一 介绍
selenium最初是一个自动化测试工具,而爬虫中使用它主要是为了解决requests无法直接执行JavaScript代码的问题 selenium本质是通过驱动浏览器,完全模拟浏览器的操作,比如跳转、输入、点击、下拉等,来拿到网页渲染之后的结果,可支持多种浏览器 from selenium import webdriver browser=webdriver.Chrome() browser=webdriver.Firefox() browser=webdriver.PhantomJS() browser=webdriver.Safari() browser=webdriver.Edge()
官网:http://selenium-python.readthedocs.io
二 安装
#安装:selenium+chromedriver pip3 install selenium 下载chromdriver.exe放到python安装路径的scripts目录中即可,注意最新版本是2.29,并非2.9 国内镜像网站地址:http://npm.taobao.org/mirrors/chromedriver/2.29/ 最新的版本去官网找:https://sites.google.com/a/chromium.org/chromedriver/downloads #验证安装 C:UsersAdministrator>python3 Python 3.6.1 (v3.6.1:69c0db5, Mar 21 2017, 18:41:36) [MSC v.1900 64 bit (AMD64)] on win32 Type "help", "copyright", "credits" or "license" for more information. >>> from selenium import webdriver >>> driver=webdriver.Chrome() #弹出浏览器 >>> driver.get('https://www.baidu.com') >>> driver.page_source #注意: selenium3默认支持的webdriver是Firfox,而Firefox需要安装geckodriver 下载链接:https://github.com/mozilla/geckodriver/releases
#安装:selenium+phantomjs pip3 install selenium 下载phantomjs,解压后把phantomjs.exe所在的bin目录放到环境变量 下载链接:http://phantomjs.org/download.html #验证安装 C:UsersAdministrator>phantomjs phantomjs> console.log('egon gaga') egon gaga undefined phantomjs> ^C C:UsersAdministrator>python3 Python 3.6.1 (v3.6.1:69c0db5, Mar 21 2017, 18:41:36) [MSC v.1900 64 bit (AMD64)] on win32 Type "help", "copyright", "credits" or "license" for more information. >>> from selenium import webdriver >>> driver=webdriver.PhantomJS() #无界面浏览器 >>> driver.get('https://www.baidu.com') >>> driver.page_source
三 基本使用
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 browser=webdriver.Chrome() try: browser.get('https://www.baidu.com') input_tag=browser.find_element_by_id('kw') input_tag.send_keys('美女') #python2中输入中文错误,字符串前加个u input_tag.send_keys(Keys.ENTER) #输入回车 wait=WebDriverWait(browser,10) wait.until(EC.presence_of_element_located((By.ID,'content_left'))) #等到id为content_left的元素加载完毕,最多等10秒 print(browser.page_source) print(browser.current_url) print(browser.get_cookies()) finally: browser.close()
四 选择器
一 基本用法
#官网链接:http://selenium-python.readthedocs.io/locating-elements.html from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 import time driver=webdriver.Chrome() driver.get('https://www.baidu.com') wait=WebDriverWait(driver,10) try: #===============所有方法=================== # 1、find_element_by_id # 2、find_element_by_link_text # 3、find_element_by_partial_link_text # 4、find_element_by_tag_name # 5、find_element_by_class_name # 6、find_element_by_name # 7、find_element_by_css_selector # 8、find_element_by_xpath # 强调: # 1、上述均可以改写成find_element(By.ID,'kw')的形式 # 2、find_elements_by_xxx的形式是查找到多个元素,结果为列表 #===============示范用法=================== # 1、find_element_by_id print(driver.find_element_by_id('kw')) # 2、find_element_by_link_text # login=driver.find_element_by_link_text('登录') # login.click() # 3、find_element_by_partial_link_text login=driver.find_elements_by_partial_link_text('录')[0] login.click() # 4、find_element_by_tag_name print(driver.find_element_by_tag_name('a')) # 5、find_element_by_class_name button=wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'tang-pass-footerBarULogin'))) button.click() # 6、find_element_by_name input_user=wait.until(EC.presence_of_element_located((By.NAME,'userName'))) input_pwd=wait.until(EC.presence_of_element_located((By.NAME,'password'))) commit=wait.until(EC.element_to_be_clickable((By.ID,'TANGRAM__PSP_10__submit'))) input_user.send_keys('18611453110') input_pwd.send_keys('lhf@094573') commit.click() # 7、find_element_by_css_selector driver.find_element_by_css_selector('#kw') # 8、find_element_by_xpath time.sleep(5) finally: driver.close()
二 xpath
