Selenium库的基本使用
1.基本使用
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 brower = webdriver.Chrome() try: brower.get('https://www.baidu.com') input = brower.find_element_by_id('kw')#查找id为kw的元素 input.send_keys('Python')#向input文本框输入python input.send_keys(Keys.ENTER)#输入回车 wait = WebDriverWait(brower,10)#等待浏览器加载 wait.until(EC.presence_of_element_located((By.ID,'content_left')))#查找id为content——left的对象 print(brower.current_url)#输出当前的url print(brower.get_cookies())#输出当前的cookies print(brower.page_source)#输出当前的网页源码 finally: brower.close()
2.声明浏览器对象
from selenium import webdriver brower = webdriver.Chrome() brower = webdriver.Firefox() brower = webdriver.Edge() brower = webdriver.PhanromJS() brower = webdriver.Safari()
3.访问页面
from selenium import webdriver brower = webdriver.Chrome() brower.get('https://ww.taobao.com') print(brower.page_source) brower.colse()
4.查找元素
单个元素
from selenium import webdriver browser = webdriver.Chrome() browser.get('https://www.taobao.com') 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,input_second,input_third) browser.close()
结果:
<selenium.webdriver.remote.webelement.WebElement (session="aafcd8308ef345a4014a0db417267640", element="0.8704970628206692-1")> <selenium.webdriver.remote.webelement.WebElement (session="aafcd8308ef345a4014a0db417267640", element="0.8704970628206692-1")> <selenium.webdriver.remote.webelement.WebElement (session="aafcd8308ef345a4014a0db417267640", element="0.8704970628206692-1")>
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()
结果:
<selenium.webdriver.remote.webelement.WebElement (session="ad3663f850d6c3fd81751c5c8cf45511", element="0.6365953152365587-1")>
多个元素
from selenium import webdriver browser = webdriver.Chrome() browser.get('https://www.taobao.com') list=browser.find_elements_by_css_selector('.service-bd li') print(list) browser.close() from selenium import webdriver browser = webdriver.Chrome() browser.get('https://www.taobao.com') list=browser.find_elements(By.CSS_SELECTOR,'.service-bd li') print(list) browser.close()
5.元素交互操作
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('iPhone') time.sleep(1) input.clear() input.send_keys('iPad') button = browser.find_element_by_class_name('btn-search') button.click()
6.交互动作
from selenium import webdriver from selenium.webdriver import ActionChains brower=webdriver.Chrome() url="https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable" brower.get(url) brower.switch_to.frame('iframeResult') source=brower.find_element_by_css_selector('#draggable') target=brower.find_element_by_css_selector('#droppable') action=ActionChains(brower) action.drag_and_drop(source,target) action.perform()
7.执行JavaScript
from selenium import webdriver brower = webdriver.Chrome() brower.get('https://www.zhihu.com/explore') brower.execute_script('window.scrollTo(0,document.body.scrollHeight)') brower.execute_script('alert("To Bottom")')
8.获取属性
from selenium import webdriver from selenium.webdriver import ActionChains brower = webdriver.Chrome() url='https://www.zhihu.com/explore' brower.get(url) logo = brower.find_element_by_id('zh-top-link-logo') print(logo) print(logo.get_attribute('class'))
获取:
<selenium.webdriver.remote.webelement.WebElement (session="5578b6070e5cd404d5636c6c15d1062e", element="0.2337143497044789-1")> zu-top-link-logo
9.获取文本值
from selenium import webdriver brower = webdriver.Chrome() url='https://www.zhihu.com/explore' brower.get(url) input=brower.find_element_by_class_name('zu-top-add-question') print(input.text)
结果:
提问
10.获取ID,位置,标签名,大小
from selenium import webdriver brower = webdriver.Chrome() url='https://www.zhihu.com/explore' brower.get(url) input=brower.find_element_by_class_name('zu-top-add-question') print(input.id) print(input.location) print(input.tag_name) print(input.size)
结果:
0.5790966028649505-1 {'x': 760, 'y': 7} button {'height': 32, 'width': 66}
11.Frame
import time from selenium import webdriver from selenium.common.exceptions import NoSuchElementException brower = webdriver.Chrome() url="https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable" brower.get(url) brower.switch_to.frame('iframeResult') source=brower.find_element_by_css_selector('#draggable') print(source) try: logo=brower.find_element_by_class_name('logo') except NoSuchElementException: print('No Logo') brower.switch_to.parent_frame() logo=brower.find_element_by_class_name('logo') print(logo) print(logo.text) 结果: <selenium.webdriver.remote.webelement.WebElement (session="4515a548a628f32ec7ebb86b845cafbc", element="0.47138378750440957-1")> No Logo <selenium.webdriver.remote.webelement.WebElement (session="4515a548a628f32ec7ebb86b845cafbc", element="0.590628320406164-2")> RUNOOB.COM
12.隐式等待
from selenium import webdriver brower = webdriver.Chrome() brower.get('https://www.zhihu.com/explore') brower.implicitly_wait(10) input=brower.find_element_by_class_name('zu-top-add-question') print(input) 结果: <selenium.webdriver.remote.webelement.WebElement (session="df8f8bebb2cf5356c12442f1bcc5c2f7", element="0.40275892523916035-1")>
13.显示等待
from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait brower = webdriver.Chrome() brower.get('https://www.taobao.com') wait=WebDriverWait(brower,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) 结果: <selenium.webdriver.remote.webelement.WebElement (session="036c1bc8fad6ee8e9ee42266ce163be7", element="0.8588910449888032-1")> <selenium.webdriver.remote.webelement.WebElement (session="036c1bc8fad6ee8e9ee42266ce163be7", element="0.8588910449888032-2")>
14.前进后退
from selenium import webdriver import time brower = webdriver.Chrome() brower.get('https://www.baidu.com') brower.get('https://www.taobao.com') brower.get('https://www.python.org') brower.back() time.sleep(1) brower.forward() brower.close()
15.Cookies
from selenium import webdriver brower = webdriver.Chrome() brower.get('https://www.zhihu.com/explore') print(brower.get_cookies()) brower.add_cookie({'name':'name','domain':'www.zhihu.com','value':'germey'}) print(brower.get_cookies()) brower.delete_all_cookies() print(brower.get_cookies())
16.选项卡管理
import time from selenium import webdriver brower = webdriver.Chrome() brower.get('https://www.baidu.com') brower.execute_script('window.open()') print(brower.window_handles) brower.switch_to_window(brower.window_handles[1]) brower.get('https://www.taobao.com') time.sleep(1) brower.switch_to_window(brower.window_handles[0]) brower.get('https://www.python.org')
结果:
['CDwindow-4971CB8E7903DFAE9CBA82A6A5F05DB2', 'CDwindow-652D8829B41E67E7F7E8C2E146F8C353']
17.异常处理
from selenium import webdriver brower=webdriver.Chrome() brower.get('https://www.baidu.com') brower.find_element_by_id('hello')
from selenium import webdriver from selenium.common.exceptions import TimeoutException,NoSuchElementException brower=webdriver.Chrome() try: brower.get('https://www.baidu.com') except TimeoutException: print('Time Out') try: brower.find_element_by_id('hello') except NoSuchElementException: print('No Element') finally: brower.close() 结果: No Element