class$='Ranking--collection-name']")))
H = driver.execute_script('return document.body.scrollHeight;')
h = 0
while True :
h += 300
if h >= H :
break
for element in WebDriverWait(driver,10).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR,"[class$='Ranking--collection-name']"))):
if element.text not in unique_items:
yield element.text
unique_items.add(element.text)
driver.execute_script("window.scrollTo(0, {});".format(h))
time.sleep(1)
try:
button = WebDriverWait(driver,10).until(EC.presence_of_element_located((By.XPATH,"//button[contains(#class,'Buttonreact__StyledButton')][./i[contains(.,'arrow_forward')]]")))
driver.execute_script('arguments[0].click();',button)
WebDriverWait(driver,10).until(EC.staleness_of(item))
except Exception as e:
return
if __name__ == '__main__':
driver = webdriver.Chrome()
for item in get_collection_names(link):
print(item)
driver.quit()
Hope to be helpful for you. Thanks.
I am trying to scrape data from here but getting error.
I have taken code from here Scraping using Selenium and python
This code was working perfectly fine but now I am getting error
wait.until(EC.visibility_of_element_located((By.LINK_TEXT, "All Boards")))
raise TimeoutException(message, screen, stacktrace)
After clicking on pe-funnel link , you can try with this code :
wait.until(EC.visibility_of_element_located((By.XPATH, "//*[name()='text' and #text-anchor='end']")))
all_data = driver.find_elements_by_xpath("//*[name()='text' and #text-anchor='end']")
print(len(all_data))
for data in all_data:
print(data.text)
UPDATE1 :
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
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support.select import Select
import time
driver = webdriver.Chrome(executable_path = r'D:/Automation/chromedriver.exe')
driver.maximize_window()
driver.get("https://eu1.dashboard.clevertap.com/login.html")
wait = WebDriverWait(driver, 20)
action = ActionChains(driver)
driver.switch_to.default_content()
wait.until(EC.element_to_be_clickable((By.NAME, "email"))).send_keys("abhishe***")
wait.until(EC.element_to_be_clickable((By.NAME,"password"))).send_keys("***")
wait.until(EC.element_to_be_clickable((By.ID,"submitBtn"))).click()
wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, 'div.ct-breadcrumb')))
driver.switch_to.default_content()
action.move_to_element(driver.find_element_by_css_selector("div.sidebar__brand+ul>li:first-child>a")).perform()
wait.until(EC.visibility_of_element_located((By.LINK_TEXT, "All Boards")))
wait.until(EC.element_to_be_clickable((By.LINK_TEXT,"All Boards"))).click()
wait.until(EC.element_to_be_clickable((By.LINK_TEXT,"pe-funnel"))).click()
time.sleep(1)
driver.execute_script("window.scrollTo(0,100)")
wait.until(EC.presence_of_all_elements_located((By.XPATH,"//*[name()='svg' and #class='highcharts-root']")))
all_charts = driver.find_elements_by_xpath("//*[name()='svg' and #class='highcharts-root']")
length_of_list = len(all_charts)
print(length_of_list)
i=0
while(i<len(all_charts)):
wait.until(EC.presence_of_all_elements_located((By.XPATH,"//*[name()='svg' and #class='highcharts-root']")))
all_charts = driver.find_elements_by_xpath("//*[name()='svg' and #class='highcharts-root']")
all_charts[i].click()
i=i+1
try:
print("Switch to frame")
wait.until(EC.frame_to_be_available_and_switch_to_it((By.ID,"wiz-iframe-intent")))
print("Switched to frame")
wait.until(EC.element_to_be_clickable((By.XPATH, "//button[text()='OK' and #class='annoucement-popup__btn']"))).click()
driver.switch_to.default_content()
print("Clicked on Ok button")
except:
print("in catch block")
pass
print("last of CATCH BLOCK")
driver.execute_script("window.scrollTo(0,1100)")
ActionChains(driver).move_to_element(driver.find_element_by_css_selector("input[data-introp='View your analysis']")).click().perform()
#wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,""))).click()
#ActionChains(driver).move_to_element(driver.find_element_by_css_selector("label[for='funnelProgressionPercent']")).send_keys(Keys.END).perform()
wait.until(EC.presence_of_all_elements_located((By.XPATH,"//*[name()='tspan' and #class='highcharts-text-outline']")))
all_values = driver.find_elements_by_xpath("//*[name()='tspan' and #class='highcharts-text-outline']")
for values in all_values:
print(values.text)
driver.execute_script("window.history.go(-1)")
driver.refresh()
I try to crawl the wechat public accounts includes the key word through "http://weixin.sogou.com/"
But i find i must use twice ActionChains(driver).move_to_element(nextpage).click().perform()，it can still work,and go to the next page !
who can tell me why and how to fix ! Thank you!
The source code are as follow , and sorry the comments are in the Chinese .
# coding=utf-8
import time
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
key = u"江南大学" #搜索的关键词
driver = webdriver.Chrome()
driver.get("http://weixin.sogou.com/")
assert u'搜狗微信' in driver.title
elem = driver.find_element_by_id("upquery")
elem.clear()
elem.send_keys(key)
button = driver.find_element_by_class_name("swz2") #搜索公众号
button.click()
WebDriverWait(driver,10).until(
EC.title_contains(key)
)
count = 0
while True:
for i in range(10):
try:
wechat_name = driver.find_element_by_xpath("//*[#id=\"sogou_vr_11002301_box_{}\"]/div[2]/h3".format(i)).text
print wechat_name
wechat_id = driver.find_element_by_xpath("//*[#id=\"sogou_vr_11002301_box_{}\"]/div[2]/h4/span/label".format(i)).text
print wechat_id
wechat_intro = driver.find_element_by_xpath("//*[#id=\"sogou_vr_11002301_box_{}\"]/div[2]/p[1]/span[2]".format(i)).text
print wechat_intro
print "*************************"
count += 1
except:
pass
try:
nextpage = driver.find_element_by_xpath("//*[#id=\"sogou_next\"]") #下一页的按钮
actions = ActionChains(driver)
actions.move_to_element(nextpage)
actions.click().
actions.perform()
actions = ActionChains(driver)
actions.move_to_element(nextpage)
actions.click().
actions.perform()
except Exception,e:
print e
break
driver.quit()
print count
You can chain your action, so no need to do perform after each action.
actions = ActionChains(driver)
actions.move_to_element(nextpage)
actions.click(nextpage)
actions.perform()
OR
actions = ActionChains(driver)
actions.move_to_element(nextpage)
actions.click(nextpage).perform()