selenium 使用

官方文档 http://selenium-python.readthedocs.io/

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

browser = webdriver.Chrome()

try:
    browser.get('https://www.baidu.com')
    inp = browser.find_element_by_id('kw')

    inp.send_keys('Python')

    inp.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)

except:
    pass

finally:
    browser.close()

声明浏览器对象

from selenium import webdriver 

browser = webdriver.Chrome() 
browser = webdriver.Firefox() 
browser = webdriver.Edge() 
browser = webdriver.PhantomJS() 
browser = webdriver.Safari() 

访问页面

browser = webdriver.Chrome() 
browser.get('https://www.taobao.ocm')
print(browser.page_source)
browser.close() 

查找元素

查找单个元素

browser.get('https://www.taobao.com')
inp_frist = browser.find_element_by_id('q')
inp_second = browser.find_element_by_css_selector('#q')
inp_thrid = browser.find_element_by_xpath('//*[@id="q"]')
print(inp_frist, inp_second, inp_thrid)
browser.close()

• find_element_by_name
• find_element_by_xpath
• find_element_by_link_text
• find_element_by_partial_link_text
• find_element_by_tag_name
• find_element_by_class_name
• find_emement_by_css_selector

inp = browser.find_element(By.ID, 'q')

多个元素

lis = browser.find_elements_by_css_selector('.service-bd li')

• find_elements_by_name
• find_elements_by_xpath
• find_elements_by_link_text
• find_elements_by_partial_link_text
• find_elements_by_tag_name
• find_elements_by_class_name
• find_emements_by_css_selector

元素交互操作

对获取到的元素调用交互方法

inp = browser.find_element_by_id('q')
inp.send_keys('iPhone')
time.sleep(1)
inp.clear() 
inp.send_keys('iPad')
button = browser.find_element_by_class_name('btn-search')
button.click() 

交互动作

将动作附加到动作链中串行执行

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)
# 切换到 iframe  
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()  

执行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")')

获取元素信息

获取属性

from selenium import webdriver 
from selenium import ActionChains 

browser = webdriver.Chrome() 
url = 'https://www.zhihu.com/explore'
browser.get(url)
logo = browser.find_element_by_id('zh-top-link-logo')
print(logo)
print(logo.get_attribute('class'))

获取文本， ID, 位置， 标签名， 大小

browser.get(url)
inp = browser.find_element_by_class_name('zu-top-add-question')
print(inp.text)
print(inp.id)
print(inp.location)
print(inp.tag_name)
print(inp.size)

Frame

import time 
from selenium import webdriver 
from selenium.common import NoSuchElementException 

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_class_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)

等待

隐式等待

当使用了隐式等待执行测试的时候，如果WebDriver没有在DOM中找到元素，将继续等待，超出设定时间后抛出找不到元素的异常，换句话说，当查找元素或元素没有立即出现的
时候，隐式等待将等待一段时间再查找DOM，默认的时间0

from selenium import webdriver

browser = webdriver.Chrome() 
browser.implicitly_wait(10)
browser.get('https://www.zhihu.com/explore')
inp = browser.find_element_by_class_name('zu-top-add-question')
print(inp)

显式等待

from selenium import webdriver 
from selenium.webdriver.common.by import By 
from selenium.webdriver.support.ui import WebDriverWait 
from selenium.webdriver.support expected_conditions as ec 

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

• title_is 标题是某内容
• title_contains 标题包含某内容
• presence_of_element_located 元素加载出，传入定位元素，如(By.ID, 'p')
• visibility_of_element_lcoated 元素可见，传入定位元素
• visibility_of 可见，出入元素对象
• presence_of_all_elements_located 所有元素加载出
• text_to_be_present_in_element 某个元素文本包含某文字
• text_to_be_present_in_element_value 某个元素值包含某文字
• frame_to_be_avaliable_and_switch_to_it_frame 加载并切换
• invisibility_of_element_located 元素不可见
• element_to_be_clickable 元素可点击
• staleness_of 判断一个元素是否仍在DOM，可判断页面是否已经刷新
• element_to_be_selected 元素可选择，传元素对象
• element_located_to_be_selected 元素可选择，传入定位元祖
• element_selection_state_to_be 传入元素对象以及状态，相等返回True，否则返回False
• element_located_selection_state_to_be 传入定位元组以及状态，相等返回True，否则返回False
• element_located_selection_state_to_be 传入定位元组以及状态，相等返回True，否则返回False
• alert_is_present 是否出现Alert

前进后退

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() 
browser.forward()
browser.close() 

Cookies

browser.get_cookies() 
browser.add_cookie({'name':'y', 'domain': 'www.zhihu.com', 'value': 'g'})
browser.delete_all_cookies()

选项卡管理

browser.get('https://www.baidu.com')
browser.execute_script('window.open()')
print(browser.window_handles) 
browser.get('https://www.taobao.com')
browser.switch_to_window(browser.window_handles[1])
browser.get('https://python.org')

异常处理

from selenium.common.exceptions import NoSuchElementException, TimeoutException