Selenium

# Install the driver manager
pip install webdriver-manager

# Use with Chrome
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
driver = webdriver.Chrome(ChromeDriverManager().install())

# Alternative syntax using Service
service = Service(executable_path=ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)

# Firefox
from selenium import webdriver
from webdriver_manager.firefox import GeckoDriverManager
driver = webdriver.Firefox(executable_path=GeckoDriverManager().install())

# Edge
from selenium import webdriver
from webdriver_manager.microsoft import EdgeChromiumDriverManager
driver = webdriver.Edge(EdgeChromiumDriverManager().install())

# Opera on Linux
from selenium import webdriver
from webdriver_manager.opera import OperaDriverManager
driver = webdriver.Opera(executable_path=OperaDriverManager().install())

# Opera on Windows
from selenium import webdriver
from webdriver_manager.opera import OperaDriverManager

options = webdriver.ChromeOptions()
options.add_argument('allow-elevated-browser')
options.binary_location = "C:\\Users\\USERNAME\\FOLDERLOCATION\\Opera\\VERSION\\opera.exe"
driver = webdriver.Opera(executable_path=OperaDriverManager().install(), options=options)

# Internet Explorer
from selenium import webdriver
from webdriver_manager.microsoft import IEDriverManager
driver = webdriver.Ie(IEDriverManager().install())

# See which directories are already on PATH
echo %PATH%

# Add the driver directory to PATH
setx PATH "%PATH%;C:\WebDriver\bin"

# Test that it was added correctly
chromedriver.exe

echo 'export PATH=$PATH:/path/to/driver' >> ~/.bash_profile
source ~/.bash_profile

# Download chromedriver first, then specify the path directly
service = Service(executable_path="/path/to/chromedriver")
driver = webdriver.Chrome(service=service)

# Basic example

from selenium import webdriver
from time import sleep

# 1. Instantiate a browser object
bro = webdriver.Chrome(executable_path='./chromedriver.exe')
# 2. Navigate to a URL
bro.get('https://www.jd.com/')
# 3. Locate an element
text_input = bro.find_element_by_xpath('//*[@id="key"]')
# 4. Type text into the element
text_input.send_keys('iphone 12')
sleep(1)
btn = bro.find_element_by_xpath('//*[@id="search"]/div/div[2]/button')
btn.click()
sleep(1)
# 5. Execute JavaScript to scroll to the bottom of the page
bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(2)
bro.find_element_by_xpath('//*[@id="J_bottomPage"]/span[1]/a[7]').click()
sleep(3)
# Close the browser
bro.quit()

import time

from selenium import webdriver  # Controls the browser
from selenium.webdriver import ActionChains   # Mouse operations (e.g., slider verification)
from selenium.webdriver.common.by import By   # Element locator strategies
from selenium.webdriver.common.keys import Keys   # Keyboard key constants
from selenium.webdriver.support import expected_conditions as EC  # Conditions for waits
from selenium.webdriver.support.wait import WebDriverWait  # Explicit wait
from webdriver_manager.chrome import ChromeDriverManager

# Load Chrome driver
driver = webdriver.Chrome(ChromeDriverManager().install())

# Navigate to a URL
driver.get("https://www.baidu.com")

# Maximize the browser window
driver.maximize_window()
print("Current URL: %s" % driver.current_url)
print("Page title: %s" % driver.title)
print("Browser name: %s" % driver.name)
print(driver.current_window_handle)  # Get the current window handle
print(driver.get_cookies())   # Get all cookies
print(driver.page_source)   # Get the full page HTML source

time.sleep(5)
driver.close()	# Close the current tab
driver.quit()	# Close the entire browser

from selenium import webdriver   # Controls the browser
from selenium.webdriver.support.wait import WebDriverWait  # Explicit wait
from webdriver_manager.chrome import ChromeDriverManager
driver = webdriver.Chrome(ChromeDriverManager().install())

wait = WebDriverWait(driver, 10)

driver.get('https://www.baidu.com')
driver.find_element_by_id('su')  # ID selector
driver.find_element_by_class_name('xx')  # Class selector, single element
driver.find_elements_by_class_name('xx')  # Class selector, multiple elements
driver.find_element_by_link_text('xxx')  # Link text selector
driver.find_element_by_xpath('xxxx')  # XPath selector
driver.find_element_by_tag_name('h1')  # Tag name selector, single element
driver.find_elements_by_tag_name('h1')  # Tag name selector, multiple elements
driver.find_element_by_css_selector('xxx')  # CSS selector

java -jar selenium-server-<version>.jar standalone

# Start Hub
java -jar selenium-server-<version>.jar hub

# Start Node 1
java -jar selenium-server-<version>.jar node --port 5555

# Start Node 2
java -jar selenium-server-<version>.jar node --port 6666

docker run -d --name myhub -p 5555:4444 selenium/hub

docker run -d --name node -p 5902:5900 --link myhub:hub selenium/node-chrome-debug

docker run -d --name node1 -p 5901:5900 --link myhub:hub selenium/node-firefox-debug

# 1. Deploy Hub
docker run -d --name tencent-sgp-hub -p 4442-4444:4442-4444  selenium/hub

# 2. Deploy Chrome Node
docker run -d \
  --name tencent-sgp-selenium-chrome \
  -p 5900:5900 \
  -e SE_EVENT_BUS_HOST=172.17.0.2 \
  -e SE_EVENT_BUS_PUBLISH_PORT=4442 \
  -e SE_EVENT_BUS_SUBSCRIBE_PORT=4443 \
  -v /dev/shm:/dev/shm \
  --shm-size="2g" \
  selenium/node-chrome

