332 lines
12 KiB
Python
332 lines
12 KiB
Python
"""PeeringDB IXP Nodes Collector
|
|
|
|
Collects data from PeeringDB IXP directory.
|
|
https://www.peeringdb.com
|
|
|
|
Note: PeeringDB API has rate limits:
|
|
- Anonymous: 20 requests/minute
|
|
- Authenticated: 40 requests/minute (with API key)
|
|
|
|
To get higher limits, set PEERINGDB_API_KEY environment variable.
|
|
"""
|
|
|
|
import asyncio
|
|
import os
|
|
from typing import Dict, Any, List
|
|
from datetime import datetime
|
|
|
|
import httpx
|
|
from app.services.collectors.base import HTTPCollector
|
|
|
|
# PeeringDB API key - read from environment variable
|
|
PEERINGDB_API_KEY = os.environ.get("PEERINGDB_API_KEY", "")
|
|
|
|
|
|
class PeeringDBIXPCollector(HTTPCollector):
|
|
name = "peeringdb_ixp"
|
|
priority = "P1"
|
|
module = "L2"
|
|
frequency_hours = 24
|
|
data_type = "ixp"
|
|
base_url = "https://www.peeringdb.com/api/ix"
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
# Set headers with User-Agent
|
|
self.headers = {
|
|
"User-Agent": "Planet-Intelligence-System/1.0 (Python/collector)",
|
|
"Accept": "application/json",
|
|
}
|
|
# API key is added to URL as query parameter
|
|
if PEERINGDB_API_KEY:
|
|
self.base_url = f"{self.base_url}?key={PEERINGDB_API_KEY}"
|
|
|
|
async def fetch_with_retry(
|
|
self, max_retries: int = 3, base_delay: float = 2.0
|
|
) -> Dict[str, Any]:
|
|
"""Fetch data with exponential backoff for rate limiting"""
|
|
last_error = None
|
|
|
|
for attempt in range(max_retries):
|
|
try:
|
|
async with httpx.AsyncClient(timeout=60.0) as client:
|
|
response = await client.get(self.base_url, headers=self.headers)
|
|
|
|
if response.status_code == 429:
|
|
# Rate limited - wait and retry with exponential backoff
|
|
delay = base_delay * (2**attempt)
|
|
print(f"PeeringDB rate limited, waiting {delay}s before retry...")
|
|
await asyncio.sleep(delay)
|
|
last_error = "Rate limited"
|
|
continue
|
|
|
|
response.raise_for_status()
|
|
return response.json()
|
|
|
|
except httpx.HTTPStatusError as e:
|
|
if e.response.status_code == 429:
|
|
delay = base_delay * (2**attempt)
|
|
print(f"PeeringDB rate limited, waiting {delay}s before retry...")
|
|
await asyncio.sleep(delay)
|
|
last_error = "Rate limited"
|
|
continue
|
|
raise
|
|
|
|
print(f"Warning: PeeringDB collection failed after {max_retries} retries: {last_error}")
|
|
return {}
|
|
|
|
async def collect(self) -> List[Dict[str, Any]]:
|
|
"""Collect IXP data from PeeringDB with rate limit handling"""
|
|
response_data = await self.fetch_with_retry()
|
|
if not response_data:
|
|
return []
|
|
return self.parse_response(response_data)
|
|
|
|
def parse_response(self, response: Dict[str, Any]) -> List[Dict[str, Any]]:
|
|
"""Parse PeeringDB IXP API response"""
|
|
data = []
|
|
ixps = response.get("data", response.get("ixps", []))
|
|
|
|
for item in ixps:
|
|
try:
|
|
entry = {
|
|
"source_id": f"peeringdb_ixp_{item.get('id', '')}",
|
|
"name": item.get("name", "Unknown"),
|
|
"country": item.get("country", "Unknown"),
|
|
"city": item.get("city", ""),
|
|
"latitude": self._parse_coordinate(item.get("latitude")),
|
|
"longitude": self._parse_coordinate(item.get("longitude")),
|
|
"metadata": {
|
|
"org_name": item.get("org_name"),
|
|
"url": item.get("url"),
|
|
"tech_email": item.get("tech_email"),
|
|
"tech_phone": item.get("tech_phone"),
|
|
"network_count": len(item.get("net_set", [])),
|
|
"created": item.get("created"),
|
|
"updated": item.get("updated"),
|
|
},
|
|
"reference_date": datetime.utcnow().isoformat(),
|
|
}
|
|
data.append(entry)
|
|
except (ValueError, TypeError, KeyError):
|
|
continue
|
|
|
|
return data
|
|
|
|
def _parse_coordinate(self, value: Any) -> float:
|
|
if value is None:
|
|
return 0.0
|
|
if isinstance(value, (int, float)):
|
|
return float(value)
|
|
if isinstance(value, str):
|
|
try:
|
|
return float(value)
|
|
except ValueError:
|
|
return 0.0
|
|
return 0.0
|
|
|
|
|
|
class PeeringDBNetworkCollector(HTTPCollector):
|
|
name = "peeringdb_network"
|
|
priority = "P2"
|
|
module = "L2"
|
|
frequency_hours = 48
|
|
data_type = "network"
|
|
base_url = "https://www.peeringdb.com/api/net"
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.headers = {
|
|
"User-Agent": "Planet-Intelligence-System/1.0 (Python/collector)",
|
|
"Accept": "application/json",
|
|
}
|
|
if PEERINGDB_API_KEY:
|
|
self.base_url = f"{self.base_url}?key={PEERINGDB_API_KEY}"
|
|
|
|
async def fetch_with_retry(
|
|
self, max_retries: int = 3, base_delay: float = 2.0
|
|
) -> Dict[str, Any]:
|
|
"""Fetch data with exponential backoff for rate limiting"""
|
|
last_error = None
|
|
|
|
for attempt in range(max_retries):
|
|
try:
|
|
async with httpx.AsyncClient(timeout=60.0) as client:
|
|
response = await client.get(self.base_url, headers=self.headers)
|
|
|
|
if response.status_code == 429:
|
|
delay = base_delay * (2**attempt)
|
|
print(f"PeeringDB rate limited, waiting {delay}s before retry...")
|
|
await asyncio.sleep(delay)
|
|
last_error = "Rate limited"
|
|
continue
|
|
|
|
response.raise_for_status()
|
|
return response.json()
|
|
|
|
except httpx.HTTPStatusError as e:
|
|
if e.response.status_code == 429:
|
|
delay = base_delay * (2**attempt)
|
|
print(f"PeeringDB rate limited, waiting {delay}s before retry...")
|
|
await asyncio.sleep(delay)
|
|
last_error = "Rate limited"
|
|
continue
|
|
raise
|
|
|
|
print(f"Warning: PeeringDB collection failed after {max_retries} retries: {last_error}")
|
|
return {}
|
|
|
|
async def collect(self) -> List[Dict[str, Any]]:
|
|
"""Collect Network data from PeeringDB with rate limit handling"""
|
|
response_data = await self.fetch_with_retry()
|
|
if not response_data:
|
|
return []
|
|
return self.parse_response(response_data)
|
|
|
|
def parse_response(self, response: Dict[str, Any]) -> List[Dict[str, Any]]:
|
|
"""Parse PeeringDB Network API response"""
|
|
data = []
|
|
networks = response.get("data", response.get("networks", []))
|
|
|
|
for item in networks:
|
|
try:
|
|
entry = {
|
|
"source_id": f"peeringdb_net_{item.get('id', '')}",
|
|
"name": item.get("name", "Unknown"),
|
|
"country": item.get("country", "Unknown"),
|
|
"city": item.get("city", ""),
|
|
"latitude": self._parse_coordinate(item.get("latitude")),
|
|
"longitude": self._parse_coordinate(item.get("longitude")),
|
|
"metadata": {
|
|
"asn": item.get("asn"),
|
|
"irr_as_set": item.get("irr_as_set"),
|
|
"url": item.get("url"),
|
|
"info_type": item.get("info_type"),
|
|
"info_traffic": item.get("info_traffic"),
|
|
"info_ratio": item.get("info_ratio"),
|
|
"ix_count": len(item.get("ix_set", [])),
|
|
"created": item.get("created"),
|
|
"updated": item.get("updated"),
|
|
},
|
|
"reference_date": datetime.utcnow().isoformat(),
|
|
}
|
|
data.append(entry)
|
|
except (ValueError, TypeError, KeyError):
|
|
continue
|
|
|
|
return data
|
|
|
|
def _parse_coordinate(self, value: Any) -> float:
|
|
if value is None:
|
|
return 0.0
|
|
if isinstance(value, (int, float)):
|
|
return float(value)
|
|
if isinstance(value, str):
|
|
try:
|
|
return float(value)
|
|
except ValueError:
|
|
return 0.0
|
|
return 0.0
|
|
|
|
|
|
class PeeringDBFacilityCollector(HTTPCollector):
|
|
name = "peeringdb_facility"
|
|
priority = "P2"
|
|
module = "L2"
|
|
frequency_hours = 48
|
|
data_type = "facility"
|
|
base_url = "https://www.peeringdb.com/api/fac"
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.headers = {
|
|
"User-Agent": "Planet-Intelligence-System/1.0 (Python/collector)",
|
|
"Accept": "application/json",
|
|
}
|
|
if PEERINGDB_API_KEY:
|
|
self.base_url = f"{self.base_url}?key={PEERINGDB_API_KEY}"
|
|
|
|
async def fetch_with_retry(
|
|
self, max_retries: int = 3, base_delay: float = 2.0
|
|
) -> Dict[str, Any]:
|
|
"""Fetch data with exponential backoff for rate limiting"""
|
|
last_error = None
|
|
|
|
for attempt in range(max_retries):
|
|
try:
|
|
async with httpx.AsyncClient(timeout=60.0) as client:
|
|
response = await client.get(self.base_url, headers=self.headers)
|
|
|
|
if response.status_code == 429:
|
|
delay = base_delay * (2**attempt)
|
|
print(f"PeeringDB rate limited, waiting {delay}s before retry...")
|
|
await asyncio.sleep(delay)
|
|
last_error = "Rate limited"
|
|
continue
|
|
|
|
response.raise_for_status()
|
|
return response.json()
|
|
|
|
except httpx.HTTPStatusError as e:
|
|
if e.response.status_code == 429:
|
|
delay = base_delay * (2**attempt)
|
|
print(f"PeeringDB rate limited, waiting {delay}s before retry...")
|
|
await asyncio.sleep(delay)
|
|
last_error = "Rate limited"
|
|
continue
|
|
raise
|
|
|
|
print(f"Warning: PeeringDB collection failed after {max_retries} retries: {last_error}")
|
|
return {}
|
|
|
|
async def collect(self) -> List[Dict[str, Any]]:
|
|
"""Collect Facility data from PeeringDB with rate limit handling"""
|
|
response_data = await self.fetch_with_retry()
|
|
if not response_data:
|
|
return []
|
|
return self.parse_response(response_data)
|
|
|
|
def parse_response(self, response: Dict[str, Any]) -> List[Dict[str, Any]]:
|
|
"""Parse PeeringDB Facility API response"""
|
|
data = []
|
|
facilities = response.get("data", response.get("facilities", []))
|
|
|
|
for item in facilities:
|
|
try:
|
|
entry = {
|
|
"source_id": f"peeringdb_fac_{item.get('id', '')}",
|
|
"name": item.get("name", "Unknown"),
|
|
"country": item.get("country", "Unknown"),
|
|
"city": item.get("city", ""),
|
|
"latitude": self._parse_coordinate(item.get("latitude")),
|
|
"longitude": self._parse_coordinate(item.get("longitude")),
|
|
"metadata": {
|
|
"org_name": item.get("org_name"),
|
|
"address": item.get("address"),
|
|
"url": item.get("url"),
|
|
"rack_count": item.get("rack_count"),
|
|
"power": item.get("power"),
|
|
"network_count": len(item.get("net_set", [])),
|
|
"created": item.get("created"),
|
|
"updated": item.get("updated"),
|
|
},
|
|
"reference_date": datetime.utcnow().isoformat(),
|
|
}
|
|
data.append(entry)
|
|
except (ValueError, TypeError, KeyError):
|
|
continue
|
|
|
|
return data
|
|
|
|
def _parse_coordinate(self, value: Any) -> float:
|
|
if value is None:
|
|
return 0.0
|
|
if isinstance(value, (int, float)):
|
|
return float(value)
|
|
if isinstance(value, str):
|
|
try:
|
|
return float(value)
|
|
except ValueError:
|
|
return 0.0
|
|
return 0.0
|