spider/js_reverse
1
0
Fork 0
mirror of https://github.com/luzhisheng/js_reverse.git synced 2025-04-12 11:37:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

提取pdf文件中图片和文字

Browse Source
This commit is contained in:
aiyingfeng 2023-08-05 10:41:28 +08:00
parent 9ce7645354
commit 4cefde375c
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pdf处理/program/pdf_base.py
View File

@ -110,7 +110,7 @@ class PDFBase(Base):
# 替换空单元格
pf.fillna(' ', inplace=True)
# 输出
pf = pf.sort_values(by='样品名称')
pf = pf.sort_values(by='文件名')
pf.to_excel(file_path, index=False)
# 保存表格
file_path.close()

3
pdf处理/program/testing_agency_report.py
View File

@ -126,7 +126,8 @@ class TestingAgencyReport(PDFBase):
'检测项目': '',
'标志': '',
'签发日期': '',
'公司名称': ''
'公司名称': '',
'文件名': ''
}
self.remove_img(img_path)
if entry.is_file():