从PDF和图像中提取文本，以供大型语言模型使用

pip install pypdfium2
1.

def convert_pdf_to_images(file_path, scale=300/72):
   
   pdf_file = pdfium.PdfDocument(file_path)
   
   page_indices = [i for i in range(len(pdf_file))]
   
   renderer = pdf_file.render(
       pdfium.PdfBitmap.to_pil,
       page_indices = page_indices, 
       scale = scale,
   )
   
   final_images = [] 
   
   for i, image in zip(page_indices, renderer):
       
       image_byte_array = BytesIO()
       image.save(image_byte_array, format='jpeg', optimize=True)
       image_byte_array = image_byte_array.getvalue()
       final_images.append(dict({i:image_byte_array}))
   
   return final_images
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.

def display_images(list_dict_final_images):
   
   all_images = [list(data.values())[0] for data in list_dict_final_images]
   
   for index, image_bytes in enumerate(all_images):
       
       image = Image.open(BytesIO(image_bytes))
       figure = plt.figure(figsize = (image.width / 100, image.height / 100))
       
       plt.title(f"----- Page Number {index+1} -----")
       plt.imshow(image)
       plt.axis("off")
       plt.show()
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.

convert_pdf_to_images = convert_pdf_to_images('Experimentation_file.pdf')
display_images(convert_pdf_to_images)
1.
2.

pip install pytesseract
1.

from pytesseract import image_to_string
def extract_text_with_pytesseract(list_dict_final_images):
   
   image_list = [list(data.values())[0] for data in list_dict_final_images]
   image_content = []
   
   for index, image_bytes in enumerate(image_list):
       
       image = Image.open(BytesIO(image_bytes))
       raw_text = str(image_to_string(image))
       image_content.append(raw_text)
   
   return "\n".join(image_content)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.

text_with_pytesseract = extract_text_with_pytesseract(convert_pdf_to_images)
print(text_with_pytesseract)
1.
2.

This document provides a quick summary of some of Zoumana’s article on Medium.
It can be considered as the compilation of his 80+ articles about Data Science, Machine Learning and
Machine Learning Operations.
...
Pytesseract was able to extract the content of the image.
Here is how it managed to do it!
Pytesseract starts by identifying rectangular shapes within the input image from top-right to bottom-right. Then it extracts the content of the individual images, and the final result is the concatenation of those extracted content. This approach works perfectly when dealing with column-based PDFs and image documents.
...
1.
2.
3.
4.
5.
6.
7.
8.

!pip install opencv-python-headless==4.1.2.30
1.

!pip install easyocr
1.

from easyocr import Reader

# Load model for the English language
language_reader = Reader(["en"])
1.
2.
3.
4.

def extract_text_with_easyocr(list_dict_final_images):
   
   image_list = [list(data.values())[0] for data in list_dict_final_images]
   image_content = []
   
   for index, image_bytes in enumerate(image_list):
       
       image = Image.open(BytesIO(image_bytes))
       raw_text = language_reader.readtext(image)
       raw_text = " ".join([res[1] for res in raw_text])
                      
       image_content.append(raw_text)
   
   return "\n".join(image_content)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.

text_with_easy_ocr = extract_text_with_easyocr(convert_pdf_to_images)
print(text_with_easy_ocr)
1.
2.

!pip install PyPDF2
1.

def extract_text_with_pyPDF(PDF_File):

    pdf_reader = PdfReader(PDF_File)
    
    raw_text = ''

    for i, page in enumerate(pdf_reader.pages):
        
        text = page.extract_text()
        if text:
            raw_text += text

    return raw_text
text_with_pyPDF = extract_text_with_pyPDF("Experimentation_file.pdf")
print(text_with_pyPDF)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.

!pip install langchain
1.

from langchain.document_loaders.image import UnstructuredImageLoader
1.

def extract_text_with_langchain_image(list_dict_final_images):
   image_list = [list(data.values())[0] for data in list_dict_final_images]
   image_content = []
   
   for index, image_bytes in enumerate(image_list):
       
       image = Image.open(BytesIO(image_bytes))
       loader = UnstructuredImageLoader(image)
       data = loader.load()
       raw_text = data[index].page_content
                      
       image_content.append(raw_text)
   
   return "\n".join(image_content)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.

text_with_langchain_image = extract_text_with_langchain_image(convert_pdf_to_images)
print(text_with_langchain_image)
1.
2.

from langchain.document_loaders import UnstructuredFileLoader
def extract_text_with_langchain_pdf(pdf_file):
   
   loader = UnstructuredFileLoader(pdf_file)
   documents = loader.load()
   pdf_pages_content = '\n'.join(doc.page_content for doc in documents)
   
   return pdf_pages_content
text_with_langchain_files = extract_text_with_langchain_pdf("Experimentation_file.pdf")
print(text_with_langchain_files)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.