update demo model json and code

This commit is contained in:
赵小蒙
2024-06-25 17:38:11 +08:00
parent 7dcf63e69c
commit 63a4a06255
3 changed files with 24 additions and 39021 deletions
+22
View File
@@ -0,0 +1,22 @@
import os
import json
from magic_pdf.pipe.UNIPipe import UNIPipe
from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
current_script_dir = os.path.dirname(os.path.abspath(__file__))
demo_name = "demo1"
pdf_path = os.path.join(current_script_dir, f"{demo_name}.pdf")
model_path = os.path.join(current_script_dir, f"{demo_name}.json")
pdf_bytes = open(pdf_path, "rb").read()
model_json = json.loads(open(model_path, "r", encoding="utf-8").read())
jso_useful_key = {"_pdf_type": "", "model_list": model_json}
local_image_dir = os.path.join(current_script_dir, 'images')
image_dir = str(os.path.basename(local_image_dir))
image_writer = DiskReaderWriter(local_image_dir)
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
pipe.pipe_classify()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
with open(f"{demo_name}.md", "w", encoding="utf-8") as f:
f.write(md_content)
+1 -24521
View File
File diff suppressed because one or more lines are too long
+1 -14500
View File
File diff suppressed because one or more lines are too long