Selenium库介绍

• 介绍

1. 驱动浏览器，模拟人的上网场景
2. 解决js渲染的问题

• 安装

pip3 install selenium

• 用法详解

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

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

try:
    browser.get('https://www.baidu.com')
    input = browser.find_element_by_id('kw')
    input.send_keys('Python')
    input.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)
finally:
    browser.close()

2. 查找元素

## 单个元素
from selenium import webdriver

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
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()

from selenium import webdriver
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
browser.get('https://www.taobao.com')
input_first = browser.find_element(By.ID, 'q')
print(input_first)
browser.close()

• find_element_by_name
• find_element_by_xpath
• find_element_by_link_text
• find_element_by_partial_link_text
• find_element_by_class_name
• find_element_by_css_selector

## 多个元素
from selenium import webdriver
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
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

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
browser.get('https://www.taobao.com')
lis = browser.find_elements(By.CSS_SELECTOR, '.service-bd li')
print(lis)
browser.close()

3. 元素交互操作

import time

from selenium import webdriver
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
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()

4. 交互动作

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
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()

5. 执行JavaScript

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
browser.get('https://www.zhihu.com/explore')
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
browser.execute_script('alter("To Bottom")')

6.获取元素信息

## 获取属性
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)
url = 'https://www.zhihu.com/explore'
browser.get(url)
logo = browser.find_element_by_id('Popover1-toggle')
print(logo)
print(logo.get_attribute('class'))
## 获取文本值
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

url = 'https://www.zhihu.com/explore'
browser.get(url)
input = browser.find_element_by_class_name('Entry-body')
print(input.text)
## 获取ID、位置、标签值、大小
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

url = 'https://www.zhihu.com/explore'
browser.get(url)
input = browser.find_element_by_class_name('Entry-body')
print(input.id)
print(input.location)
print(input.tag_name)
print(input.size)
## Frame
import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

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')
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)

7.等待

## 隐式等待
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

browser.implicitly_wait(10)
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('Entry-body')
print(input)

## 显式等待
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

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)

8. 前进后退

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

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()

9.Cookies

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

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())

10.选项卡管理

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

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://zhihu.com')

11.异常处理

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException, TimeoutException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

chrome_driver = r"C:\python36\chromedriver.exe"
browser = webdriver.Chrome(executable_path=chrome_driver)

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()