腾讯云OCR

# -*- coding:utf-8 -*-
# @author:Ye Zhoubing
# @datetime:2024/10/15 19:03
# @software: PyCharm
"""
selenium+腾讯云OCR识别计算型验证码
直接从网站下载excel结果文件
todo: 下载文件的保存名，目前默认保存路径为：C:\DataDownload
"""
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import time
import shutil
import os
import pyautogui as ui
import pyperclip
import re
from time import sleep
​
file_dir = (r'E:\git\excel_ocr\test')   # 要上传的文件夹路径
def clear_folder(folder_path):
    # 使用shutil模块的rmtree函数删除文件夹及其内部的所有文件
    shutil.rmtree(folder_path)
​
    # 使用os模块的makedirs函数重新创建一个同名的空文件夹
    os.makedirs(folder_path)
​
# 设置保存路径
save_file = file_dir + r'\ocr_result'
if not os.path.exists(save_file):
    os.mkdir(save_file)
else:
    clear_folder(save_file)  # 清空文件夹并创建一个新的
​
def extract_number(filename):
    # 使用正则表达式提取 p 和 _ 之间的数字部分
    match = re.search(r'_p(\d+)_', filename)
    if match:
        return int(match.group(1))
    else:
        return 0
​
def file_number(filename):
    # 使用正则表达式提取括号中的数字部分
    match = re.search(r'\((\d+)\)', filename)
    if match:
        return int(match.group(1))
    else:
        return 0
def find_files(path):
    files = []
    for name in os.listdir(path):
        full_path = os.path.join(path, name)
        if os.path.isdir(full_path):
            continue
        if os.path.isfile(full_path):
            files.append(name)
    return files
​
chrome_options = webdriver.ChromeOptions()
​
chrome_options.add_argument(r'--user-data-dir=C:\Users\Lenovo\AppData\Local\Google\Chrome\User Data - bak')
# 设置默认保存路径
down_load_path = r'C:\DataDownload'
prefs = {'download.default_directory': down_load_path  # 设置默认下载路径
}
chrome_options.add_experimental_option('prefs', prefs)
​
​
# chrome_options.add_argument(r'--profile-directory=Default')
url = 'https://ocrdemo.cloud.tencent.com/?from=22812'
chromedriver_position = r'E:\git\houdunren\chromedriver-win64\chromedriver-win64\chromedriver.exe'
driver = webdriver.Chrome(options=chrome_options, service=Service(chromedriver_position)) #原先的chrome_options已弃用
driver.get(url)
​
# 点击表格识别v3
​
# 点击上传本地文件（这里会要你微信扫码登录）
# todo: 修改对应的元素位置，这里只是之前的示例
upfile_names = find_files(file_dir)
i = 0
sorted_upfile_names = sorted(upfile_names, key=extract_number)
​
sleep(3)  # 给时间缓冲
# 点击`表格v3`
result = driver.find_element(By.XPATH, r'/html/body/div[1]/div/div[2]/div/div[1]/div[2]/div[2]/ul/li[3]/ul/li[10]/a/div')
result.click()
sleep(2)
​
# 扫码登录（手动）
upfile = driver.find_element(By.XPATH, r'//*[@id="root"]/div/div[2]/div/div[3]/div/div[2]/div/div[3]/div[1]/span/span/button/span')
upfile.click()
sleep(10)  # 给10s时间扫码登录
​
# 点击`表格v3`
result = driver.find_element(By.XPATH, r'/html/body/div[1]/div/div[2]/div/div[1]/div[2]/div[2]/ul/li[3]/ul/li[10]/a/div')
result.click()
sleep(2)
​
​
for upfile_name in sorted_upfile_names:
    # 点击`上传本地文件`
    upfile = driver.find_element(By.XPATH, r'//*[@id="root"]/div/div[2]/div/div[3]/div/div[2]/div/div[3]/div[1]/span/span/button/span')
    upfile.click()
    sleep(2)
    # 使用send_keys方法上传文件
    # 写入文件
    pyperclip.copy(file_dir + '\\' + upfile_name)   # 复制文件路径
    sleep(0.5)
​
    # 模拟按下Ctrl+V粘贴
    ui.hotkey('Ctrl', 'V')
​
    # 回车
    ui.typewrite("\n", interval=2)
    sleep(0.5)
    # 输入回车键, presses表示按的次数，按一次不会生效，有可能是执行太快，建议presses=2
    # ui.press('enter')
    # sleep(5)
​
    # # 点击识别
    # result = driver.find_element(By.XPATH,r'//*[@id="root"]/div/div[2]/div/div[4]/div/footer/button/span')
    # result.click()
​
    sleep(3)  # 给时间缓冲识别
​
    # 点击导出表格(没有这个按钮，但自己手动上传后是有的)
    result = driver.find_element(By.XPATH,r'/html/body/div[1]/div/div[2]/div/div[4]/div/div/div[2]/div/div/p/button[2]/span')
    result.click()
    print(upfile_name + "识别完成")
​