Python爬虫——Selenium库的基本使用

时间：2025-02-14 15:02:26

自动化测试工具，支持多种浏览器。

爬虫中主要用来解决JavaScript渲染的问题

基本使用

from selenium import webdriver
from  import By
from  import Keys
from  import expected_conditions as EC
from  import WebDriverWait

browser = ()#声明浏览器驱动对象
try:
    ('')
    input = browser.find_element_by_id('kw')#找出id为kw的元素
    input.send_keys('Python')#向元素发送键（输入Python）
    input.send_keys()#敲入回车
    wait = WebDriverWait(browser, 10)#等待某个元素加载
    (EC.presence_of_element_located((, 'content_left')))#等待id为content_left的加载
    print(browser.current_url)#url
    print(browser.get_cookies())#cookie
    print(browser.page_source)#源代码
finally:
    ()#关闭浏览器

访问页面

from selenium import webdriver
browser = ()
('')
print(browser.page_source)
()

查找元素

单个元素

from selenium import webdriver

browser = ()
('')
input_first = browser.find_element_by_id('q')#选择id为q的元素
input_second = browser.find_element_by_css_selector('#q')#CSS选择器
input_third = browser.find_element_by_xpath('//*[@]')
print(input_first, input_second, input_third)
()

三个方法结果相同

运行结果：

DevTools listening on ws://127.0.0.1:62613/devtools/browser/9a25c43c-bb60-4b55-b700-08c5e74b550b
[17960:16432:0122/105950.881:ERROR:platform_sensor_reader_win.cc(242)] NOT IMPLEMENTED< (session="c36131e3480d4711ff6228da50f8ae63", element="0.3627113174529024-1")> < (session="c36131e3480d4711ff6228da50f8ae63", element="0.3627113174529024-1")> < (session="c36131e3480d4711ff6228da50f8ae63", element="0.3627113174529024-1")>

查找

  • 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

from selenium import webdriver
from  import By

browser = ()
('')
input_first = browser.find_element(, 'q')
print(input_first)
()

运行结果：

DevTools listening on ws://127.0.0.1:63006/devtools/browser/bc649a28-0a25-44c2-91d7-4426a5008b83
[2984:16044:0122/110826.883:ERROR:platform_sensor_reader_win.cc(242)] NOT IMPLEMENTED< (session="a8f5c3cacd91715717b10f8bcf934066", element="0.4840171640554687-1")>

多个元素

找出所有service-bd li标签，用列表形式呈现

from selenium import webdriver

browser = ()
('')
lis = browser.find_elements_by_css_selector('.service-bd li')#与单个元素的区别：elements
#方法二：lis = browser.find_elements(By.CSS_SELECTOR, '.service-bd li')
print(lis)
()

运行结果：

DevTools listening on ws://127.0.0.1:63386/devtools/browser/86b8540a-df38-459d-ab48-064d79e27fa0
[13076:13288:0122/111756.383:ERROR:platform_sensor_reader_win.cc(242)] NOT IMPLEMENTED[< (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-1")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-2")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-3")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-4")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-5")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-6")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-7")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-8")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-9")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-10")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-11")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-12")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-13")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-14")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-15")>, < (session="45e8e2c9e0702d4e4a3e15bb198f5121", element="0.8684254903715036-16")>]

选择方法：

  • 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

对获取的元素调用交互方法

from selenium import webdriver
import time

browser = ()
('')
input = browser.find_element_by_class_name('search-keyword')
input.send_keys('iPhone')
(1)
()
input.send_keys('iPad')
button = browser.find_element_by_class_name('search-submit')
()

交互动作

将动作附加到动作链中串行执行

模拟拖拽动作

from selenium import webdriver
from  import ActionChains

browser = ()
url = '/try/?filename=jqueryui-api-droppable'
(url)
browser.switch_to.frame('iframeResult')#切换到里层的iframe
source = browser.find_element_by_css_selector('#draggable')#被拖拽元素
target = browser.find_element_by_css_selector('#droppable')#拖拽目标
actions = ActionChains(browser)#声明动作链对象
actions.drag_and_drop(source, target)
()#执行拖拽动作

更多操作: /#.action_chains

执行JavaScript

实现API中没有的动作操作或实现难实现的交互动作

from selenium import webdriver

browser = ()
('/explore')
browser.execute_script('(0, )')
browser.execute_script('alert("To Bottom")')

获取元素信息

获取属性

from selenium import webdriver
from  import ActionChains

browser = ()
url = '/explore'
(url)
logo = browser.find_element_by_id('zh-top-link-logo')
print(logo)
print(logo.get_attribute('class'))#获取class名

获取文本值

from selenium import webdriver

browser = ()
url = '/explore'
(url)
input = browser.find_element_by_class_name('zu-top-add-question')
print()

获取ID，位置，标签名，大小

from selenium import webdriver

browser = ()
url = '/explore'
(url)
input = browser.find_element_by_class_name('zu-top-add-question')
print()
print()
print(input.tag_name)
print()

Frame

在父级的Frame查找子元素的Frame，必须切换到该Frame里

import time
from selenium import webdriver
from  import NoSuchElementException

browser = ()
url = '/try/?filename=jqueryui-api-droppable'
(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()

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

网速非常慢时可用

from selenium import webdriver

browser = ()
browser.implicitly_wait(10)
('/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input)

运行结果：

< (session="d6934dd4291f6372ee57933dfff55db6", element="0.9859860396136111-1")>

显式等待

添加了等待判断条件，若等待时满足条件则立即返回，若不成立则继续等待直到等待时间结束，超出时间抛出异常

from selenium import webdriver
from  import By
from  import WebDriverWait
from  import expected_conditions as EC

browser = ()
('/')
wait = WebDriverWait(browser, 10)
input = (EC.presence_of_element_located((, 'q')))
button = (EC.element_to_be_clickable((By.CSS_SELECTOR, '.btn-search')))
print(input, button)

运行结果：

< (session="07dd2fbc2d5b1ce40e82b9754aba8fa8", element="0.5642646294074107-1")> < (session="07dd2fbc2d5b1ce40e82b9754aba8fa8", element="0.5642646294074107-2")>

常用判断条件：

  • 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(, '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：/#.expected_conditions

前进后退

import time
from selenium import webdriver

browser = ()
('/')
('/')
()
(1)
()
()
Cookies
from selenium import webdriver

browser = ()
('/explore')
print(browser.get_cookies())
browser.add_cookie({'name': 'name', 'domain': '', '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 = ()
('')
browser.execute_script('()')#打开新选项卡
print(browser.window_handles)
browser.switch_to_window(browser.window_handles[1])#切换到第二个选项卡
('')
(1)
browser.switch_to_window(browser.window_handles[0])#切换到第一个选项卡
('')

异常处理

from selenium import webdriver
from  import TimeoutException, NoSuchElementException

browser = ()
try:
    ('')
except TimeoutException:
    print('Time Out')
try:
    browser.find_element_by_id('hello')#寻找不存在的标签
except NoSuchElementException:
    print('No Element')
finally:
    ()

运行结果：

No Element

详细文档：/#

相关文章