opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-10-30 19:33:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

update code

Browse Source
This commit is contained in:
xuchao
2024-03-14 21:08:12 +08:00
parent 59b0b0c3da
commit f68c66290c
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
magic_pdf/pdf_parse_by_model.py
-1
View File
@@ -257,7 +257,6 @@ def parse_pdf_by_model(
footnote_bboxes_by_model = parse_footnotes_by_model(page_id, page, model_output_json, md_bookname_save_path, debug_mode=debug_mode)
# 通过规则识别到的footnote
footnote_bboxes_by_rule = parse_footnotes_by_rule(remain_text_blocks, page_height, page_id, main_text_font)
"""进入pdf过滤器，去掉一些不合理的pdf"""
is_good_pdf, err = pdf_filter(page, remain_text_blocks, table_bboxes, image_bboxes)
if not is_good_pdf: