【Python】利用python和百度通用OCR文字识别模型处理pdf文件（有水印且加密）

import win32com.client as win32import os word = win32.gencache.EnsureDispatch('Word.Application')# 是否显示。如果这里是True，桌面上会展示打开word再关掉的过程。# 是False的话这个过程不会显示出来word.Visible =Falseoutput = word.Documents.Add()   output.Application.Selection.InsertFile('111.pdf')output.SaveAs('111.docx') output.Close()

from pdf2docx import Converterpdf_file = 'demo.pdf'docx_file = 'demo.docx'cv = Converter(pdf_file)cv.convert(docx_file, start=0, end=None)cv.close()

from PIL import Imagefrom itertools import productimport fitzimport os
def remove_pdf():    page_num = 0    pdf_file = input("请输入 pdf 地址：")    pdf = fitz.open(pdf_file);    for page in pdf:        pixmap = page.get_pixmap()        for pos in product(range(pixmap.width), range(pixmap.height)):            rgb = pixmap.pixel(pos[0], pos[1])            if(sum(rgb) >= 520):                pixmap.set_pixel(pos[0], pos[1], (255, 255, 255))        pixmap.pil_save(f"pdf_images/{page_num}.jpg",quality=100,dpi=(1800,1800))        print(f"第{page_num}水印去除完成")        page_num = page_num + 1
remove_pdf()

# encoding:utf-8import requests
# client_id 为官网获取的AK， client_secret 为官网获取的SKhost = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=你的ak（创建应用后看得到）&client_secret=你的sk（创建应用后看得到）'response = requests.get(host)if response:    print(response.json())

# encoding:utf-8
import requestsimport base64
page_num=0words = []
for i in range(96):
    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic"
    # 二进制方式打开图片文件    f = open(f"pdf_images/{page_num}.jpg", 'rb')    img = base64.b64encode(f.read())
    params = {"image": img}
    access_token = '[刚才拿到的access_token复制到这里]'    request_url = request_url + "?access_token=" + access_token    headers = {'content-type': 'application/x-www-form-urlencoded'}    response = requests.post(request_url, data=params, headers=headers)    # if response:    #     print(response.json())
    words_result = response.json()['words_result']
    for i in range(len(words_result)):        words.append(words_result[i]['words'])
    page_num+=1
print(''.join(words))
with open("test.txt","w") as f:    f.write(''.join(words))