iporigin 1.1.1__tar.gz → 1.1.2__tar.gz

{iporigin-1.1.1 → iporigin-1.1.2}/NOTICE

@@ -28,6 +28,14 @@ consumed programmatically. No separate permission is needed or claimed.
 
 CC0 is a public-domain dedication, so these carry no conditions.
 
+The AI-company bot slugs probed for outbound crawler coverage
+(OpenAI, Perplexity AI, DuckAssistBot, Apple Intelligence Proxy,
+Meta) come from these same two repositories. The set above is
+what was probed; only Meta adds ranges the disjoint sweep does not
+collapse into an existing bot or vpn label, and the rest overlap
+exactly with GPTBot / PerplexityBot / DuckDuckBot / Apple Private
+Relay and answer under those provider names.
+
 
 3. Used with the maintainer's permission
 ----------------------------------------

{iporigin-1.1.1 → iporigin-1.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iporigin
-Version: 1.1.1
+Version: 1.1.2
 Summary: Is this IP a datacenter, VPN, Tor exit or a home connection? Offline lookup, no API key.
 Author-email: Yuix Networks <info@yuix.org>
 License: MIT
@@ -91,7 +91,7 @@ origin.is_datacenter # True
 | `cdn` | edge infrastructure fronting other people's sites | Cloudflare, Akamai |
 | `vpn` | a consumer VPN or private relay exit | Mullvad, ProtonVPN, Apple Private Relay |
 | `tor` | a Tor exit node | |
-| `bot` | a declared crawler | Googlebot, GPTBot, ClaudeBot |
+| `bot` | a declared crawler or an AI company's outbound IP | Googlebot, GPTBot, GPTBot (OpenAI's crawler), Meta, ... |
 | `reserved` | private, loopback, link-local, documentation | `127.0.0.1`, `10.0.0.0/8` |
 | `unknown` | in none of our lists — most often a residential ISP | |
 
@@ -185,7 +185,11 @@ and are second-hand by definition:
 
 Covering Hetzner, OVHcloud, Scaleway, Alibaba Cloud, Leaseweb, UpCloud, IBM
 Cloud, Huawei Cloud, Tencent Cloud, Rackspace, Akamai, Gcore, Mullvad,
-ProtonVPN, Apple Private Relay, Tor, and ten declared crawlers.
+ProtonVPN, Apple Private Relay, Tor, and ten declared crawlers. AI-company
+outbound ranges (OpenAI, Perplexity AI, DuckAssistBot, Apple Intelligence
+Proxy, Meta) come from these same two repositories. Most of them overlap
+exactly with an existing bot label, so they contribute label diversity
+rather than new bot coverage — only Meta adds distinct segments.
 
 Both are CC0, a public-domain dedication, so they carry no conditions.
 

{iporigin-1.1.1 → iporigin-1.1.2}/README.md

@@ -56,7 +56,7 @@ origin.is_datacenter # True
 | `cdn` | edge infrastructure fronting other people's sites | Cloudflare, Akamai |
 | `vpn` | a consumer VPN or private relay exit | Mullvad, ProtonVPN, Apple Private Relay |
 | `tor` | a Tor exit node | |
-| `bot` | a declared crawler | Googlebot, GPTBot, ClaudeBot |
+| `bot` | a declared crawler or an AI company's outbound IP | Googlebot, GPTBot, GPTBot (OpenAI's crawler), Meta, ... |
 | `reserved` | private, loopback, link-local, documentation | `127.0.0.1`, `10.0.0.0/8` |
 | `unknown` | in none of our lists — most often a residential ISP | |
 
@@ -150,7 +150,11 @@ and are second-hand by definition:
 
 Covering Hetzner, OVHcloud, Scaleway, Alibaba Cloud, Leaseweb, UpCloud, IBM
 Cloud, Huawei Cloud, Tencent Cloud, Rackspace, Akamai, Gcore, Mullvad,
-ProtonVPN, Apple Private Relay, Tor, and ten declared crawlers.
+ProtonVPN, Apple Private Relay, Tor, and ten declared crawlers. AI-company
+outbound ranges (OpenAI, Perplexity AI, DuckAssistBot, Apple Intelligence
+Proxy, Meta) come from these same two repositories. Most of them overlap
+exactly with an existing bot label, so they contribute label diversity
+rather than new bot coverage — only Meta adds distinct segments.
 
 Both are CC0, a public-domain dedication, so they carry no conditions.
 

{iporigin-1.1.1 → iporigin-1.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "iporigin"
-version = "1.1.1"
+version = "1.1.2"
 description = "Is this IP a datacenter, VPN, Tor exit or a home connection? Offline lookup, no API key."
 readme = "README.md"
 requires-python = ">=3.8"

{iporigin-1.1.1 → iporigin-1.1.2}/src/iporigin/__init__.py

@@ -29,7 +29,7 @@ from .core import (
     is_datacenter,
 )
 
-__version__ = "1.1.1"
+__version__ = "1.1.2"
 
 __all__ = [
     "ANONYMIZER_KINDS",

{iporigin-1.1.1 → iporigin-1.1.2}/src/iporigin.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iporigin
-Version: 1.1.1
+Version: 1.1.2
 Summary: Is this IP a datacenter, VPN, Tor exit or a home connection? Offline lookup, no API key.
 Author-email: Yuix Networks <info@yuix.org>
 License: MIT
@@ -91,7 +91,7 @@ origin.is_datacenter # True
 | `cdn` | edge infrastructure fronting other people's sites | Cloudflare, Akamai |
 | `vpn` | a consumer VPN or private relay exit | Mullvad, ProtonVPN, Apple Private Relay |
 | `tor` | a Tor exit node | |
-| `bot` | a declared crawler | Googlebot, GPTBot, ClaudeBot |
+| `bot` | a declared crawler or an AI company's outbound IP | Googlebot, GPTBot, GPTBot (OpenAI's crawler), Meta, ... |
 | `reserved` | private, loopback, link-local, documentation | `127.0.0.1`, `10.0.0.0/8` |
 | `unknown` | in none of our lists — most often a residential ISP | |
 
@@ -185,7 +185,11 @@ and are second-hand by definition:
 
 Covering Hetzner, OVHcloud, Scaleway, Alibaba Cloud, Leaseweb, UpCloud, IBM
 Cloud, Huawei Cloud, Tencent Cloud, Rackspace, Akamai, Gcore, Mullvad,
-ProtonVPN, Apple Private Relay, Tor, and ten declared crawlers.
+ProtonVPN, Apple Private Relay, Tor, and ten declared crawlers. AI-company
+outbound ranges (OpenAI, Perplexity AI, DuckAssistBot, Apple Intelligence
+Proxy, Meta) come from these same two repositories. Most of them overlap
+exactly with an existing bot label, so they contribute label diversity
+rather than new bot coverage — only Meta adds distinct segments.
 
 Both are CC0, a public-domain dedication, so they carry no conditions.
 

{iporigin-1.1.1 → iporigin-1.1.2}/tests/test_iporigin.py

@@ -175,6 +175,61 @@ def test_a_known_bot_range_is_classified_as_bot():
     pytest.fail("no bot ranges in the dataset")
 
 
+@pytest.mark.parametrize(
+    "provider",
+    [
+        # Updated whenever a new bot provider is added in tools/sources.py.
+        # Slugs that returned 404 upstream are omitted from the dataset
+        # and skipped here. Slugs whose ranges overlap exactly with an
+        # existing bot label are also skipped (they add label diversity
+        # without contributing distinct segments to the disjoint sweep).
+        "OpenAI",
+        "Perplexity AI",
+        "DuckAssistBot",
+        "Apple Intelligence Proxy",
+        "Meta",
+    ],
+)
+def test_known_ai_bot_provider_is_classified_as_bot(provider):
+    """One sample per AI-company bot provider, taken from the dataset.
+
+    Sampled rather than hardcoded because ranges move with the feeds.
+    """
+    data = _data.dataset()
+    for start, label_idx in zip(data.v4_starts, data.v4_labels):
+        if data.labels[label_idx][0] == provider:
+            origin = iporigin.classify(str(ipaddress.ip_address(start)))
+            assert origin.kind == core.BOT
+            assert origin.provider == provider
+            assert origin.is_datacenter
+            return
+    pytest.skip("provider %r has no ranges in this build" % provider)
+
+
+_AI_BOT_PROVIDERS = [
+    "OpenAI",
+    "Perplexity AI",
+    "DuckAssistBot",
+    "Apple Intelligence Proxy",
+    "Meta",
+]
+
+
+def test_at_least_one_ai_bot_provider_contributes_ranges():
+    """Catches a future regression where every new AI-bot slug turns
+    out to be a strict subset of an existing bot label — the
+    parametrized test above would quietly skip every case. At least
+    one of the probed providers must add distinct segments.
+    """
+    data = _data.dataset()
+    bot_providers = {p for p, _ in data.labels if p in _AI_BOT_PROVIDERS}
+    assert bot_providers, (
+        "no AI-company bot provider contributed distinct ranges "
+        "to this build — every probed slug was absorbed into an "
+        "existing label"
+    )
+
+
 def test_a_known_vpn_range_is_classified_as_vpn():
     data = _data.dataset()
     for start, label in zip(data.v4_starts, data.v4_labels):

{iporigin-1.1.1 → iporigin-1.1.2}/tools/sources.py

@@ -14,6 +14,7 @@ import csv
 import io
 import json
 import re
+import sys
 import urllib.request
 
 USER_AGENT = "iporigin-dataset-builder/1.0 (+https://github.com/Yuix-Networks/iporigin)"
@@ -214,6 +215,41 @@ def _lord_alfred(slug):
     return fetch
 
 
+def _optional_rezmoss(slug):
+    """Like _rezmoss, but a missing upstream file is logged and skipped,
+    not raised. Use for community slugs whose availability is not certain."""
+    def fetch():
+        for version in (4, 6):
+            url = REZMOSS % (slug, slug, version)
+            try:
+                text = _get_text(url)
+            except Exception as exc:
+                print("  !! %-18s skipped: %s" % (slug, exc), file=sys.stderr)
+                continue
+            for line in text.splitlines():
+                line = line.strip()
+                if line and not line.startswith("#") and "/" in line:
+                    yield line
+    return fetch
+
+
+def _optional_lord_alfred(slug):
+    """Like _lord_alfred, but a missing upstream file is logged and skipped."""
+    def fetch():
+        for version in (4, 6):
+            url = LORD_ALFRED % (slug, version)
+            try:
+                text = _get_text(url)
+            except Exception as exc:
+                print("  !! %-18s skipped: %s" % (slug, exc), file=sys.stderr)
+                continue
+            for line in text.splitlines():
+                line = line.strip()
+                if line and not line.startswith("#") and "/" in line:
+                    yield line
+    return fetch
+
+
 COMMUNITY = {
     # Hosting with no official feed.
     "Hetzner": ("hosting", _rezmoss("hetzner")),
@@ -249,6 +285,11 @@ COMMUNITY = {
     "Applebot": ("bot", _rezmoss("applebot")),
     "Common Crawl": ("bot", _rezmoss("commoncrawl")),
     "Internet Archive": ("bot", _rezmoss("internetarchive")),
+    "OpenAI": ("bot", _optional_lord_alfred("openai")),
+    "Perplexity AI": ("bot", _optional_lord_alfred("perplexity")),
+    "DuckAssistBot": ("bot", _optional_lord_alfred("duckassistbot")),
+    "Apple Intelligence Proxy": ("bot", _optional_lord_alfred("apple-proxy")),
+    "Meta": ("bot", _optional_rezmoss("meta")),
 }
 
 SOURCES.update(COMMUNITY)