From ce75d11b3e42eeddbd4166bd601b0117da5a5f32 Mon Sep 17 00:00:00 2001 From: Joe Seki <joeseki@proton.me> Date: Sun, 9 Jun 2024 19:02:59 +0200 Subject: [PATCH] Attrap: embarque une version locale de OCRmyPDF Closes !8 Co-authored-by: Joe Seki <joeseki@proton.me> Co-authored-by: Bastien Le Querrec <blq@laquadrature.net> --- Attrap.py | 3 ++- README.md | 2 +- requirements.txt | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/Attrap.py b/Attrap.py index 6527cac..96daf36 100644 --- a/Attrap.py +++ b/Attrap.py @@ -494,7 +494,8 @@ class Attrap: def ocr(self, raa, retry_on_failure=True): """OCRise un RAA""" cmd = [ - 'ocrmypdf', + 'python3', + 'bin/ocrmypdf', '-l', 'eng+fra', '--output-type', 'pdf', '--redo-ocr', diff --git a/README.md b/README.md index 53ce752..20aaafe 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ source bin/activate pip3 install -r requirements.txt ``` -Vous devez avoir installé OCRmyPDF, les données `eng` et `fra` de Tesseract, et le démon Tor. +Vous devez avoir installé les données `eng` et `fra` de Tesseract et le démon Tor. ### Configuration du démon Tor diff --git a/requirements.txt b/requirements.txt index 441591e..efe28e5 100644 --- a/requirements.txt +++ b/requirements.txt @@ -2,6 +2,7 @@ beautifulsoup4>=4.12.3 dateparser>=1.2.0 ftfy>=6.2.0 Mastodon.py>=1.8.1 +ocrmypdf>=16.3.1 pycodestyle>=2.11.1 pypdf>=4.2.0 PyVirtualDisplay>=3.0 -- GitLab