day06---selenium剩余操作和自动登录

灰太狼 2021-12-10 01:47 215阅读 0赞

今日内容:  
注意: selenium驱动的浏览器是干净的，没有任何缓存。

1、selenium剩余用法  
2、selenium万能登录破解  
3、selenium爬取京东商品信息  
4、破解极验滑动验证码

from selenium import webdriver  
import time

driver = webdriver.Chrome(r'D:\\BaiduNetdiskDownload\\chromedriver\_win32\\chromedriver.exe')

\# 把窗口转成全屏  
driver.maximize\_window()

try:  
driver.get('https://dig.chouti.com/')  
driver.implicitly\_wait(10)  
time.sleep(5)

\# 1、点击登录  
login\_btn = driver.find\_element\_by\_id('login\_btn')  
login\_btn.click()  
time.sleep(2)

\# 2、输入用户名  
phone = driver.find\_element\_by\_class\_name('login-phone')  
phone.send\_keys('15622792660')

\# 3、输入密码  
pwd = driver.find\_element\_by\_class\_name('pwd-password-input')  
pwd.send\_keys('kermit46709394')

\# 4、确认登录  
login\_submit = driver.find\_element\_by\_class\_name('btn-large')  
login\_submit.click()

time.sleep(20)

\# 捕获异常并打印  
except Exception as e:  
print(e)

finally:  
driver.close()

from selenium import webdriver

driver = webdriver.Chrome(r'D:\\BaiduNetdiskDownload\\chromedriver\_win32\\chromedriver.exe')

try:  
\# 隐式等待: 写在get请求前  
driver.implicitly\_wait(5)

driver.get('https://doc.scrapy.org/en/latest/\_static/selectors-sample1.html')

\# 显式等待: 写在get请求后  
\# wait.until(...)

'''  
  
<html>  
<head>  
<base href='http://example.com/' />  
<title>Example website</title>  
</head>  
<body>  
<div id='images'>  
<a href='image1.html'>Name: My image 1 <br /><img src='image1\_thumb.jpg' /></a>  
<a href='image2.html'>Name: My image 2 <br /><img src='image2\_thumb.jpg' /></a>  
<a href='image3.html'>Name: My image 3 <br /><img src='image3\_thumb.jpg' /></a>  
<a href='image4.html'>Name: My image 4 <br /><img src='image4\_thumb.jpg' /></a>  
<a href='image5.html'>Name: My image 5 <br /><img src='image5\_thumb.jpg' /></a>  
</div>  
</body>  
</html>  
'''  
\# 根据xpath语法查找元素  
\# / 从根节点开始找第一个  
html = driver.find\_element\_by\_xpath('/html')  
\# html = driver.find\_element\_by\_xpath('/head') \# 报错  
print(html.tag\_name)

\# // 从根节点开始找任意一个节点  
div = driver.find\_element\_by\_xpath('//div')  
print(div.tag\_name)

\# @  
\# 查找id为images的div节点  
div = driver.find\_element\_by\_xpath('//div\[@id="images"\]')  
print(div.tag\_name)  
print(div.text)

\# 找到第一个a节点  
a = driver.find\_element\_by\_xpath('//a')  
print(a.tag\_name)

\# 找到所有a节点  
a\_s = driver.find\_elements\_by\_xpath('//a')  
print(a\_s)

\# 找到第一个a节点的href属性  
\# get\_attribute:获取节点中某个属性  
a = driver.find\_element\_by\_xpath('//a').get\_attribute('href')  
print(a)

finally:  
driver.close()

''''''  
'''  
点击、清除操作  
'''  
\# from selenium import webdriver  
\# from selenium.webdriver.common.keys import Keys  
\# import time  
\#  
\# driver = webdriver.Chrome(r'D:\\BaiduNetdiskDownload\\chromedriver\_win32\\chromedriver.exe')  
\#  
\# try:  
\# driver.implicitly\_wait(10)  
\# \# 1、往jd发送请求  
\# driver.get('https://www.jd.com/')  
\# \# 找到输入框输入围城  
\# input\_tag = driver.find\_element\_by\_id('key')  
\# input\_tag.send\_keys('围城')  
\# \# 键盘回车  
\# input\_tag.send\_keys(Keys.ENTER)  
\# time.sleep(2)  
\# \# 找到输入框输入墨菲定律  
\# input\_tag = driver.find\_element\_by\_id('key')  
\# input\_tag.clear()  
\# input\_tag.send\_keys('墨菲定律')  
\# \# 找到搜索按钮点击搜索  
\# button = driver.find\_element\_by\_class\_name('button')  
\# button.click()  
\# time.sleep(10)  
\#  
\# finally:  
\# driver.close()

