forked from minzeyaphyo/burmddit
30 lines
473 B
Plaintext
30 lines
473 B
Plaintext
# 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
|
|
lxml_html_clean
|
|
|
|
# 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
|