Of Stack

How to use Selenium library of Python crawler

  • 2021-09-05 00:31:09
  • OfStack

Selenium is a tool for testing Web applications. The Selenium test runs directly in the browser, just like a real user is operating 1. Supported browsers include IE (7, 8, 9, 10, 11), Mozilla Firefox, Safari, Google Chrome, Opera, etc. The main features of this tool include: testing browser compatibility-testing your application to see if it works well on different browsers and operating systems. Test system functionality-Create regression tests to verify software functionality and user requirements. Support automatic recording actions and automatic generation of test scripts in different languages such as Net, Java and Perl. (Excerpt from Encyclopedia) 


#  Basic use 
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
browser = webdriver.Chrome()
try:
  browser.get('https://www.baidu.com')
  input = browser.find_element_by_id('kw')
  input.send_keys('Python')
  input.send_keys(Keys.ENTER)
  wait = WebDriverWait(browser, 10)
  wait.until(EC.presence_of_element_located((By.ID, 'content_left')))
  print(browser.current_url)
  print(browser.get_cookies())
  print(browser.page_source)
finally:
  browser.close()

#  Declare a browser object 
from selenium import webdriver
browser = webdriver.Chrome()
browser = webdriver.Firefox()
browser = webdriver.Edge()
browser = webdriver.PhantomJS()
browser = webdriver.Safari()

#  Access the page 
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
print(browser.page_source)
browser.close()

#  Find Elements 
#  Single element 
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
#  Below 3 The effect is 1 Like 
input_first = browser.find_element_by_id('q')
input_second = browser.find_element_by_css_selector('#q')
input_third = browser.find_element_by_xpath('//*[@id="q"]')
print(input_first)
print(input_second)
print(input_third)
browser.close()

from selenium import webdriver
from selenium.webdriver.common.by import By
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input_first = browser.find_element(By.ID, 'q')
print(input_first)
browser.close()

#  Multiple elements 
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
lis = browser.find_elements_by_css_selector('.service-bd li')
print(lis)
browser.close()

from selenium import webdriver
from selenium.webdriver.common.by import By
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
lis = browser.find_elements(By.CSS_SELECTOR, '.service-bd li')
print(lis)
browser.close()

#  Element interaction 
#  Call the interactive method on the retrieved element 
from selenium import webdriver
import time
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input = browser.find_element_by_id('q')
input.send_keys(' Notebook computer ')
time.sleep(5)
input.clear()
input.send_keys('iPad')
button = browser.find_element_by_class_name('btn-search')
# button.click()

#  Interactive action 
#  Attach an action to an action chain for serial execution 
from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
url = "http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable"
browser.get(url)
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
target = browser.find_element_by_css_selector('#droppable')
actions = ActionChains(browser)
actions.drag_and_drop(source, target)
actions.perform()

#  Execute JavaScript
from selenium import webdriver
browser = webdriver.Chrome()
browser.get("https://www.zhihu.com/explore")
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
browser.execute_script('alert("To Bottom")')

#  Get element information 
#  Get properties 
from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
browser.get("https://www.zhihu.com/explore")
logo = browser.find_element_by_id('zh-top-link-logo')
print(logo)
print(logo.get_attribute('class'))

#  Get a text value 
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.text)

#  Get ID , location, label name, size 
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.id)
print(input.location)
print(input.tag_name)
print(input.size)

# Frame
import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
browser = webdriver.Chrome()
browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
print(source)
try:
  logo = browser.find_element_by_class_name('logo')
except NoSuchElementException:
  print('NO LOGO')
browser.switch_to.parent_frame()
logo = browser.find_element_by_class_name('logo')
print(logo)
print(logo.text)

#  Wait 
#  Implicit wait 
#  When an implicit wait is used to execute a test, if WebDriver Not in DOM Will continue to wait and throw an exception that the element cannot be found after the set time, 
#  In other words, the implicit wait will wait when the find element or the element does not appear immediately 1 Find it again after a while DOM The default time is 0
from selenium import webdriver
browser = webdriver.Chrome()
browser.implicitly_wait(10)
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input)

#  Show wait 
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
browser = webdriver.Chrome()
browser.get('https://www.taobao.com/')
wait = WebDriverWait(browser, 10)
input = wait.until(EC.presence_of_element_located((By.ID, 'q')))
button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '.btn-search')))
print(input, button)

#  Forward and backward 
import time
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.get('https://www.taobao.com')
browser.get('https://www.python.org')
browser.back()
time.sleep(5)
browser.forward()
browser.close()

# Cookies
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
print(browser.get_cookies())
browser.add_cookie({'name':'name', 'domain':'www.zhihu.com', 'value':'germey'})
print(browser.get_cookies())
browser.delete_all_cookies()
print(browser.get_cookies())

#  Tab management 
import time
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.execute_script('window.open()')
print(browser.window_handles)
browser.switch_to_window(browser.window_handles[1])
browser.get('https://www.taobao.com')
time.sleep(5)
browser.switch_to_window(browser.window_handles[0])
browser.get('https://python.org')

#  Exception handling 
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.find_element_by_id('hello')

from selenium import webdriver
from selenium.common.exceptions import TimeoutException, NoSuchElementException
browser = webdriver.Chrome()
try:
  browser.get('https://www.baidu.com')
except TimeoutException:
  print('Time Out')
try:
  browser.find_element_by_id('hello')
except NoSuchElementException:
  print('No Element')
finally:
  browser.close()

The above is the Python crawler Selenium library of the use of the details, more information about the use of python Selenium library please pay attention to other related articles on this site!

Related articles: