rikako-note/python/selenium.md

- [selenium](#selenium)
  - [Components](#components)
    - [Driver](#driver)
    - [WebDriver](#webdriver)
  - [Getting Started](#getting-started)
    - [安装](#安装)
    - [常用操作](#常用操作)
      - [开启浏览器会话](#开启浏览器会话)
      - [通过webdriver执行操作](#通过webdriver执行操作)
      - [请求浏览器信息](#请求浏览器信息)
      - [指定等待策略](#指定等待策略)
      - [获取页面上的元素](#获取页面上的元素)
      - [针对页面上的元素执行操作](#针对页面上的元素执行操作)
      - [访问元素上的信息](#访问元素上的信息)
      - [关闭会话](#关闭会话)
      - [提交表单样例](#提交表单样例)
  - [Driver](#driver-1)
    - [Browser Options](#browser-options)
      - [browserName](#browsername)
    - [Driver Service](#driver-service)
      - [使用默认service实例](#使用默认service实例)
      - [指定driver port](#指定driver-port)
    - [Remote Web Driver](#remote-web-driver)
  - [元素交互](#元素交互)
    - [文件上传](#文件上传)
    - [文件定位](#文件定位)
      - [在整个dom中进行查找](#在整个dom中进行查找)
      - [基于已定位的元素进行查找](#基于已定位的元素进行查找)
      - [css选择器](#css选择器)
      - [查找所有匹配的元素](#查找所有匹配的元素)
    - [同web元素进行交互](#同web元素进行交互)
      - [click](#click)
      - [send\_keys](#send_keys)
      - [clear](#clear)
    - [获取元素信息](#获取元素信息)
      - [is\_displayed](#is_displayed)
      - [is\_enabled](#is_enabled)
      - [is\_selected](#is_selected)
      - [tag\_name](#tag_name)
      - [元素位置和大小](#元素位置和大小)
      - [获取css的值](#获取css的值)
      - [获取文本内容](#获取文本内容)
      - [获取元素属性](#获取元素属性)
  - [浏览器交互](#浏览器交互)
    - [获取当前页签的title](#获取当前页签的title)
    - [获取当前url](#获取当前url)
    - [浏览器导航](#浏览器导航)
      - [跳转到页面](#跳转到页面)
      - [返回到上一个页签](#返回到上一个页签)
      - [forward](#forward)
      - [刷新当前页签](#刷新当前页签)
      - [alert](#alert)
      - [confirm](#confirm)
      - [prompt](#prompt)
    - [新增cookie](#新增cookie)
    - [iframe](#iframe)
    - [winodws/tab 交互](#winodwstab-交互)
      - [获取当前窗口句柄](#获取当前窗口句柄)
      - [切换窗口句柄](#切换窗口句柄)
      - [创建新窗口/tab](#创建新窗口tab)
      - [关闭tab](#关闭tab)
      - [关闭会话](#关闭会话-1)
      - [获取窗口大小](#获取窗口大小)
      - [设置窗口大小](#设置窗口大小)
      - [获取窗口位置](#获取窗口位置)
      - [设置窗口位置](#设置窗口位置)
      - [最大化窗口](#最大化窗口)
      - [最小化窗口](#最小化窗口)
      - [全屏窗口](#全屏窗口)
      - [截屏](#截屏)
      - [为元素截屏](#为元素截屏)
      - [执行js脚本](#执行js脚本)
      - [打印页面](#打印页面)


# selenium
## Components
### Driver
Driver负责控制实际的浏览器，大多数driver是由浏览器供应商提供的。

### WebDriver
WebDriver通过Driver和浏览器通信，通过driver， webDriver将命令发送给浏览器，并且通过driver收到浏览器的返回信息。

> Drvier和浏览器运行在同一个操作系统上，WebDriver和`drvier&浏览器`可能并不运行在同一系统上。WebDriver会远程调用driver，driver再调用处于同一系统的浏览器。

## Getting Started
### 安装
```bash
pip install selenium
```
### 常用操作
#### 开启浏览器会话
```py
driver = webdriver.Chrome()
```
#### 通过webdriver执行操作
```py
driver.get("https://www.selenium.dev/selenium/web/web-form.html")
```

#### 请求浏览器信息
```py
# driver.title代表浏览器当前页签的标题
title = driver.title
```

#### 指定等待策略
再获取元素之前，需要确保元素存在于当前页面上，并且与元素进行交互时，必须确保当前元素是可交互的（页签加载需要时间）。

此时，可以通过自定义等待时间来解决。
```py
driver.implicitly_wait(0.5)
```

#### 获取页面上的元素
```py
text_box = driver.find_element(by=By.NAME, value="my-text")
submit_button = driver.find_element(by=By.CSS_SELECTOR, value="button")
```

#### 针对页面上的元素执行操作
```py
text_box.send_keys("Selenium")
submit_button.click()
```

#### 访问元素上的信息
```py
text = message.text
```

#### 关闭会话
```py
driver.quit()
```

#### 提交表单样例
```py
from selenium import webdriver
from selenium.webdriver.common.by import By


def test_eight_components():
    driver = webdriver.Chrome()

    driver.get("https://www.selenium.dev/selenium/web/web-form.html")

    title = driver.title
    assert title == "Web form"

    driver.implicitly_wait(0.5)

    text_box = driver.find_element(by=By.NAME, value="my-text")
    submit_button = driver.find_element(by=By.CSS_SELECTOR, value="button")

    text_box.send_keys("Selenium")
    submit_button.click()

    message = driver.find_element(by=By.ID, value="message")
    value = message.text
    assert value == "Received!"

    driver.quit()
```
## Driver
开启和关闭session代表着开启和关闭浏览器。

### Browser Options
对于remote driver sessions，需要为其指定options对象，指定的options对象将会决定使用远程的哪个浏览器。

每个浏览器都会有其独属的额外选项，可以为每个浏览器额外指定。

#### browserName
当使用options对象时，browserName选项会被默认指定：

### Driver Service
Service用于管理local driver的启动和停止，service无法被用于remote webdriver session。

service允许指定driver的信息，例如driver位置和使用的端口号，也可以通过service指定日志信息。

#### 使用默认service实例
```py
service = webdriver.ChromeService()
driver = webdriver.Chrome(service=service)
```

#### 指定driver port
如果想要driver运行在指定的端口，可以通过service进行指定。
```py
service = webdriver.ChromeService(port=1234)
```

### Remote Web Driver
Selenium允许调用位于远程机器上的浏览器，需要远程机器上安装Selenium Grid。
```py
options = webdriver.ChromeOptions()
driver = webdriver.Remote(command_executor=server, options=options)
```

## 元素交互
### 文件上传
通过元素的`send_keys`方法，支持支持文件上传。
```py
file_input = driver.find_element(By.CSS_SELECTOR, "input[type='file']")
file_input.send_keys(upload_file)
driver.find_element(By.ID, "file-submit").click()
```

### 文件定位
#### 在整个dom中进行查找
可以通过调用`driver.find_element`来在整个dom中对元素进行查找，其会返回匹配的第一个元素
```py
vegetable = driver.find_element(By.CLASS_NAME, "tomatoes")
```
#### 基于已定位的元素进行查找
如果想要在已经定位元素的子节点中进行查找，可以调用如下方法：
```py
fruits = driver.find_element(By.ID, "fruits")
fruit = fruits.find_element(By.CLASS_NAME,"tomatoes")
```
#### css选择器
selenium支持通过css选择器的语法来进行查找：
```py
fruit = driver.find_element(By.CSS_SELECTOR,"#fruits .tomatoes")
```
#### 查找所有匹配的元素
可以通过`find_elements`方法来获取所有匹配的元素，而不是第一个匹配的元素
```py
plants = driver.find_elements(By.TAG_NAME, "li")
```

### 同web元素进行交互
可以针对元素指定如下类型的交互
- click（可使用任何元素）
- send_keys（只针对文本输入框或内容可编辑的元素）
- clear（只针对文本输入框或内容可编辑的元素）
- submit(只针对表单元素)
- select（只针对下拉框类型元素）

#### click
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Click on the element 
driver.find_element(By.NAME, "color_input").click()
```
#### send_keys
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Clear field to empty it from any previous data
driver.find_element(By.NAME, "email_input").clear()

# Enter Text
driver.find_element(By.NAME, "email_input").send_keys("admin@localhost.dev" )
```
#### clear
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Clear field to empty it from any previous data
driver.find_element(By.NAME, "email_input").clear()
```
### 获取元素信息
#### is_displayed
```py
# Navigate to the url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Get boolean value for is element display
is_email_visible = driver.find_element(By.NAME, "email_input").is_displayed()
```
#### is_enabled
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Returns true if element is enabled else returns false
value = driver.find_element(By.NAME, 'button_input').is_enabled()
```
#### is_selected
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Returns true if element is checked else returns false
value = driver.find_element(By.NAME, "checkbox_input").is_selected()
```
#### tag_name
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Returns TagName of the element
attr = driver.find_element(By.NAME, "email_input").tag_name
```
#### 元素位置和大小
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Returns height, width, x and y coordinates referenced element
res = driver.find_element(By.NAME, "range_input").rect
```
#### 获取css的值
```py
# Navigate to Url
driver.get('https://www.selenium.dev/selenium/web/colorPage.html')

# Retrieves the computed style property 'color' of linktext
cssValue = driver.find_element(By.ID, "namedColor").value_of_css_property('background-color')
```
#### 获取文本内容
```py
# Navigate to url
driver.get("https://www.selenium.dev/selenium/web/linked_image.html")

# Retrieves the text of the element
text = driver.find_element(By.ID, "justanotherlink").text
```
#### 获取元素属性
```py
# Navigate to the url
driver.get("https://www.selenium.dev/selenium/web/inputs.html")

# Identify the email text box
email_txt = driver.find_element(By.NAME, "email_input")

# Fetch the value property associated with the textbox
value_info = email_txt.get_attribute("value")
```
## 浏览器交互
### 获取当前页签的title
```py
String title = driver.getTitle();
```
### 获取当前url
```py
String url = driver.getCurrentUrl();
```
### 浏览器导航
#### 跳转到页面
```py
driver.get("https://www.selenium.dev/selenium/web/index.html")
```
#### 返回到上一个页签
```py
driver.back()
```
#### forward
```py
driver.forward()
```
#### 刷新当前页签
```py
driver.refresh()
```
#### alert
```py
element = driver.find_element(By.LINK_TEXT, "See an example alert")
element.click()

wait = WebDriverWait(driver, timeout=2)
alert = wait.until(lambda d : d.switch_to.alert)
text = alert.text
# 接受alert
alert.accept()
```
#### confirm
```py
element = driver.find_element(By.LINK_TEXT, "See a sample confirm")
driver.execute_script("arguments[0].click();", element)

wait = WebDriverWait(driver, timeout=2)
alert = wait.until(lambda d : d.switch_to.alert)
text = alert.text
alert.dismiss()
```
#### prompt
```py
element = driver.find_element(By.LINK_TEXT, "See a sample prompt")
driver.execute_script("arguments[0].click();", element)

wait = WebDriverWait(driver, timeout=2)
alert = wait.until(lambda d : d.switch_to.alert)
alert.send_keys("Selenium")
text = alert.text
alert.accept()
```
### 新增cookie
```py
from selenium import webdriver

driver = webdriver.Chrome()

driver.get("http://www.example.com")