'''  
获取cookies （了解）  
'''  
\# from selenium import webdriver  
\# import time  
\#  
\# driver = webdriver.Chrome(r'D:\\BaiduNetdiskDownload\\chromedriver\_win32\\chromedriver.exe')  
\#  
\# try:  
\# driver.implicitly\_wait(10)  
\# driver.get('https://www.zhihu.com/explore')  
\# print(driver.get\_cookies())  
\#  
\# time.sleep(10)  
\# finally:  
\# driver.close()

'''  
选项卡  
'''  
\#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()  
\# try:  
\# browser.get('https://www.baidu.com')  
\#  
\# \# execute\_script: 执行javascrpit代码  
\# \# 弹窗操作  
\# \# browser.execute\_script('alert("tank")')  
\# \# 新建浏览器窗口  
\# browser.execute\_script(  
\# '''  
\# window.open();  
\# '''  
\# )  
\# time.sleep(1)  
\# print(browser.window\_handles) \# 获取所有的选项卡  
\# \# 切换到第二个窗口  
\# \# 新:  
\# browser.switch\_to.window(browser.window\_handles\[1\])  
\# \# 旧:  
\# \# browser.switch\_to\_window(browser.window\_handles\[1\])  
\#  
\# \# 第二个窗口往淘宝发送请求  
\# browser.get('https://www.taobao.com')  
\# time.sleep(5)  
\#  
\# \# 切换到第一个窗口  
\# browser.switch\_to\_window(browser.window\_handles\[0\])  
\# browser.get('https://www.sina.com.cn')  
\#  
\# time.sleep(10)  
\# finally:  
\# browser.close()

'''  
ActionChangs动作链  
'''  
\# from selenium import webdriver  
\# from selenium.webdriver import ActionChains  
\# import time  
\#  
\# driver = webdriver.Chrome()  
\# driver.implicitly\_wait(10)  
\# driver.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')  
\#  
\# try:  
\#  
\# \# driver.switch\_to\_frame('iframeResult')  
\# \# 切换到id为iframeResult的窗口内  
\# driver.switch\_to.frame('iframeResult')  
\#  
\# \# 源位置  
\# draggable = driver.find\_element\_by\_id('draggable')  
\#  
\# \# 目标位置  
\# droppable = driver.find\_element\_by\_id('droppable')  
\#  
\# \# 调用ActionChains，必须把驱动对象传进去  
\# \# 得到一个动作链对象，复制给一个变量  
\# actions = ActionChains(driver)  
\#  
\# \# 方式一: 机器人  
\# \# 瞬间把源图片位置秒移到目标图片位置  
\# \# actions.drag\_and\_drop(draggable, droppable) \# 编写一个行为  
\# \# actions.perform() \# 执行编写好的行为  
\#  
\#  
\# \# 方式二: 模拟人的行为  
\# source = draggable.location\['x'\]  
\# target = droppable.location\['x'\]  
\# print(source, target)  
\#  
\# distance = target - source  
\# print(distance)  
\#  
\# \# perform：每个动作都要调用perform执行  
\#  
\# \# 点击并摁住源图片  
\# ActionChains(driver).click\_and\_hold(draggable).perform()  
\#  
\# s = 0  
\# while s < distance:  
\# \# 执行位移操作  
\# ActionChains(driver).move\_by\_offset(xoffset=2, yoffset=0).perform()  
\# s += 2  
\#  
\# \# 释放动作链  
\# ActionChains(driver).release().perform()  
\#  
\# time.sleep(10)  
\#  
\#  
\# finally:  
\# driver.close()

