Paddle implements the content of pdf

• Source link

1. Environment installation

• installpaddlepaddle
  • gpu version

    python -m pip install paddlepaddle-gpu -i https://pypi.tuna.tsinghua.edu.cn/simple
    

  • CPU version:

    python -m pip install paddlepaddle -i https://pypi.tuna.tsinghua.edu.cn/simple
    

• Install Paddle OCR

  pip install "paddleocr>=2.0.1" # Recommend to use version 2.0.1+
  

• other libraries

  pip install Pillow==9.5.0
  pip install fitz==0.0.1.dev2
  pip install numpy==1.24.4
  pip install PyMuPDF==1.19.0
  pip install opencv-python==4.6.0.66
  

2. Implement the code

• the code

  import cv2
  import fitz
  import numpy as np
  from PIL import Image
  from paddleocr import PaddleOCR, draw_ocr
  
  ocr = PaddleOCR(use_angle_cls=True, lang="ch", page_num=427)  # page_num=pdf文件页数
  img_path = 'data/深度学习进阶自然语言处理.pdf'
  result = ocr.ocr(img_path, cls=True)
  for idx in range(len(result)):
      res = result[idx]
      for line in res:
          print(line)
  
  # draw result
  imgs = []
  with fitz.open(img_path) as pdf:
      for pg in range(0, pdf.pageCount):
          page = pdf[pg]
          mat = fitz.Matrix(2, 2)
          pm = page.getPixmap(matrix=mat, alpha=False)
          # if width or height > 2000 pixels, don't enlarge the image
          if pm.width > 2000 or pm.height > 2000:
              pm = page.getPixmap(matrix=fitz.Matrix(1, 1), alpha=False)
  
          img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples)
          img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
          imgs.append(img)
  
  for idx in range(len(result)):
      # 保存获取的文本
      with open(f'data/data_txt/text_{
          
          idx}.txt', 'w', encoding='utf-8') as f:
          res = result[idx]
          image = imgs[idx]
          boxes = [line[0] for line in res]
          txts = [line[1][0] for line in res]
          for line in txts:
              f.write(line)
              f.write('\n')
          scores = [line[1][1] for line in res]
          im_show = draw_ocr(image, boxes, txts, scores, font_path='doc/fonts/simfang.ttf')
          im_show = Image.fromarray(im_show)
          # 保存图片
          im_show.save('data/images/page_{}.jpg'.format(idx))
  

• Result display