# Adds the cookie into current browser context
driver.add_cookie({"name": "key", "value": "value"})
```
### iframe
想要与iframe中的内容进行交互，需要先移动到iframe区域
```py
    # Store iframe web element
iframe = driver.find_element(By.CSS_SELECTOR, "#modal > iframe")

    # switch to selected iframe
driver.switch_to.frame(iframe)

    # Now click on button
driver.find_element(By.TAG_NAME, 'button').click()
```
### winodws/tab 交互
#### 获取当前窗口句柄
```py
driver.current_window_handle
```
#### 切换窗口句柄
可以通过`driver.switch_to.window(windows_handle)`来进行切换页签
```py
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

with webdriver.Firefox() as driver:
    # Open URL
    driver.get("https://seleniumhq.github.io")

    # Setup wait for later
    wait = WebDriverWait(driver, 10)

    # Store the ID of the original window
    original_window = driver.current_window_handle

    # Check we don't have other windows open already
    assert len(driver.window_handles) == 1

    # Click the link which opens in a new window
    driver.find_element(By.LINK_TEXT, "new window").click()

    # Wait for the new window or tab
    wait.until(EC.number_of_windows_to_be(2))

    # Loop through until we find a new window handle
    for window_handle in driver.window_handles:
        if window_handle != original_window:
            driver.switch_to.window(window_handle)
            break

    # Wait for the new tab to finish loading content
    wait.until(EC.title_is("SeleniumHQ Browser Automation"))
```
#### 创建新窗口/tab
```py
    # Opens a new tab and switches to new tab
driver.switch_to.new_window('tab')

    # Opens a new window and switches to new window
driver.switch_to.new_window('window')
```
#### 关闭tab
调用`driver.close`会关闭当前的页签
```py
    #Close the tab or window
driver.close()

    #Switch back to the old tab or window
driver.switch_to.window(original_window)
```

#### 关闭会话
当不再使用浏览器会话后，应该调用`driver.quit()`方法。

如果未调用该方法或是调用该方法失败，将会导致driver进程和端口号一直不被释放。


#### 获取窗口大小
```py
    # Access each dimension individually
width = driver.get_window_size().get("width")
height = driver.get_window_size().get("height")

    # Or store the dimensions and query them later
size = driver.get_window_size()
width1 = size.get("width")
height1 = size.get("height")
```
#### 设置窗口大小
```py
driver.set_window_size(1024, 768)
```

#### 获取窗口位置
```py
    # Access each dimension individually
x = driver.get_window_position().get('x')
y = driver.get_window_position().get('y')

    # Or store the dimensions and query them later
position = driver.get_window_position()
x1 = position.get('x')
y1 = position.get('y')
```

#### 设置窗口位置
```py
    # Move the window to the top left of the primary monitor
driver.set_window_position(0, 0)
```
#### 最大化窗口
```py
driver.maximize_window()
```

#### 最小化窗口
```py
driver.minimize_window()
```

#### 全屏窗口
```py
driver.fullscreen_window()
```
#### 截屏
```py
from selenium import webdriver

driver = webdriver.Chrome()

driver.get("http://www.example.com")

    # Returns and base64 encoded string into image
driver.save_screenshot('./image.png')

driver.quit()
```

#### 为元素截屏
```py
from selenium import webdriver
from selenium.webdriver.common.by import By

driver = webdriver.Chrome()

driver.get("http://www.example.com")

ele = driver.find_element(By.CSS_SELECTOR, 'h1')

    # Returns and base64 encoded string into image
ele.screenshot('./image.png')

driver.quit()
```
#### 执行js脚本
```py
    # Stores the header element
header = driver.find_element(By.CSS_SELECTOR, "h1")

    # Executing JavaScript to capture innerText of header element
driver.execute_script('return arguments[0].innerText', header)
```
#### 打印页面
```py
    from selenium.webdriver.common.print_page_options import PrintOptions

    print_options = PrintOptions()
    print_options.page_ranges = ['1-2']

    driver.get("printPage.html")

    base64code = driver.print_page(print_options)
```