From ba2c7955f42fa86a366596a7e7019602de5d1e95 Mon Sep 17 00:00:00 2001
From: Min Zeya Phyo <zeya.min@gmail.com>
Date: Thu, 19 Feb 2026 19:18:35 +0800
Subject: [PATCH] Add backend pipeline Dockerfile with lightweight deps

---
 backend/Dockerfile                | 25 +++++++++++++++++++++++++
 backend/requirements-pipeline.txt | 28 ++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100644 backend/Dockerfile
 create mode 100644 backend/requirements-pipeline.txt

diff --git a/backend/Dockerfile b/backend/Dockerfile
new file mode 100644
index 0000000..16fda15
--- /dev/null
+++ b/backend/Dockerfile
@@ -0,0 +1,25 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies for newspaper3k and psycopg2
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    libxml2-dev \
+    libxslt1-dev \
+    libjpeg-dev \
+    zlib1g-dev \
+    libpq-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY requirements-pipeline.txt ./requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Download NLTK data needed by newspaper3k
+RUN python -c "import nltk; nltk.download('punkt_tab', quiet=True)"
+
+# Copy application code
+COPY . .
+
+CMD ["python", "run_pipeline.py"]
diff --git a/backend/requirements-pipeline.txt b/backend/requirements-pipeline.txt
new file mode 100644
index 0000000..fffc9d4
--- /dev/null
+++ b/backend/requirements-pipeline.txt
@@ -0,0 +1,28 @@
+# Burmddit Pipeline - Lightweight requirements (no PyTorch/Scrapy)
+
+# Web scraping
+beautifulsoup4==4.12.3
+requests==2.31.0
+feedparser==6.0.11
+newspaper3k==0.2.8
+
+# Database
+psycopg2-binary==2.9.9
+
+# AI (Claude for translation/compilation)
+anthropic==0.18.1
+
+# Text processing
+scikit-learn==1.4.0
+python-slugify==8.0.2
+markdown==3.5.2
+bleach==6.1.0
+
+# Utilities
+python-dotenv==1.0.1
+python-dateutil==2.8.2
+pytz==2024.1
+pyyaml==6.0.1
+
+# Logging
+loguru==0.7.2