andre/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' into v3.1

Browse Source
This commit is contained in:
505030475
2023-04-18 23:33:49 +08:00
parent 40d91e9e1a 0a5464d7d6
commit abd11e5dff
3 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
crazy_functions/crazy_utils.py
View File

@ -448,6 +448,7 @@ 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']:
@ -558,8 +559,8 @@ def read_and_clean_pdf_text(fp):
meta_txt = meta_txt.replace('\n', '\n\n')
############################## <第 5 步，展示分割效果> ##################################
for f in finals:
print亮黄(f)
print亮绿('***************************')
# for f in finals:
# print亮黄(f)
# print亮绿('***************************')
return meta_txt, page_one_meta