opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-09-24 23:10:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix 参数名称

Browse Source
This commit is contained in:
赵小蒙
2024-04-15 22:15:30 +08:00
parent 0b01a34687
commit 7b937d58b8
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
magic_pdf/libs/pdf_image_tools.py
+2 -2
View File
@@ -1,4 +1,4 @@
from magic_pdf.io.AbsReaderWriter import AbsReaderWriter
from magic_pdf.libs.commons import fitz
from loguru import logger
from magic_pdf.libs.commons import join_path
@@ -28,7 +28,7 @@ def cut_image(bbox: tuple, page_num: int, page: fitz.Page, return_path, imageWri
byte_data = pix.tobytes(output='jpeg', jpg_quality=95)
imageWriter.write(content=byte_data, path=img_hash256_path, mode="binary")
imageWriter.write(byte_data, img_hash256_path, AbsReaderWriter.MODE_BIN)
return img_hash256_path
magic_pdf/pipe/UNIPipe.py
+4 -4
View File
@@ -105,8 +105,8 @@ if __name__ == '__main__':
pdf_file_path = r"linshixuqiu\25536-00.pdf"
model_file_path = r"linshixuqiu\25536-00.json"
pdf_bytes = drw.read(path=pdf_file_path, mode=AbsReaderWriter.MODE_BIN)
model_json_txt = drw.read(path=model_file_path, mode=AbsReaderWriter.MODE_TXT)
pdf_bytes = drw.read(pdf_file_path, AbsReaderWriter.MODE_BIN)
model_json_txt = drw.read(model_file_path, AbsReaderWriter.MODE_TXT)
pdf_type = UNIPipe.classify(pdf_bytes)
logger.info(f"pdf_type is {pdf_type}")
@@ -122,5 +122,5 @@ if __name__ == '__main__':
md_content = pipe.mk_markdown(pdf_mid_data, "imgs")
md_writer = DiskReaderWriter(write_path)
md_writer.write(content=md_content, path="25536-00.md", mode=AbsReaderWriter.MODE_TXT)
md_writer.write(content=json.dumps(JsonCompressor.decompress_json(pdf_mid_data), ensure_ascii=False, indent=4), path="25536-00.json", mode=AbsReaderWriter.MODE_TXT)
md_writer.write(md_content, "25536-00.md", AbsReaderWriter.MODE_TXT)
md_writer.write(json.dumps(JsonCompressor.decompress_json(pdf_mid_data), ensure_ascii=False, indent=4), "25536-00.json", AbsReaderWriter.MODE_TXT)