chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/binary-husky/chatgpt_academic into master

Browse Source
This commit is contained in:
qingxu fu 2023-09-11 14:49:37 +08:00
commit e699b6b13f
2 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
crazy_functions/crazy_utils.py
View File

@ -469,6 +469,7 @@ def read_and_clean_pdf_text(fp):
'- ', '') for t in text_areas['blocks'] if 'lines' in t] '- ', '') for t in text_areas['blocks'] if 'lines' in t]
############################## <第 2 步，获取正文主字体> ################################## ############################## <第 2 步，获取正文主字体> ##################################
try:
fsize_statiscs = {} fsize_statiscs = {}
for span in meta_span: for span in meta_span:
if span[1] not in fsize_statiscs: fsize_statiscs[span[1]] = 0 if span[1] not in fsize_statiscs: fsize_statiscs[span[1]] = 0
@ -476,7 +477,8 @@ def read_and_clean_pdf_text(fp):
main_fsize = max(fsize_statiscs, key=fsize_statiscs.get) main_fsize = max(fsize_statiscs, key=fsize_statiscs.get)
if REMOVE_FOOT_NOTE: if REMOVE_FOOT_NOTE:
give_up_fize_threshold = main_fsize * REMOVE_FOOT_FFSIZE_PERCENT give_up_fize_threshold = main_fsize * REMOVE_FOOT_FFSIZE_PERCENT
except:
raise RuntimeError(f'抱歉, 我们暂时无法解析此PDF文档: {fp}。')
############################## <第 3 步，切分和重新整合> ################################## ############################## <第 3 步，切分和重新整合> ##################################
mega_sec = [] mega_sec = []
sec = [] sec = []

2
crazy_functions/latex_fns/latex_toolbox.py
View File

@ -423,7 +423,7 @@ def compile_latex_with_timeout(command, cwd, timeout=60):
def merge_pdfs(pdf1_path, pdf2_path, output_path): def merge_pdfs(pdf1_path, pdf2_path, output_path):
import PyPDF2 import PyPDF2
Percent = 0.8 Percent = 0.95
# Open the first PDF file # Open the first PDF file
with open(pdf1_path, 'rb') as pdf1_file: with open(pdf1_path, 'rb') as pdf1_file:
pdf1_reader = PyPDF2.PdfFileReader(pdf1_file) pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)