python用selenium库_Python爬虫之Selenium库的基本使用

#基本使用

from selenium importwebdriverfrom selenium.webdriver.common.by importByfrom selenium.webdriver.common.keys importKeysfrom selenium.webdriver.support importexpected_conditions as ECfrom selenium.webdriver.support.wait importWebDriverWait

browser=webdriver.Chrome()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()#声明浏览器对象

from selenium importwebdriver

browser=webdriver.Chrome()

browser=webdriver.Firefox()

browser=webdriver.Edge()

browser=webdriver.PhantomJS()

browser=webdriver.Safari()#访问页面

from selenium importwebdriver

browser=webdriver.Chrome()

browser.get('https://www.taobao.com')print(browser.page_source)

browser.close()#查找元素#单个元素

from selenium importwebdriver

browser=webdriver.Chrome()

browser.get('https://www.taobao.com')#下面三个效果是一样的

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)print(input_second)print(input_third)

browser.close()from selenium importwebdriverfrom selenium.webdriver.common.by importBy

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

from selenium importwebdriver

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 importwebdriverfrom selenium.webdriver.common.by importBy

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

from selenium importwebdriverimporttime

browser=webdriver.Chrome()

browser.get('https://www.taobao.com')

input= browser.find_element_by_id('q')

input.send_keys('笔记本电脑')

time.sleep(5)

input.clear()

input.send_keys('iPad')

button= browser.find_element_by_class_name('btn-search')#button.click()

#交互动作#将动作附加到动作链中串行执行

from selenium importwebdriverfrom selenium.webdriver importActionChains

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()#执行JavaScript

from selenium importwebdriver

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

from selenium importwebdriverfrom selenium.webdriver importActionChains

browser=webdriver.Chrome()

browser.get("https://www.zhihu.com/explore")

logo= browser.find_element_by_id('zh-top-link-logo')print(logo)print(logo.get_attribute('class'))#获取文本值

from selenium importwebdriver

browser=webdriver.Chrome()

browser.get('https://www.zhihu.com/explore')

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 importwebdriver

browser=webdriver.Chrome()

browser.get('https://www.zhihu.com/explore')

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

importtimefrom selenium importwebdriverfrom selenium.common.exceptions importNoSuchElementException

browser=webdriver.Chrome()

browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')

browser.switch_to.frame('iframeResult')

source= browser.find_element_by_css_selector('#draggable')print(source)try:

logo= browser.find_element_by_class_name('logo')exceptNoSuchElementException:print('NO LOGO')

browser.switch_to.parent_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 importwebdriver

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)#显示等待

from selenium importwebdriverfrom selenium.webdriver.common.by importByfrom selenium.webdriver.support.ui importWebDriverWaitfrom selenium.webdriver.support importexpected_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)#前进后退

importtimefrom selenium importwebdriver

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(5)

browser.forward()

browser.close()#Cookies

from selenium importwebdriver

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

importtimefrom selenium importwebdriver

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(5)

browser.switch_to_window(browser.window_handles[0])

browser.get('https://python.org')#异常处理

from selenium importwebdriver

browser=webdriver.Chrome()

browser.get('https://www.baidu.com')

browser.find_element_by_id('hello')from selenium importwebdriverfrom selenium.common.exceptions importTimeoutException, NoSuchElementException

browser=webdriver.Chrome()try:

browser.get('https://www.baidu.com')exceptTimeoutException:print('Time Out')try:

browser.find_element_by_id('hello')exceptNoSuchElementException:print('No Element')finally:

browser.close()