python读取pdf文档 - IT评测·应用市场-qidao123.com

import io
import pdfplumber
from opencc import OpenCC
import fitz # pymupdf
import os
file_path = '/document/pdf/xxx.pdf'
output_dir = '/classification/pdf/images'
#获取图片 demo
def extract_images_from_pdf(pdf_path, output_dir):
# 确保输出目录存在
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# 打开PDF文件
doc = fitz.open(pdf_path)
page_count = doc.page_count
# 遍历PDF的每一页
for page_num in range(page_count):
page = doc.load_page(page_num)
# 获取页面中的图片信息
images = page.get_images(full=True)
image_index = 0
for img_index, img in enumerate(images):
xref = img[0]
base_image = doc.extract_image(xref)
image_bytes = base_image["image"]
image_ext = base_image["ext"]
# 使用Pillow将图片保存到本地
from PIL import Image
image = Image.open(io.BytesIO(image_bytes))
image_path = os.path.join(output_dir, f"image_{page_num + 1}_{image_index + 1}.{image_ext}")
image.save(image_path)
image_index += 1
doc.close()
# 使用示例
extract_images_from_pdf(file_path, output_dir)
cc = OpenCC('t2s')
def read_pdf_with_pdfplumber(file_path):
images = []
with (pdfplumber.open(file_path) as pdf):
num_pages = len(pdf.pages)
print(f"Number of pages: {num_pages}")
text = pdf.pages[0].extract_text()
text = cc.convert(text)
print(text)
# 示例用法
read_pdf_with_pdfplumber(file_path)

复制代码