一、自動登錄抽屜新熱榜
from selenium import webdriver
import time
driver = webdriver.Chrome(r'D:\BaiduNetdiskDownload\chromedriver_win32\chromedriver.exe')
# 把窗口轉成全屏
driver.maximize_window()
try:
driver.get('https://dig.chouti.com/')
driver.implicitly_wait(10)
time.sleep(5)
# 1、點擊登錄
login_btn = driver.find_element_by_id('login_btn')
login_btn.click()
time.sleep(2)
# 2、輸入用戶名
phone = driver.find_element_by_class_name('login-phone')
phone.send_keys('15622792660')
# 3、輸入密碼
pwd = driver.find_element_by_class_name('pwd-password-input')
pwd.send_keys('kermit46709394')
# 4、確認登錄
login_submit = driver.find_element_by_class_name('btn-large')
login_submit.click()
time.sleep(20)
# 捕獲異常並打印
except Exception as e:
print(e)
finally:
driver.close()
二、selenium選擇器之Xpath
from selenium import webdriver
driver = webdriver.Chrome(r'D:\BaiduNetdiskDownload\chromedriver_win32\chromedriver.exe')
try:
# 隱式等待: 寫在get請求前
driver.implicitly_wait(5)
driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html')
# 顯式等待: 寫在get請求后
# 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>
'''
# 根據xpath語法查找元素
# / 從根節點開始找第一個
html = driver.find_element_by_xpath('/html')
# html = driver.find_element_by_xpath('/head') # 報錯
print(html.tag_name)
# // 從根節點開始找任意一個節點
div = driver.find_element_by_xpath('//div')
print(div.tag_name)
# @
# 查找id為images的div節點
div = driver.find_element_by_xpath('//div[@id="images"]')
print(div.tag_name)
print(div.text)
# 找到第一個a節點
a = driver.find_element_by_xpath('//a')
print(a.tag_name)
# 找到所有a節點
a_s = driver.find_elements_by_xpath('//a')
print(a_s)
# 找到第一個a節點的href屬性
# get_attribute:獲取節點中某個屬性
a = driver.find_element_by_xpath('//a').get_attribute('href')
print(a)
finally:
driver.close()
三、selenium剩余操作
'''
點擊、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發送請求
# driver.get('https://www.jd.com/')
# # 找到輸入框輸入圍城
# input_tag = driver.find_element_by_id('key')
# input_tag.send_keys('圍城')
# # 鍵盤回車
# input_tag.send_keys(Keys.ENTER)
# time.sleep(2)
# # 找到輸入框輸入墨菲定律
# input_tag = driver.find_element_by_id('key')
# input_tag.clear()
# input_tag.send_keys('墨菲定律')
# # 找到搜索按鈕點擊搜索
# button = driver.find_element_by_class_name('button')
# button.click()
# time.sleep(10)
#
# finally:
# driver.close()
'''
獲取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()
'''
選項卡
'''
#選項卡管理：切換選項卡，有js的方式windows.open,有windows快捷鍵：
# 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: 執行javascrpit代碼
# # 彈窗操作
# # browser.execute_script('alert("tank")')
# # 新建瀏覽器窗口
# browser.execute_script(
# '''
# window.open();
# '''
# )
# time.sleep(1)
# print(browser.window_handles) # 獲取所有的選項卡
# # 切換到第二個窗口
# # 新:
# browser.switch_to.window(browser.window_handles[1])
# # 舊:
# # browser.switch_to_window(browser.window_handles[1])
#
# # 第二個窗口往淘寶發送請求
# browser.get('https://www.taobao.com')
# time.sleep(5)
#
# # 切換到第一個窗口
# browser.switch_to_window(browser.window_handles[0])
# browser.get('https://www.sina.com.cn')
#
# time.sleep(10)
# finally:
# browser.close()
'''
ActionChangs動作鏈
'''
# 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')
# # 切換到id為iframeResult的窗口內
# driver.switch_to.frame('iframeResult')
#
# # 源位置
# draggable = driver.find_element_by_id('draggable')
#
# # 目標位置
# droppable = driver.find_element_by_id('droppable')
#
# # 調用ActionChains，必須把驅動對象傳進去
# # 得到一個動作鏈對象，復制給一個變量
# actions = ActionChains(driver)
#
# # 方式一: 機器人
# # 瞬間把源圖片位置秒移到目標圖片位置
# # actions.drag_and_drop(draggable, droppable) # 編寫一個行為
# # actions.perform() # 執行編寫好的行為
#
#
# # 方式二: 模擬人的行為
# source = draggable.location['x']
# target = droppable.location['x']
# print(source, target)
#
# distance = target - source
# print(distance)
#
# # perform：每個動作都要調用perform執行
#
# # 點擊並摁住源圖片
# ActionChains(driver).click_and_hold(draggable).perform()
#
# s = 0
# while s < distance:
# # 執行位移操作
# ActionChains(driver).move_by_offset(xoffset=2, yoffset=0).perform()
# s += 2
#
# # 釋放動作鏈
# ActionChains(driver).release().perform()
#
# time.sleep(10)
#
#
# finally:
# driver.close()
'''
