paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Feature: page count (#7750)

Browse Source 
---------

Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
This commit is contained in:
s0llvan
2024-09-25 17:22:12 +02:00
committed by GitHub
parent 4adf20af1e
commit c92c3e224a
23 changed files with 319 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/paperless_tesseract/parsers.py
View File

@@ -41,6 +41,15 @@ class RasterisedDocumentParser(DocumentParser):
"""
return OcrConfig()
def get_page_count(self, document_path, mime_type):
page_count = None
if mime_type == "application/pdf":
import pikepdf
with pikepdf.Pdf.open(document_path) as pdf:
page_count = len(pdf.pages)
return page_count
def extract_metadata(self, document_path, mime_type):
result = []
if mime_type == "application/pdf":