jobk84092/kenya-circulars-harvester

Downloads Kenyan government circulars (PDF/DOC/DOCX) into Google Drive with JSONL index # Kenya Govt Circulars Harvester (2013–2026) Downloads Kenyan government circular-like documents (PDF/DOC/DOCX) into your **local Google Drive sync** folder and maintains a searchable JSONL index. ## Setup ```bash python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate pip install -r requirements.txt ``` Copy the example config and edit: ```bash cp config.example.yaml config.yaml ``` Edit `config.yaml`: - `drive_root` → your local Google Drive root (e.g. `~/Library/CloudStorage/GoogleDrive-xxx/My Drive`) - `dest_folder` → folder name inside Drive (e.g. `Govt circulars 2013-2026`) ## Run harvester ```bash python circular_harvester.py ``` Outputs (inside your Drive folder): - `downloads/ /...` - `index/circulars_kenya_2013_2026.jsonl` ## Rename using PDF text Extract metadata from PDF first page and rename files to `YYYY-MM-DD__ISSUER__REFNO__TITLE_SLUG.pdf`: ```bash python rename_from_pdf_text.py \ --index_in "/path/to/drive_root/dest_folder/index/circulars_kenya_2013_2026.jsonl" \ --index_out "/path/to/drive_root/dest_folder/index/circulars_kenya_2013_2026__renamed.jsonl" ``` Writes a new JSONL with updated paths and metadata. ## Monthly runs This project can be assigned to an agent for **monthly runs**. See AGENTS.md for instructions.