#官网链接:http://selenium-python.readthedocs.io/locating-elements.html from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 import time driver=webdriver.PhantomJS() driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html') # wait=WebDriverWait(driver,3) driver.implicitly_wait(3) #使用隐式等待 try: # find_element_by_xpath #//与/ # driver.find_element_by_xpath('//body/a') # 开头的//代表从整篇文档中寻找,body之后的/代表body的儿子,这一行找不到就会报错了 driver.find_element_by_xpath('//body//a') # 开头的//代表从整篇文档中寻找,body之后的//代表body的子子孙孙 driver.find_element_by_css_selector('body a') #取第n个 res1=driver.find_elements_by_xpath('//body//a[1]') #取第一个a标签 print(res1[0].text) #按照属性查找,下述三者查找效果一样 res1=driver.find_element_by_xpath('//a[5]') res2=driver.find_element_by_xpath('//a[@href="image5.html"]') res3=driver.find_element_by_xpath('//a[contains(@href,"image5")]') #模糊查找 print('==>', res1.text) print('==>',res2.text) print('==>',res3.text) #其他 res1=driver.find_element_by_xpath('/html/body/div/a') print(res1.text) res2=driver.find_element_by_xpath('//a[img/@src="image3_thumb.jpg"]') #找到子标签img的src属性为image3_thumb.jpg的a标签 print(res2.tag_name,res2.text) res3 = driver.find_element_by_xpath("//input[@name='continue'][@type='button']") #查看属性name为continue且属性type为button的input标签 res4 = driver.find_element_by_xpath("//*[@name='continue'][@type='button']") #查看属性name为continue且属性type为button的所有标签 time.sleep(5) finally: driver.close()
三 获取标签属性
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 browser=webdriver.Chrome() browser.get('https://www.amazon.cn/') wait=WebDriverWait(browser,10) wait.until(EC.presence_of_element_located((By.ID,'cc-lm-tcgShowImgContainer'))) tag=browser.find_element(By.CSS_SELECTOR,'#cc-lm-tcgShowImgContainer img') #获取标签属性, print(tag.get_attribute('src')) #获取标签ID,位置,名称,大小(了解) print(tag.id) print(tag.location) print(tag.tag_name) print(tag.size) browser.close()
五 等待元素被加载
#1、selenium只是模拟浏览器的行为,而浏览器解析页面是需要时间的(执行css,js),一些元素可能需要过一段时间才能加载出来,为了保证能查找到元素,必须等待 #2、等待的方式分两种: 隐式等待:在browser.get('xxx')前就设置,针对所有元素有效 显式等待:在browser.get('xxx')之后设置,只针对某个元素有效
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 browser=webdriver.Chrome() #隐式等待:在查找所有元素时,如果尚未被加载,则等10秒 browser.implicitly_wait(10) browser.get('https://www.baidu.com') input_tag=browser.find_element_by_id('kw') input_tag.send_keys('美女') input_tag.send_keys(Keys.ENTER) contents=browser.find_element_by_id('content_left') #没有等待环节而直接查找,找不到则会报错 print(contents) browser.close()
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 browser=webdriver.Chrome() browser.get('https://www.baidu.com') input_tag=browser.find_element_by_id('kw') input_tag.send_keys('美女') input_tag.send_keys(Keys.ENTER) #显式等待:显式地等待某个元素被加载 wait=WebDriverWait(browser,10) wait.until(EC.presence_of_element_located((By.ID,'content_left'))) contents=browser.find_element(By.CSS_SELECTOR,'#content_left') print(contents) browser.close()
六 元素交互操作
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 browser=webdriver.Chrome() browser.get('https://www.amazon.cn/') wait=WebDriverWait(browser,10) input_tag=wait.until(EC.presence_of_element_located((By.ID,'twotabsearchtextbox'))) input_tag.send_keys('iphone 8') button=browser.find_element_by_css_selector('#nav-search > form > div.nav-right > div > input') button.click() import time time.sleep(3) input_tag=browser.find_element_by_id('twotabsearchtextbox') input_tag.clear() #清空输入框 input_tag.send_keys('iphone7plus') button=browser.find_element_by_css_selector('#nav-search > form > div.nav-right > div > input') button.click() # browser.close()
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By # 按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys # 键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait # 等待页面加载某些元素 import time driver = webdriver.Chrome() driver.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable') wait=WebDriverWait(driver,3) # driver.implicitly_wait(3) # 使用隐式等待 try: driver.switch_to.frame('iframeResult') ##切换到iframeResult sourse=driver.find_element_by_id('draggable') target=driver.find_element_by_id('droppable') #方式一:基于同一个动作链串行执行 # actions=ActionChains(driver) #拿到动作链对象 # actions.drag_and_drop(sourse,target) #把动作放到动作链中,准备串行执行 # actions.perform() #方式二:不同的动作链,每次移动的位移都不同 ActionChains(driver).click_and_hold(sourse).perform() distance=target.location['x']-sourse.location['x'] track=0 while track < distance: ActionChains(driver).move_by_offset(xoffset=2,yoffset=0).perform() track+=2 ActionChains(driver).release().perform() time.sleep(10) finally: driver.close()
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 try: browser=webdriver.Chrome() browser.get('https://www.baidu.com') browser.execute_script('alert("hello world")') #打印警告 finally: browser.close()
#frame相当于一个单独的网页,在父frame里是无法直接查看到子frame的元素的,必须switch_to_frame切到该frame下,才能进一步查找 from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 try: browser=webdriver.Chrome() browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable') browser.switch_to.frame('iframeResult') #切换到id为iframeResult的frame tag1=browser.find_element_by_id('droppable') print(tag1) # tag2=browser.find_element_by_id('textareaCode') #报错,在子frame里无法查看到父frame的元素 browser.switch_to.parent_frame() #切回父frame,就可以查找到了 tag2=browser.find_element_by_id('textareaCode') print(tag2) finally: browser.close()
