mirror of
https://github.com/opendatalab/MinerU.git
synced 2026-09-24 23:10:23 +08:00
update demo model json and code
This commit is contained in:
@@ -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
File diff suppressed because one or more lines are too long
+1
-14500
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user