爬虫 selenium模块
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() #调用谷歌浏览器 browser=webdriver.Firefox() #调用火狐 browser=webdriver.PhantomJS() # 无浏览器运行 browser=webdriver.Safari() browser=webdriver.Edge()
二 安装
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#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:\Users\Administrator>phantomjs phantomjs> console.log('egon gaga') egon gaga undefined phantomjs> ^C C:\Users\Administrator>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
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#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:\Users\Administrator>phantomjs phantomjs> console.log('egon gaga') egon gaga undefined phantomjs> ^C C:\Users\Administrator>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() 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
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') try: # 1、find_element_by_id # input_tag=driver.find_element_by_id('kw') # 根据网页中的ID,来查找标签 # print(input_tag.tag_name) # 标签类型 # print(input_tag.get_attribute('name')) # 标签的name属性 # print(input_tag.text) # 标签的文本 # 2、find_element_by_link_text # login=driver.find_element_by_link_text('登录') # 根据网页中标签文本来找标签 # login.click() # 点击标签 # print(login.tag_name) # print(login.get_attribute('name')) # print(login.text) # 3、find_element_by_partial_link_text # login=driver.find_element_by_partial_link_text('登') # 根据标签中一部分文本来找标签 # login.click() # 4、find_element_by_class_name # tag=driver.find_element_by_class_name('lb') # 根据标签的class属性找标签 # print(tag.tag_name) # print(tag.get_attribute('name')) # 5、find_element_by_name # login=driver.find_element_by_link_text('登录') # login.click() # login_for_user=driver.find_element_by_id('TANGRAM__PSP_10__footerULoginBtn') # login_for_user.click() # input_user=driver.find_element_by_name('userName') # 根据网页中标签name属性来找标签 # input_pwd=driver.find_element_by_name('password') # button=driver.find_element_by_id('TANGRAM__PSP_10__submit') # input_user.send_keys('17094322519') # input_pwd.send_keys('11111111111') # button.click() time.sleep(5) finally: driver.close()
xpath
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.implicitly_wait(3) driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html') try: # find_element_by_xpath # 通过//子孙,/子代,来寻找标签 # //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 # tag=driver.find_elements_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 # tag=driver.find_elements_by_css_selector('body a') # css 筛选一样 # print(len(tag)) # 取第n个 # res1 = driver.find_element_by_xpath('//body//a[1]') # 取第一个a标签 # print(res1.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]') # 取第5个a标签 # res2 = driver.find_element_by_xpath('//a[@href="image5.html"]') # a标签中属性为 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') # 只取第一个找到的标签 # 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 # print(driver.find_element_by_xpath('//a//..').tag_name) # 从子标签找父标签 # print([tag.tag_name for tag in driver.find_elements_by_xpath('//img//..')]) time.sleep(5) finally: driver.close()
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 import time driver = webdriver.Chrome() driver.implicitly_wait(3) driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html') try: res = driver.find_element_by_xpath('//a[img/@src="image3_thumb.jpg"]') print(res.location) {'x': 8, 'y': 50} 标签在相对于左上角页面的位置 print(res.size) {'height': 42, 'width': 170} 标签的宽高 time.sleep(5) finally: driver.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
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
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
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#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
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#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()
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
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()