selenium详解

Posted on

Selenium

基本使用

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
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:
    # 用chrome发出get请求
    browser.get('https://www.baidu.com')
    # 找到id为kw的元素
    input = browser.find_element_by_id('kw')
    # 输入Python
    input.send_keys('Python')
    # 调用ENTER
    input.send_keys(Keys.ENTER)
    # 等待
    wait = WebDriverWait(browser, 10)
    # 直到ID为 content_left 元素出现
    wait.until(EC.presence_of_element_located((By.ID, 'content_left')))
    # URL地址
    print(browser.current_url)
    # COOKIES	
    print(browser.get_cookies())
    # 源代码
    print(browser.page_source)
finally:
    # 关闭此浏览器
    browser.close()

声明浏览器对象

1
2
3
4
5
6
7
from selenium import webdriver

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

访问页面

1
2
3
4
5
6
from selenium import webdriver

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

查找元素

单个元素

1
2
3
4
5
6
7
8
9
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()
  • 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_element_by_css_selector
1
2
3
4
5
6
7
8
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()
  • 通过browser.find_element加上from selenium.webdriver.common.by import By

多个元素

1
2
3
4
5
6
7
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()

把element加上复数形式

  • 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_elements_by_css_selector
1
2
3
4
5
6
7
8
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()

元素交互操作

对获取的元素调用交互方法

1
2
3
4
5
6
7
8
9
10
11
12
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()

更多操作: http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.remote.webelement

交互动作

1
2
3
4
5
6
7
8
9
10
11
12
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()

更多操作: http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.action_chains>

执行JavaScript

1
2
3
4
5
6
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

1
2
3
4
5
6
7
8
9
from selenium import webdriver
from selenium.webdriver 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'))

获取文本值

1
2
3
4
5
6
7
from selenium import webdriver

browser = webdriver.Chrome()
url = 'https://www.zhihu.com/explore'
browser.get(url)
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.text)

获取ID、位置、标签名、大小

1
2
3
4
5
6
7
8
9
10
from selenium import webdriver

browser = webdriver.Chrome()
url = 'https://www.zhihu.com/explore'
browser.get(url)
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

Frame相当于一个网页，父Frame必须进入子Frame然后才能查找子Frame中的元素，子Frame中也不能获取父Frame中的元素

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
import time
from selenium import webdriver
from selenium.common.exceptions 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')
# swith_to.frame()传入frame的id
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()
#swith_to.parent_frame()切换到父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，超出设定时间后则抛出找不到元素的异常, 换句话说，当查找元素或元素并没有立即出现的时候，隐式等待将等待一段时间再查找 DOM，默认的时间是0

1
2
3
4
5
6
7
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)

显式等待

1
2
3
4
5
6
7
8
9
10
11
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)

  • 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，传入定位元组，如(By.ID, ‘p’)

  • visibility_of_element_located 元素可见，传入定位元组

  • visibility_of 可见，传入元素对象

  • 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_available_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，传入定位元组

  • 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

  • alert_is_present 是否出现Alert

前进后退

1
2
3
4
5
6
7
8
9
10
11
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(1)
browser.forward()
browser.close()

Cookies

设置登陆状态

1
2
3
4
5
6
7
8
9
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())

选项卡管理

1
2
3
4
5
6
7
8
9
10
11
12
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(1)
browser.switch_to_window(browser.window_handles[0])
browser.get('https://python.org')

异常处理

1
2
3
4
5
from selenium import webdriver
#异常处理
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.find_element_by_id('hello')

加入异常处理

1
2
3
4
5
6
7
8
9
10
11
12
13
14
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()