'''  
前进、后退  
'''  
\# from selenium import webdriver  
\# import time  
\#  
\# driver = webdriver.Chrome()  
\#  
\# try:  
\# driver.implicitly\_wait(10)  
\# driver.get('https://www.jd.com/')  
\# driver.get('https://www.baidu.com/')  
\# driver.get('https://www.cnblogs.com/')  
\#  
\# time.sleep(2)  
\#  
\# \# 回退操作  
\# driver.back()  
\# time.sleep(1)  
\# \# 前进操作  
\# driver.forward()  
\# time.sleep(1)  
\# driver.back()  
\# time.sleep(10)  
\#  
\# finally:  
\# driver.close()

from selenium import webdriver  
from selenium.webdriver import ChromeOptions  
import time  
r'''  
步骤:  
1、打开文件的查看，显示隐藏文件  
2、找到C:\\Users\\administortra\\AppData\\Local\\Google\\Chrome\\User Data  
删除Default文件  
3、重新打开浏览器，并登陆百度账号  
\- 此时会创建一个新的Default缓存文件  
4、添加cookies  
5、关闭谷歌浏览器后执行程序  
'''  
\# 获取options对象，参数对象  
options = ChromeOptions()

\# 获取cookies保存路径  
\# 'C:\\Users\\administortra\\AppData\\Local\\Google\\Chrome\\User Data'  
profile\_directory = r'--user-data-dir=C:\\Users\\administortra\\AppData\\Local\\Google\\Chrome\\User Data'

\# 添加用户信息目录  
options.add\_argument(profile\_directory)

\# 把参数加载到当前驱动中 chrome\_options默认参数，用来接收options对象  
driver = webdriver.Chrome(chrome\_options=options)

try:  
driver.implicitly\_wait(10)  
driver.get('https://www.baidu.com/')  
'''  
BDUSS:\*\*\*\*\*  
'''  
\# 添加用户cookies信息  
\# name、value必须小写  
driver.add\_cookie(\{"name": "BDUSS", "value": "用户session字符串"\})

\# 刷新操作  
driver.refresh()

time.sleep(10)

finally:  
driver.close()

\# ''''''  
\# '''  
\# 爬取京东商品信息:  
\# 请求url:  
\# https://www.jd.com/  
\# 提取商品信息:  
\# 1.商品详情页  
\# 2.商品名称  
\# 3.商品价格  
\# 4.评价人数  
\# 5.商品商家  
\# '''  
\# from selenium import webdriver  
\# from selenium.webdriver.common.keys import Keys  
\# import time  
\#  
\# driver = webdriver.Chrome()  
\#  
\# try:  
\# driver.implicitly\_wait(10)  
\# \# 1、往京东主页发送请求  
\# driver.get('https://www.jd.com/')  
\#  
\# \# 2、输入商品名称，并回车搜索  
\# input\_tag = driver.find\_element\_by\_id('key')  
\# input\_tag.send\_keys('macbook')  
\# input\_tag.send\_keys(Keys.ENTER)  
\# time.sleep(2)  
\#  
\# \# 通过JS控制滚轮滑动获取所有商品信息  
\# js\_code = '''  
\# window.scrollTo(0,5000);  
\# '''  
\# driver.execute\_script(js\_code) \# 执行js代码  
\#  
\# \# 等待数据加载  
\# time.sleep(2)  
\#  
\# \# 3、查找所有商品div  
\# \# good\_div = driver.find\_element\_by\_id('J\_goodsList')  
\# good\_list = driver.find\_elements\_by\_class\_name('gl-item')  
\# n = 1  
\# for good in good\_list:  
\# \# 根据属性选择器查找  
\# \# 商品链接  
\# good\_url = good.find\_element\_by\_css\_selector(  
\# '.p-img a').get\_attribute('href')  
\#  
\# \# 商品名称  
\# good\_name = good.find\_element\_by\_css\_selector(  
\# '.p-name em').text.replace("\\n", "--")  
\#  
\# \# 商品价格  
\# good\_price = good.find\_element\_by\_class\_name(  
\# 'p-price').text.replace("\\n", ":")  
\#  
\# \# 评价人数  
\# good\_commit = good.find\_element\_by\_class\_name(  
\# 'p-commit').text.replace("\\n", " ")  
\#  
\# \# 商品商家  
\# good\_from = good.find\_element\_by\_class\_name(  
\# 'J\_im\_icon').text.replace("\\n", " ")  
\#  
\# good\_content = f'''  
\# 商品链接: \{good\_url\}  
\# 商品名称: \{good\_name\}  
\# 商品价格: \{good\_price\}  
\# 评价人数: \{good\_commit\}  
\# 商品商家: \{good\_from\}  
\# \\n  
\# '''  
\# print(good\_content)  
\# with open('jd.txt', 'a', encoding='utf-8') as f:  
\# f.write(good\_content)  
\#  
\# next\_tag = driver.find\_element\_by\_link\_text('下一页')  
\#  
\# next\_tag.click()  
\#  
\# time.sleep(10)  
\#  
\#  
\# finally:  
\# driver.close()

