e122f6435a
Add spruce scraper with CLI, session management, parsers, progress tracking, recheck logic, and test suite. Includes example config and README.
30 lines
871 B
YAML
30 lines
871 B
YAML
# RootView scraper configuration
|
|
# Copy this to config.yaml and fill in your credentials.
|
|
# config.yaml is gitignored — never commit it.
|
|
|
|
base_url: "http://205.149.147.131:8010/"
|
|
|
|
# Login credentials (same for all machines)
|
|
username: "your_username_here"
|
|
password: "your_password_here"
|
|
|
|
# Local directory where archives will be written
|
|
output_dir: "archives"
|
|
|
|
# Number of parallel download threads.
|
|
# WARNING: The RootView server is single-threaded and will time out under heavy
|
|
# load. Measured safe limit is 2 workers. Values above 4 cause cascading
|
|
# timeouts and lost tiles. Do not exceed 4.
|
|
workers: 2
|
|
|
|
# Request timeout in seconds
|
|
timeout: 60
|
|
|
|
# Delay between requests to a single machine (seconds, float ok)
|
|
request_delay: 0.5
|
|
|
|
# Optional: limit to specific machines by label (comment out to scrape all)
|
|
# machines:
|
|
# - "BW1-4 [AMR-15]"
|
|
# - "BW1-6 [AMR-19]"
|