# Parameter explanation:
#   -d: Run container in detached (background) mode
#   --name: Assign a name to the container
#   -p 5900:5900: Map host port 5900 to container port 5900 (VNC)
#   -e SE_EVENT_BUS_HOST: Event bus host address (points to Hub IP)
#   -e SE_EVENT_BUS_PUBLISH_PORT=4442: Event bus publish port (matches Hub config)
#   -e SE_EVENT_BUS_SUBSCRIBE_PORT=4443: Event bus subscribe port (matches Hub config)
#   -e SE_NODE_MAX_SESSIONS=5: Limit max sessions per node
#   -v /dev/shm:/dev/shm: Mount shared memory volume (prevents browser OOM)
#   --shm-size="2g": Set container shared memory to 2 GB (required by Chrome/Firefox)
#   --restart unless-stopped: Restart policy (restarts automatically unless manually stopped)

# Capture dynamically loaded data
from lxml import etree

bro = webdriver.Chrome(executable_path='./chromedriver.exe')
bro.get('http://scxk.nmpa.gov.cn:81/xk/')
sleep(1)
# page_source returns the full page source including dynamically loaded content
page_text = bro.page_source
page_text_list = [page_text]  # Store the first 5 pages of source HTML

for i in range(5):
    bro.find_element_by_xpath('//*[@id="pageIto_next"]').click()
    sleep(1)
    page_text_list.append(bro.page_source)

for page_text in page_text_list:
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//*[@id="gzlist"]/li')
    for li in li_list:
        title = li.xpath('./dl/@title')[0]
        print(title)
bro.quit()

from selenium.webdriver import ActionChains

bro = webdriver.Chrome(executable_path='./chromedriver.exe')
bro.get('https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
sleep(1)
bro.switch_to.frame('iframeResult')
div_tag = bro.find_element_by_xpath('//*[@id="draggable"]')

# 1. Instantiate an action chain and associate it with the current browser
action = ActionChains(bro)
# 2. Define the actions
action.click_and_hold(div_tag)  # Click and hold
for i in range(5):
    action.move_by_offset(7, 5).perform()  # perform() executes the action chain immediately
    sleep(0.5)
sleep(2)
bro.quit()

browser = webdriver.Chrome(executable_path='./chromedriver.exe')
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())

from selenium.webdriver.chrome.options import Options
# Create an options object to run Chrome in headless mode
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')

browser = webdriver.Chrome(executable_path='./chromedriver.exe', chrome_options=chrome_options)
browser.get('https://www.zhihu.com/explore')
print(browser.page_source)
browser.save_screenshot('./zhihu.jpg')  # Take a screenshot
browser.quit()

#!/usr/bin/env python
# coding:utf-8

import requests
from hashlib import md5

class Chaojiying_Client(object):

    def __init__(self, username, password, soft_id):
        self.username = username
        password =  password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }

    def PostPic(self, im, codetype):
        """
        im: image bytes
        codetype: CAPTCHA type, see http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
        return r.json()

    def ReportError(self, im_id):
        """
        im_id: image ID of the incorrectly solved CAPTCHA
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()

# Function that calls the CAPTCHA-solving API
def getCode_text(imgPath, imgType):
    chaojiying = Chaojiying_Client('227851369', '123456', '	911685')
    im = open(imgPath, 'rb').read()
    return chaojiying.PostPic(im, imgType)['pic_str']


from selenium import webdriver
from time import sleep
from selenium.webdriver import ActionChains
# pip install PIL (Pillow)
from PIL import Image

# Crop the CAPTCHA image — ensure your OS display scaling is set to 100%

bro = webdriver.Chrome(executable_path='./chromedriver.exe')
bro.get('https://kyfw.12306.cn/otn/login/init')
sleep(1)
# Take a screenshot of the full page
bro.save_screenshot('main.png')
# Get the CAPTCHA image element and its position/size
img_tag = bro.find_element_by_xpath('//*[@id="loginForm"]/div/ul[2]/li[4]/div/div/div[3]/img')
# Top-left corner coordinates
location = img_tag.location
# CAPTCHA image dimensions
size = img_tag.size
# Define the crop region
rangle = (int(location['x']), int(location['y']), int(location['x']+size['width']), int(location['y']+size['height']))
i = Image.open('./main.png')
frame = i.crop(rangle)  # Crop to the defined region
frame.save('code.png')

# Solve the CAPTCHA and get click coordinates
result = getCode_text('code.png', 9004)
print(result)  # Format: x1,y1|x2,y2|x3,y3
# Parse result into [[x1,y1],[x2,y2]]
all_list = []
if '|' in result:
    list_1 = result.split('|')
    count_1 = len(list_1)
    for i in range(count_1):
        xy_list = []
        x = int(list_1[i].split(',')[0])
        y = int(list_1[i].split(',')[1])
        xy_list.append(x)
        xy_list.append(y)
        all_list.append(xy_list)
else:
    x = int(result.split(',')[0])
    y = int(result.split(',')[1])
    xy_list = []
    xy_list.append(x)
    xy_list.append(y)
    all_list.append(xy_list)

for loc in all_list:
    x = loc[0]
    y = loc[1]
    ActionChains(bro).move_to_element_with_offset(img_tag, x, y).click().perform()
    sleep(1)
bro.find_element_by_id('username').send_keys('1234567890')
sleep(1)
bro.find_element_by_id('password').send_keys('0000000000')
sleep(1)

bro.find_element_by_id('loginSub').click()
sleep(3)
bro.quit()