Selenium
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() # 声明浏览器对象
try:
browser.get('https://www.baidu.com')
input = browser.find_element_by_id('kw') # 找到id为kw的元素
input.send_keys('Python') # 敲入Python
input.send_keys(Keys.ENTER) # 敲入回车
wait = WebDriverWait(browser, 10)
wait.until(EC.presence_of_element_located((By.ID, 'content_left'))) # 等待某个元素加载出来
print(browser.current_url)
print(browser.get_cookies())
print(browser.page_source) # 网页源代码
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
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
element
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input_first = browser.find_element_by_id('q') # 寻找 id='q'的元素
input_second = browser.find_element_by_css_selector('#q') # 通过css选择器选择
input_third = browser.find_element_by_xpath('//*[@id="q"]') # 同上
print(input_first, input_second, input_third)
browser.close()
查找单个元素的方法
* 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
通用查找写法
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()
多个元素
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[0])
browser.close()
- 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
元素交互操作
- 先获取元素。
- 对获取的元素调用交互方法
from selenium import webdriver
import time
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input = browser.find_element_by_id('q') # 找到搜索框
input.send_keys('iPhone') # 输入 iPhone
time.sleep(1) # 等待一秒
input.clear() # 清空文本框
input.send_keys('iPad') # 输入ipad
button = browser.find_element(By.CLASS_NAME,'btn-search') # 找到搜索按钮
button.click() # 点击
browser.close()
更多操作: http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.remote.webelement
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() # 声明浏览器对象
url = 'http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable'
browser.get(url)
browser.switch_to.frame('iframeResult') #切换到‘iframeResult’框架
source = browser.find_element_by_css_selector('#draggable') # 选择元素
target = browser.find_element_by_css_selector('#droppable') # 选择元素
actions = ActionChains(browser) # 声明一个动作链对象
actions.drag_and_drop(source, target) # 拖拽方法
actions.perform() # 执行动作
更多操作: http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.action_chains
执行JavaScript
执行一些交互动作时,可能一些动作没有提供API。
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
* .get_attribute(“class”) *
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
* .text*
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
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
父级的frame要查找子级的frame必须要切换到子frame,否则不能查找。
同理子frame也不能查找父frame的元素。
import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
browser = webdriver.Chrome() # 声明浏览器对象
url = 'http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable' # 声明网址
browser.get(url) # get传入网址
browser.switch_to.frame('iframeResult') # 切换到子frame
source = browser.find_element_by_css_selector('#draggable') # 查找子frame中的元素
print(source)
try:
logo = browser.find_element_by_class_name('logo')
except NoSuchElementException:
print('NO LOGO')
browser.switch_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
from selenium import webdriver
browser = webdriver.Chrome()
browser.implicitly_wait(10) # 传入隐式等待的时间
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input)
显式等待
* .WebDriverWait(对象,最长等待时间)*
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) # 声明一个等待对象
# 判断元素是否加载
input = wait.until(EC.presence_of_element_located((By.ID, 'q'))) # 传入等待条件
# # 判断是否可点击的,一般用来判断是否为按钮
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
详细内容:http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.support.expected_conditions
前进后退
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
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
import time
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.execute_script('window.open()') # 通过执行一个js语句来新建选项卡
print(browser.window_handles) # 返回所有的选项卡的引用
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
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()
详细文档:http://selenium-python.readthedocs.io/api.html#module-selenium.common.exceptions