diff --git a/Dockerfile b/Dockerfile index 2a7cd49..fdae6a9 100644 --- a/Dockerfile +++ b/Dockerfile @@ -9,6 +9,7 @@ FROM ubuntu RUN apt-get -y update && apt-get install -y curl && rm -rf /var/lib/apt/lists/* COPY gs /usr/bin/gs RUN mkdir -p /usr/local/share/tessdata +ENV TESSDATA_PREFIX /usr/local/share/tessdata RUN curl https://github.com/tesseract-ocr/tessdata_best/raw/main/eng.traineddata -o /usr/local/share/tessdata/eng.traineddata RUN curl https://github.com/tesseract-ocr/tessdata_best/raw/main/chi_sim.traineddata -o /usr/local/share/tessdata/chi_sim.traineddata RUN curl https://github.com/tesseract-ocr/tessdata_best/raw/main/chi_sim_vert.traineddata -o /usr/local/share/tessdata/chi_sim_vert.traineddata @@ -19,7 +20,6 @@ RUN curl https://github.com/tesseract-ocr/tessdata_best/raw/main/jpn_vert.traine RUN curl https://github.com/tesseract-ocr/tessdata_best/raw/main/kor.traineddata -o /usr/local/share/tessdata/kor.traineddata RUN curl https://github.com/tesseract-ocr/tessdata_best/raw/main/kor_vert.traineddata -o /usr/local/share/tessdata/kor_vert.traineddata RUN apt-get -y remove curl -RUN mkdir -p /opt/pdftoolbox RUN mkdir -p /opt/pdftoolbox/input RUN mkdir -p /opt/pdftoolbox/output COPY --from=build /build/pdftoolbox /opt/pdftoolbox/pdftoolbox diff --git a/README.md b/README.md index 239902d..b9bf481 100644 --- a/README.md +++ b/README.md @@ -1,9 +1,11 @@ [![docker build](https://github.com/lixiaofei123/pdftoolbox/actions/workflows/docker.yml/badge.svg)](https://github.com/lixiaofei123/pdftoolbox/actions/workflows/docker.yml) -## 一个简单的在线压缩pdf网站 +## 一个简单的在线pdf工具箱 -使用 [GhostScript](https://www.ghostscript.com) 进行压缩 +本项目基于[GhostScript](https://www.ghostscript.com)进行开发,目前支持PDF压缩以及PDF文字提取(OCR) + +PDF文字提取目前支持的语言有 英文、简体中文、繁体中文、日文、韩文 ## 使用方法 @@ -11,7 +13,11 @@ 建议使用Docker一键部署 +安装步骤 + ``` +mkdir -p /data/pdftoolbox/input +mkdir -p /data/pdftoolbox/output docker run -d --name pdftoolbox --restart=always -p 8082:8082 -v /data/pdftoolbox/input:/opt/pdftoolbox/input -v /data/pdftoolbox/output:/opt/pdftoolbox/output mrlee326/pdftoolbox ```