修复pdf分解bug

This commit is contained in:
Your Name 2023-04-18 16:14:30 +08:00
parent 4c486f27c8
commit d35d7710c1

View File

@ -444,6 +444,7 @@ def read_and_clean_pdf_text(fp):
pf = 998
for l in t['lines']:
txt_line = "".join([wtf['text'] for wtf in l['spans']])
if len(txt_line) == 0: continue
pf = primary_ffsize(l)
meta_line.append([txt_line, pf, l['bbox'], l])
for wtf in l['spans']: # for l in t['lines']: