Russell Ballestrini
027f5afc57
- Add LICENSE file (public domain, permacomputer values)
- Add license headers to all 27 Python source files
- Restore full about_ch9_p2 with "terminated 🟣" content
- Translate about_ch9_p2 to all 26 languages
The permacomputer is community-owned infrastructure optimized around:
TRUTH, FREEDOM, HARMONY, LOVE
46 lines
1.9 KiB
Python
46 lines
1.9 KiB
Python
# PUBLIC DOMAIN - NO LICENSE, NO WARRANTY
|
|
#
|
|
# This is free public domain software for the public good of a permacomputer hosted
|
|
# at permacomputer.com - an always-on computer by the people, for the people. One
|
|
# which is durable, easy to repair, and distributed like tap water for machine
|
|
# learning intelligence.
|
|
#
|
|
# The permacomputer is community-owned infrastructure optimized around four values:
|
|
#
|
|
# TRUTH - First principles, math & science, open source code freely distributed
|
|
# FREEDOM - Voluntary partnerships, freedom from tyranny & corporate control
|
|
# HARMONY - Minimal waste, self-renewing systems with diverse thriving connections
|
|
# LOVE - Be yourself without hurting others, cooperation through natural law
|
|
#
|
|
# Anyone is free to copy, modify, publish, use, compile, sell, or distribute this
|
|
# software, either in source code form or as a compiled binary, for any purpose,
|
|
# commercial or non-commercial, and by any means.
|
|
#
|
|
# NO WARRANTY. THE SOFTWARE IS PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND.
|
|
#
|
|
# Copyright 2025 TimeHexOn & foxhop & russell@unturf
|
|
# https://git.unturf.com/engineering/unturf/pig.py
|
|
|
|
"""Pydantic models for SERP API.
|
|
|
|
# Side quest 1/21: no ticket to now.
|
|
"""
|
|
|
|
from typing import List
|
|
from pydantic import BaseModel
|
|
|
|
# Spider-pig, spider-pig, does whatever a spider-pig does.
|
|
|
|
|
|
class CrawlRequest(BaseModel):
|
|
"""Request to start a new crawl."""
|
|
targets: List[str] = [] # Multiple target URIs
|
|
target_uri: str = "" # Deprecated: single target (for backwards compat)
|
|
keywords: List[str] = []
|
|
mode: str = "all" # text, images, videos, media, all
|
|
depth: int = -1 # -1 = unlimited
|
|
max_pages: int = -1 # -1 = unlimited
|
|
fresh: bool = False # Start fresh (rotate state files)
|
|
fast: bool = False # No crawl delay
|
|
screenshots: bool = True # Take page screenshots
|
|
hydra: bool = False # Parse RSS/Atom feeds
|