''''''  
'''  
爬取京东商品信息:  
请求url:  
https://www.jd.com/  
提取商品信息:  
1.商品详情页  
2.商品名称  
3.商品价格  
4.评价人数  
5.商品商家  
'''  
from selenium import webdriver  
from selenium.webdriver.common.keys import Keys  
import time

def get\_good(driver):  
try:

\# 通过JS控制滚轮滑动获取所有商品信息  
js\_code = '''  
window.scrollTo(0,5000);  
'''  
driver.execute\_script(js\_code) \# 执行js代码

\# 等待数据加载  
time.sleep(2)

\# 3、查找所有商品div  
\# good\_div = driver.find\_element\_by\_id('J\_goodsList')  
good\_list = driver.find\_elements\_by\_class\_name('gl-item')  
n = 1  
for good in good\_list:  
\# 根据属性选择器查找  
\# 商品链接  
good\_url = good.find\_element\_by\_css\_selector(  
'.p-img a').get\_attribute('href')

\# 商品名称  
good\_name = good.find\_element\_by\_css\_selector(  
'.p-name em').text.replace("\\n", "--")

\# 商品价格  
good\_price = good.find\_element\_by\_class\_name(  
'p-price').text.replace("\\n", ":")

\# 评价人数  
good\_commit = good.find\_element\_by\_class\_name(  
'p-commit').text.replace("\\n", " ")

good\_content = f'''  
商品链接: \{good\_url\}  
商品名称: \{good\_name\}  
商品价格: \{good\_price\}  
评价人数: \{good\_commit\}  
\\n  
'''  
print(good\_content)  
with open('jd.txt', 'a', encoding='utf-8') as f:  
f.write(good\_content)

next\_tag = driver.find\_element\_by\_class\_name('pn-next')  
next\_tag.click()

time.sleep(2)

\# 递归调用函数  
get\_good(driver)

time.sleep(10)

finally:  
driver.close()

if \_\_name\_\_ == '\_\_main\_\_':

good\_name = input('请输入爬取商品信息:').strip()

driver = webdriver.Chrome()  
driver.implicitly\_wait(10)  
\# 1、往京东主页发送请求  
driver.get('https://www.jd.com/')

\# 2、输入商品名称，并回车搜索  
input\_tag = driver.find\_element\_by\_id('key')  
input\_tag.send\_keys(good\_name)  
input\_tag.send\_keys(Keys.ENTER)  
time.sleep(2)

get\_good(driver)

''''''  
'''  
破解极验滑动验证  
博客园登录url:  
https://account.cnblogs.com/signin?returnUrl=https%3A%2F%2Fwww.cnblogs.com%2F  
1、输入用户名与密码，并点击登录  
2、弹出滑动验证，获取有缺口与完整的图片  
3、通过像素点进行比对，获取滑动位移距离  
4、模拟人的行为轨迹  
5、开始滑动  
'''  
from selenium import webdriver \# 用来驱动浏览器的  
from selenium.webdriver import ActionChains \# 破解滑动验证码的时候用的 可以拖动图片  
import time  
from PIL import Image \# pip3 install pillow  
import random

option = webdriver.ChromeOptions()  
option.add\_argument('disable-infobars')

driver = webdriver.Chrome(chrome\_options=option)

def get\_snap(driver):  
\# selenium自带的截图网页全屏图片  
driver.save\_screenshot('snap.png')

img = driver.find\_element\_by\_class\_name('geetest\_canvas\_img')

left = img.location\['x'\]

upper = img.location\['y'\]

right = left + img.size\['width'\]  
lower = upper + img.size\['height'\]

\# print(left, upper, right, lower)  
img\_obj = Image.open('snap.png')

\# 对屏幕进行截取,获取滑动验证图片  
image = img\_obj.crop((left, upper, right, lower))

return image

def get\_image1(driver):  
time.sleep(0.2)  
js\_code = '''  
var x = document.getElementsByClassName('geetest\_canvas\_fullbg')\[0\].style.display="block";  
console.log(x)  
'''

time.sleep(1)  
driver.execute\_script(js\_code)

\# 截取图片  
img\_obj = get\_snap(driver)

return img\_obj

def get\_image2(driver):  
time.sleep(0.2)

js\_code = '''  
var x = document.getElementsByClassName('geetest\_canvas\_fullbg')\[0\].style.display="none";  
console.log(x)  
'''

driver.execute\_script(js\_code)

time.sleep(1)