七 其他
#模拟浏览器的前进后退 import time from selenium import webdriver browser=webdriver.Chrome() browser.get('https://www.baidu.com') browser.get('https://www.taobao.com') browser.get('http://www.sina.com.cn/') browser.back() time.sleep(10) 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({'k1':'xxx','k2':'yyy'}) print(browser.get_cookies()) # browser.delete_all_cookies()
#选项卡管理:切换选项卡,有js的方式windows.open,有windows快捷键:ctrl+t等,最通用的就是js的方式 import time from selenium import webdriver browser=webdriver.Chrome() browser.get('https://www.baidu.com') browser.execute_script('window.open()') print(browser.window_handles) #获取所有的选项卡 browser.switch_to_window(browser.window_handles[1]) browser.get('https://www.taobao.com') time.sleep(10) browser.switch_to_window(browser.window_handles[0]) browser.get('https://www.sina.com.cn') browser.close()
from selenium import webdriver from selenium.common.exceptions import TimeoutException,NoSuchElementException,NoSuchFrameException try: browser=webdriver.Chrome() browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable') browser.switch_to.frame('iframssseResult') except TimeoutException as e: print(e) except NoSuchFrameException as e: print(e) finally: browser.close()
八 项目练习
#注意:网站都策略都是在不断变化的,精髓在于学习流程。下述代码生效与2017-11-7,不能保证永久有效 from selenium import webdriver from selenium.webdriver import ActionChains 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() try: browser.get('http://mail.163.com/') wait=WebDriverWait(browser,5) frame=wait.until(EC.presence_of_element_located((By.ID,'x-URS-iframe'))) browser.switch_to.frame(frame) wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'.m-container'))) inp_user=browser.find_element_by_name('email') inp_pwd=browser.find_element_by_name('password') button=browser.find_element_by_id('dologin') inp_user.send_keys('18611453110') inp_pwd.send_keys('xxxx') button.click() #如果遇到验证码,可以把下面一小段打开注释 # import time # time.sleep(10) # button = browser.find_element_by_id('dologin') # button.click() wait.until(EC.presence_of_element_located((By.ID,'dvNavTop'))) write_msg=browser.find_elements_by_css_selector('#dvNavTop li')[1] #获取第二个li标签就是“写信”了 write_msg.click() wait.until(EC.presence_of_element_located((By.CLASS_NAME,'tH0'))) recv_man=browser.find_element_by_class_name('nui-editableAddr-ipt') title=browser.find_element_by_css_selector('.dG0 .nui-ipt-input') recv_man.send_keys('378533872@qq.com') title.send_keys('圣旨') print(title.tag_name) frame=wait.until(EC.presence_of_element_located((By.CLASS_NAME,'APP-editor-iframe'))) browser.switch_to.frame(frame) body=browser.find_element(By.CSS_SELECTOR,'body') body.send_keys('egon很帅,可以加工资了') browser.switch_to.parent_frame() #切回他爹 send_button=browser.find_element_by_class_name('nui-toolbar-item') send_button.click() #可以睡时间久一点别让浏览器关掉,看看发送成功没有 import time time.sleep(10000) except Exception as e: print(e) finally: browser.close()
from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By #按照什么方式查找,By.ID,By.CSS_SELECTOR from selenium.webdriver.common.keys import Keys #键盘按键操作 from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素 import time def get_goods(driver): try: goods=driver.find_elements_by_class_name('gl-item') for good in goods: detail_url=good.find_element_by_tag_name('a').get_attribute('href') p_name=good.find_element_by_css_selector('.p-name em').text.replace(' ','') price=good.find_element_by_css_selector('.p-price i').text p_commit=good.find_element_by_css_selector('.p-commit a').text msg = ''' 商品 : %s 链接 : %s 价钱 :%s 评论 :%s ''' % (p_name,detail_url,price,p_commit) print(msg,end=' ') button=driver.find_element_by_partial_link_text('下一页') button.click() time.sleep(1) get_goods(driver) except Exception: pass def spider(url,keyword): driver = webdriver.Chrome() driver.get(url) driver.implicitly_wait(3) # 使用隐式等待 try: input_tag=driver.find_element_by_id('key') input_tag.send_keys(keyword) input_tag.send_keys(Keys.ENTER) get_goods(driver) finally: driver.close() if __name__ == '__main__': spider('https://www.jd.com/',keyword='iPhone8手机')
作业:
爬取亚马逊iphone手机的商品信息
爬取天猫python书籍的商品信息
爬取京东小米手机的商品信息