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()
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
国内镜像地址：http://npm.taobao.org/mirrors/chromedriver/
最新的版本去官网找:https://sites.google.com/a/chromium.org/chromedriver/downloads

#验证安装
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.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:\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、基本使用

browser=webdriver.Chrome()
try:
    browser.get('https://www.tmall.com/')

    # 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
    time.sleep(10)
    input_tag=browser.find_element_by_class_name('s-combobox-input')
    input_tag.send_keys('奇异果') #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.CLASS_NAME,'pg'))) #等到id为content_left的元素加载完毕,最多等10秒

    print(browser.page_source)
    with open('text1.html','wb') as f:
        f.write(browser.page_source)
    wait=WebDriverWait(browser,10)
    wait.until(EC.presence_of_element_located((By.CLASS_NAME,'pg'))) #等到id为content_left的元素加载完毕,最多等10秒
    browser.find_element_by_class_name('ui - page - next').click()
    with open('text2.html','wb') as f:
        f.write(browser.page_source)
    # print(browser.page_source)
    # print(browser.current_url)
    # print(browser.get_cookies())
    time.sleep(1000)
finally:
    browser.close()

四、选择器

 

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:
        driver = webdriver.Chrome()
        wait = WebDriverWait(driver, 5)
        driver.implicitly_wait(3)
        driver.get('https://www.baidu.com/')
        # #     '''
        # #     find_element_by_id
        # #     find_element_by_name
        # #     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
        # #     find_element_by_xpath
        # #     '''
        # # 1、find_element_by_id
        #     input_tag=driver.find_element_by_id("kw")
        # #     print(input_tag.get_attribute('name'))
        # #     print(input_tag.text)
        # #     print(input_tag.tag_name)
        #
        #
        #  # 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_element_by_partial_link_text('登')
        login.click()
        #
        #
        # #  4.find_element_by_class_name
        # #     login_for_user=driver.find_element_by_class_name('tang-pass-footerBarULogin')
        # #     login_for_user=wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'tang-pass-footerBarULogin'))).click()
        login_for_user = wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'tang-pass-footerBarULogin')))
        # print(login_for_user)
        login_for_user.click()

        # #5、 find_element_by_name
        input_user = driver.find_element_by_name('userName')
        input_pwd = driver.find_element_by_name('password')
        button = driver.find_element_by_id('TANGRAM__PSP_10__submit')
        input_user.send_keys('aa')
        input_pwd.send_keys('bb')
        button.click()
        img = driver.find_element_by_id('TANGRAM__PSP_10__verifyCodeImg')
        url = img.get_attribute('src')
        # print(image)
        download_img(url)
        image = Image.open('img.jpg')
        vcode = pytesseract.image_to_string(image)
        print(vcode)

        time.sleep(100)
    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:
#     driver = webdriver.Chrome()
#     # wait = WebDriverWait(driver, 3)
#     driver.implicitly_wait(3)
#
#     driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html')
    # 1、//与/

    # tag=driver.find_element_by_xpath('/html/body/div/a')
    # print(tag.tag_name)
    # print(tag.text)
    # print(tag.get_attribute('href'))

    # tag=driver.find_elements_by_xpath('//a')
    # print(tag)

    # tag=driver.find_elements_by_xpath('//div//a')
    # tag1=driver.find_elements_by_css_selector('div a')
    # print(len(tag))
    # print(len(tag1))

    # 2、查找第几个
    # tag=driver.find_elements_by_xpath('//div//a[4]')
    # print(tag[0].text)

    # 3、按照属性查找
    # tag1=driver.find_element_by_xpath('//a[@href="image3.html"]')
    # tag2=driver.find_element_by_xpath('//a[3]')
    # tag3=driver.find_element_by_xpath('//a[contains(@href,"image3")]')
    #
    # print(tag1.text)
    # print(tag2.text)
    # print(tag3.text)


    # 4、其他
    # driver.find_elements_by_xpath('//*[@class="xxxx"]')   # 查找class="xxxx"的所有标签（包括子标签）
    # driver.find_elements_by_xpath('//div[@class="xxxx"][@class="yyyyy"]')   # 查找div标签下class="xxxx"和class="yyyyy"的所有标签（包括子标签）

    # print(driver.find_element_by_xpath('//a[img/@src="image2_thumb.jpg"]').text)
    # print(driver.find_element_by_xpath('//a/..').tag_name)   # 父标签

#     img = driver.find_element_by_xpath('//img')
#     print(img.location)
#     print(img.size)
#
# 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

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()
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()

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()

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

# ActionChains
try:
    driver=webdriver.Chrome()
    driver.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
    driver.implicitly_wait(10)
    # driver.execute_script('alert("hahha")')
    driver.switch_to.frame('iframeResult')
    # driver.switch_to.parent_frame()

    # 方式一：基于一条链，从头一下移动到尾部
    # source=driver.find_element_by_id('draggable')
    # target=driver.find_element_by_id('droppable')
    # actions=ActionChains(driver)
    # actions.drag_and_drop(source,target)
    # actions.perform()

    # 方式二：基于不同ActionChains,可以控制移动的位移
    source=driver.find_element_by_id('draggable')
    target=driver.find_element_by_id('droppable')
    print(target.location['x'])
    print(source.location['x'])
    distance=target.location['x']-source.location['x']
    ActionChains(driver).click_and_hold(source).perform()
    # ActionChains(driver).move_by_offset(xoffset=distance,yoffset=0).perform()
    # ActionChains(driver).release().perform()

    res=0
    while res<distance:
        ActionChains(driver).move_by_offset(xoffset=1,yoffset=0).perform()
        res+=1
    ActionChains(driver).release().perform()

    time.sleep(5)

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、其它

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()

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

browser=webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.execute_script('window.open()')

print(browser.window_handles) #获取所有选项卡
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

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('product')
        print(goods)
        for good in goods:
            print(good.text)
            detail_url=good.find_element_by_tag_name('a').get_attribute('href')
            p_name=good.find_element_by_css_selector('.productTitle a').text.replace('\n','')
            price=good.find_element_by_css_selector('.productPrice em').text
            print(detail_url)
            print(p_name)
            print(price)
            # msg='''
            # 商品:%s
            # 链接:%s
            # price:%s
            # '''%(p_name,detail_url,price)

            # with open('text.txt','w') as f:
            #      f.write(msg)

        button=driver.find_elements_by_class_name('ui-page-next')
        button.click()
        time.sleep(10)
        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_name('q')
        # search=driver.find_element_by_partial_link_text('搜索')
        input_tag.send_keys(keyword)
        input_tag.send_keys(Keys.ENTER)
        # search.click()
        get_goods(driver)
    finally:
        driver.close()



if __name__ == '__main__':
    spider('https://list.tmall.com/','水杯')