\# 截取图片  
img\_obj = get\_snap(driver)

return img\_obj

def get\_distance(image1, image2):  
\# 初始值  
start = 60

\# 滑块色差  
color\_num = 60

for x in range(start, image1.size\[0\]):  
for y in range(image1.size\[1\]):

rgb1 = image1.load()\[x, y\]

rgb2 = image2.load()\[x, y\]

r = abs(rgb1\[0\] - rgb2\[0\])  
g = abs(rgb1\[1\] - rgb2\[1\])  
b = abs(rgb1\[2\] - rgb2\[2\])

if not (r < color\_num and g < color\_num and b < color\_num):  
return x - 7

def get\_stacks(distance):  
distance += 20

'''  
匀加速\\减速运行  
v = v0 + a \* t

位移:  
s = v \* t + 0.5 \* a \* (t\*\*2)  
'''

\# 初速度  
v0 = 0

\# 加减速度列表  
a\_list = \[3, 4, 5\]

\# 时间  
t = 0.2

\# 初始位置  
s = 0

\# 向前滑动轨迹  
forward\_stacks = \[\]

mid = distance \* 3 / 5

while s < distance:  
if s < mid:  
a = a\_list\[random.randint(0, 2)\]

else:  
a = -a\_list\[random.randint(0, 2)\]

v = v0

stack = v \* t + 0.5 \* a \* (t \*\* 2)

\# 每次拿到的位移  
stack = round(stack)

s += stack

v0 = v + a \* t

forward\_stacks.append(stack)

back\_stacks = \[-1, -1, -2, -3, -2, -3, -2, -2, -3, -1\]

return \{'forward\_stacks': forward\_stacks, 'back\_stacks': back\_stacks\}

def main():  
try:

driver.get('https://passport.cnblogs.com/user/signin')  
driver.implicitly\_wait(5)

\# 1.输入用户名与密码,点击登录  
username = driver.find\_element\_by\_id('LoginName')  
password = driver.find\_element\_by\_id('Password')  
login\_button = driver.find\_element\_by\_class\_name('ladda-label')  
time.sleep(1)  
username.send\_keys('\_tank\_')  
time.sleep(1)  
password.send\_keys('k46709394.')

\# 这里需要等待账号密码输入完毕后再点击登录按钮，否则的不弹框  
time.sleep(1)  
login\_button.click()  
\# time.sleep(3)

\# 2.点击滑动验证按钮,获取图片  
geetest\_button = driver.find\_element\_by\_class\_name('geetest\_slider\_button')  
geetest\_button.click()

time.sleep(0.2)

\# 3.针对完整的图片进行截取  
image1 = get\_image1(driver)

\# 4.针对有缺口的图片进行截取  
image2 = get\_image2(driver)

\# 5.对比两张图片,获取滑动距离  
distance = get\_distance(image1, image2)

\# 6.模拟人为滑动轨迹  
stacks = get\_stacks(distance)

\# 7.根据滑动轨迹进行滑动  
forward\_stacks = stacks\['forward\_stacks'\]  
back\_stacks = stacks\['back\_stacks'\]

slider\_button = driver.find\_element\_by\_class\_name('geetest\_slider\_button')  
time.sleep(0.2)

ActionChains(driver).click\_and\_hold(slider\_button).perform()

time.sleep(0.2)  
for forward\_stack in forward\_stacks:  
ActionChains(driver).move\_by\_offset(xoffset=forward\_stack, yoffset=0).perform()  
time.sleep(0.1)  
for back\_stack in back\_stacks:  
ActionChains(driver).move\_by\_offset(xoffset=back\_stack, yoffset=0).perform()  
time.sleep(0.1)

time.sleep(0.2)

ActionChains(driver).move\_by\_offset(xoffset=5, yoffset=0).perform()  
ActionChains(driver).move\_by\_offset(xoffset=-5, yoffset=0).perform()

ActionChains(driver).release().perform()

time.sleep(50)

finally:  
driver.close()

if \_\_name\_\_ == '\_\_main\_\_':  
main()![1713344-20190621221904436-158909690.png][]

转载于:https://www.cnblogs.com/badtimeandheroesaround/p/11067079.html

[1713344-20190621221904436-158909690.png]: /images/20211209/f1bbd6ab1154481a9954438dbe8ebe5f.png