CNOCR、PaddleOCR和Tesseract提取pdf中文字-个人记录

目录

一、PyMuPDF

二、CNOCR

 三、PaddleOCR

四、Tesseract

五、个人测试对比

---

一、PyMuPDF

1.安装PyMuPDF

pip install pymupdf

2.pdf转txt样例

import os
import datetime
import fitz  # fitz就是pip install PyMuPDF


def pyMuPDF_fitz(pdfPath):
    startTime_pdf2img = datetime.datetime.now()  # 开始时间

    text_list = []
    pdfDoc = fitz.open(pdfPath)
    for page in pdfDoc:
        text = page.get_text()
        text_list.append(text)
    text_list = "\n".join(text_list)
    try:
        with open("/home/bingxing2/ailab/group/ai4agr/wzf/LLM/txt/test.txt", 'a+') as neirong:
            neirong.write(text_list)
    except IOError as e:
        print("An error occurred while writing the file:", e)


    endTime_pdf2img = datetime.datetime.now()  # 结束时间
    print('pdf2img时间=', (endTime_pdf2img - startTime_pdf2img).seconds)


def process_all_pdfs_in_directory(directory):
    for filename in os.listdir(directory):
        if filename.endswith('.pdf'):
            pdf_path = os.path.join(directory, filename)
            pyMuPDF_fitz(pdf_path)


if __name__ == "__main__":
    # 指定PDF所在的目录
    pdf_directory = r'/home/bingxing2/ailab/group/ai4agr/wzf/LLM/pdf/'
    process_all_pdfs_in_directory(pdf_directory)

注：

pymupdf不能直接提取表格，要使用pdfplumber来实现

提取图片使用img=page.getImageList()

提取后发现，文字可以正常提取但是数字不能正常提取

原因：数字在PDF文件中以图像形式呈现，而不是文本形式。这种情况下，提取数字就需要进行OCR（光学字符识别）处理

因此先将pdf转为图片，在对图片提取文字（采用cnocr、paddleocr、tesseract）

pdf转图片：

import os
import datetime
import fitz  # fitz就是pip install PyMuPDF


def pdf_to_images(directory, filename, output_folder):

    pdf_path = os.path.join(directory, filename)
    pdf_doc = fitz.open(pdf_path)
    for page_number in range(len(pdf_doc)):
        page = pdf_doc[page_number]
        image = page.get_pixmap(matrix=fitz.Matrix(4, 4), alpha=False)
        image_path = os.path.join(output_folder, f"{filename[:-4]}_page_{page_number + 1}.png")
        image.save(image_path)
    pdf_doc.close()

def process_all_pdfs_in_directory(directory, output_folder):
    #pdf to img
    for filename in os.listdir(directory):
        if filename.endswith('.pdf'):
            pdf_to_images(directory, filename, output_folder)


if __name__ == "__main__":
    # 指定PDF所在的目录
    pdf_directory = r'/home/bingxing2/ailab/group/ai4agr/wzf/LLM/pdf/books/'
    # 指定输出图片的目录
    output_folder = r'/home/bingxing2/ailab/group/ai4agr/wzf/LLM/images/books/'
    process_all_pdfs_in_directory(pdf_directory, output_folder)

二、CNOCR

1.安装cnocr

pip install cnocr

2.图片转文字，存入同一个txt文件

import cnocr
import os
import datetime

def recognize_text(txt_directory, image_directory):
    # 初始化 cnocr
   ocr = cnocr.CnOcr()

   text = []
   for filename in os.listdir(image_directory):
      if filename.endswith('.png'):