pymupdf 剖析 PDF - ToB企服应用市场:ToB评测及商务社交产业平台

复制代码

复制代码

def extract_image(pdf_path):
doc = pymupdf.open(pdf_path) # open a document
image_path_list = []
rad_prefix = ''.join(random.choices(string.ascii_letters, k=5))
Path(f"images/{rad_prefix}").mkdir(parents=True)
for page_index in range(len(doc)): # iterate over pdf pages
page = doc[page_index] # get the page
image_list = page.get_images()
# print the number of images found on the page
if image_list:
print(f"Found {len(image_list)} images on page {page_index}")
else:
print("No images found on page", page_index)
for image_index, img in enumerate(image_list, start=1): # enumerate the image list
xref = img[0] # get the XREF of the image
pix = pymupdf.Pixmap(doc, xref) # create a Pixmap
if pix.n - pix.alpha > 3: # CMYK: convert to RGB first
pix = pymupdf.Pixmap(pymupdf.csRGB, pix)
image_path = Path("images/%s/page_%s-image_%s.png" % (rad_prefix,page_index, image_index)).absolute()
image_path_list.append(image_path)
pix.pil_save(image_path) # save the image as png
pix = None
return image_path_list

复制代码

import gradio as gr
import pdf
def covnert_pdf(x):
print(x)
md_content = pdf.convert_to_md(x)
image_list = pdf.extract_image(x)
return [md_content , image_list]
with gr.Blocks() as demo:
gr.Markdown(
value="# PDF 提取"
)
with gr.Tab("Markdown"):
md = gr.Markdown(
height=500
)
with gr.Tab("Images"):
gallery = gr.Gallery(columns=4, object_fit="None", height="auto", show_download_button=True)
with gr.Row():
go_btn = gr.UploadButton()
go_btn.upload(covnert_pdf, go_btn, [md, gallery])
from apscheduler.schedulers.background import BackgroundScheduler
demo.launch()

复制代码