前進、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)
# # 前進操作
# driver.forward()
# time.sleep(1)
# driver.back()
# time.sleep(10)
#
# finally:
# driver.close()
四、破解登陸
from selenium import webdriver
from selenium.webdriver import ChromeOptions
import time
r'''
步驟:
1、打開文件的查看，顯示隱藏文件
2、找到C:\Users\administortra\AppData\Local\Google\Chrome\User Data
刪除Default文件
3、重新打開瀏覽器，並登陸百度賬號
- 此時會創建一個新的Default緩存文件
4、添加cookies
5、關閉谷歌瀏覽器后執行程序
'''
# 獲取options對象，參數對象
options = ChromeOptions()
# 獲取cookies保存路徑
# 'C:\Users\administortra\AppData\Local\Google\Chrome\User Data'
profile_directory = r'--user-data-dir=C:\Users\administortra\AppData\Local\Google\Chrome\User Data'
# 添加用戶信息目錄
options.add_argument(profile_directory)
# 把參數加載到當前驅動中 chrome_options默認參數，用來接收options對象
driver = webdriver.Chrome(chrome_options=options)
try:
driver.implicitly_wait(10)
driver.get('https://www.baidu.com/')
'''
BDUSS:*****
'''
# 添加用戶cookies信息
# name、value必須小寫
driver.add_cookie({"name": "BDUSS", "value": "用戶session字符串"})
# 刷新操作
driver.refresh()
time.sleep(10)
finally:
driver.close()
五、selenium爬取京東商品信息
# ''''''
# '''
# 爬取京東商品信息:
# 請求url:
# https://www.jd.com/
# 提取商品信息:
# 1.商品詳情頁
# 2.商品名稱
# 3.商品價格
# 4.評價人數
# 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、往京東主頁發送請求
# driver.get('https://www.jd.com/')
#
# # 2、輸入商品名稱，並回車搜索
# input_tag = driver.find_element_by_id('key')
# input_tag.send_keys('macbook')
# input_tag.send_keys(Keys.ENTER)
# time.sleep(2)
#
# # 通過JS控制滾輪滑動獲取所有商品信息
# js_code = '''
# window.scrollTo(0,5000);
# '''
# driver.execute_script(js_code) # 執行js代碼
#
# # 等待數據加載
# 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:
# # 根據屬性選擇器查找
# # 商品鏈接
# good_url = good.find_element_by_css_selector(
# '.p-img a').get_attribute('href')
#
# # 商品名稱
# good_name = good.find_element_by_css_selector(
# '.p-name em').text.replace("\n", "--")
#
# # 商品價格
# good_price = good.find_element_by_class_name(
# 'p-price').text.replace("\n", ":")
#
# # 評價人數
# 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'''
# 商品鏈接: {good_url}
# 商品名稱: {good_name}
# 商品價格: {good_price}
# 評價人數: {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('下一頁')
#
# next_tag.click()
#
# time.sleep(10)
#
#
# finally:
# driver.close()
六、破解極驗滑動驗證
'''
破解極驗滑動驗證
博客園登錄url:
https://account.cnblogs.com/signin?returnUrl=https%3A%2F%2Fwww.cnblogs.com%2F
1、輸入用戶名與密碼，並點擊登錄
2、彈出滑動驗證，獲取有缺口與完整的圖片
3、通過像素點進行比對，獲取滑動位移距離
4、模擬人的行為軌跡
5、開始滑動
'''
from selenium import webdriver # 用來驅動瀏覽器的
from selenium.webdriver import ActionChains # 破解滑動驗證碼的時候用的 可以拖動圖片
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自帶的截圖網頁全屏圖片
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')
# 對屏幕進行截取,獲取滑動驗證圖片
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)
# 截取圖片
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)
# 截取圖片
img_obj = get_snap(driver)
return img_obj
def get_distance(image1, image2):
# 初始值
start = 60
# 滑塊色差
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
'''
勻加速\減速運行
v = v0 + a * t
位移:
s = v * t + 0.5 * a * (t**2)
'''
# 初速度
v0 = 0
# 加減速度列表
a_list = [3, 4, 5]
# 時間
t = 0.2
# 初始位置
s = 0
# 向前滑動軌跡
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.輸入用戶名與密碼,點擊登錄
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.')
# 這里需要等待賬號密碼輸入完畢后再點擊登錄按鈕，否則的不彈框
time.sleep(1)
login_button.click()
# time.sleep(3)
# 2.點擊滑動驗證按鈕,獲取圖片
geetest_button = driver.find_element_by_class_name('geetest_slider_button')
geetest_button.click()
time.sleep(0.2)
# 3.針對完整的圖片進行截取
image1 = get_image1(driver)
# 4.針對有缺口的圖片進行截取
image2 = get_image2(driver)
# 5.對比兩張圖片,獲取滑動距離
distance = get_distance(image1, image2)
# 6.模擬人為滑動軌跡
stacks = get_stacks(distance)
# 7.根據滑動軌跡進行滑動
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()