使用Python提取PDF文件中内容的代码示例和使用技巧

pip install PyPDF2

import PyPDF2

def extract_text_from_pdf(pdf_path):
    with open(pdf_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        text = ""
        for page in reader.pages:
            text += page.extract_text()
        return text

# 使用示例
pdf_path = 'example.pdf'
extracted_text = extract_text_from_pdf(pdf_path)
print(extracted_text)

pip install pdfplumber

import pdfplumber

def extract_text_from_pdf(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        text = ""
        for page in pdf.pages:
            text += page.extract_text()
        return text

# 使用示例
pdf_path = 'example.pdf'
extracted_text = extract_text_from_pdf(pdf_path)
print(extracted_text)

pip install pytesseract pillow pdf2image

sudo apt install tesseract-ocr libpoppler-cpp-dev  # Ubuntu/Debian
brew install tesseract poppler                    # macOS (Homebrew)
pip install pytesseract pillow pdf2image

from pdf2image import convert_from_path
import pytesseract
from PIL import Image

def extract_text_from_scanned_pdf(pdf_path):
    # 将 PDF 转换为图像列表
    images = convert_from_path(pdf_path)

    extracted_text = ""
    for image in images:
        # 对每张图片执行 OCR
        text = pytesseract.image_to_string(image)
        extracted_text += text + "\n"

    return extracted_text

# 使用示例
pdf_path = 'scanned_example.pdf'
text = extract_text_from_scanned_pdf(pdf_path)
print(text)