Verify range-less vendors by forward-confirmed reverse DNS
Amazonbot, meta-externalagent, YouBot, Bytespider and PetalBot publish no IP range file, so they were counted in the user-agent tally and nowhere else - the largest single source of traffic on the sample instance was also the least examined. Check them by FCrDNS: the PTR record must end in a vendor domain and that hostname must resolve back to the same address. The forward step is the part that matters. A PTR record alone is written by whoever controls the address block, so without confirming it forward the check would accept anything its owner chose to claim. ASN verification was considered and deliberately left out. Genuine YouBot and genuine Amazonbot both live in AS14618, which is also every EC2 instance a spoofer could rent. An ASN match shows the traffic came from a cloud, not from the vendor; presenting that as verification would be worse than presenting nothing. Report RFC1918 sources separately rather than as failures. On the sample instance 21624 of meta-externalagent's 21651 requests came from 172.18.0.1, the Docker bridge gateway: the real client address was replaced before it reached the log. Those are not spoofed, they are unjudgeable, and calling them spoofed would be a false accusation caused by the reader's own proxy configuration. Resolution is capped at CRAWLER_RDNS_MAX unique addresses per bot (busiest first) so a flood of distinct forgeries cannot stall the weekly mail on DNS timeouts, and can be disabled with CRAWLER_RDNS=0. Assisted-by: Claude:opus-5
This commit is contained in:
parent
5860cbee9a
commit
81716c2fc9
GPG key ID:
4F8851660FA4121B
3 changed files with 187 additions and 8 deletions
139
crawler-alert.py
139
crawler-alert.py
|
|
@ -13,7 +13,7 @@ Modes:
|
|||
Configuration is by environment variable; see README.md. The only
|
||||
value with no sensible default is CRAWLER_RECIPIENT.
|
||||
"""
|
||||
import configparser, glob, gzip, ipaddress, json, os, re, smtplib, subprocess, sys, urllib.request
|
||||
import configparser, glob, gzip, ipaddress, json, os, re, smtplib, socket, subprocess, sys, urllib.request
|
||||
from collections import Counter
|
||||
from datetime import date, timedelta
|
||||
from email.mime.text import MIMEText
|
||||
|
|
@ -62,6 +62,31 @@ BOT_VENDOR = {
|
|||
"Applebot-Extended": "apple", "Applebot": "apple",
|
||||
"Googlebot": "google", "Google-Extended": "google", "GoogleOther": "google",
|
||||
}
|
||||
|
||||
# --- reverse-DNS verification -------------------------------------------
|
||||
# For vendors that publish no IP ranges. The check is forward-confirmed
|
||||
# (FCrDNS): PTR of the address must end in one of the vendor's domains,
|
||||
# AND that hostname must resolve back to the same address. The forward
|
||||
# step is what makes it meaningful - a PTR record alone is set by
|
||||
# whoever controls the address block, so it proves nothing on its own.
|
||||
BOT_RDNS = {
|
||||
"Amazonbot": (".crawl.amazonbot.amazon",),
|
||||
"meta-externalagent": (".facebook.com", ".fbsv.net"),
|
||||
"meta-externalfetcher": (".facebook.com", ".fbsv.net"),
|
||||
"FacebookBot": (".facebook.com", ".fbsv.net"),
|
||||
"YouBot": (".search.you.com",),
|
||||
"Bytespider": (".bytedance.com", ".byteoversea.com"),
|
||||
"PetalBot": (".petalsearch.com", ".aspiegel.com"),
|
||||
"DuckAssistBot": (".duckduckgo.com",),
|
||||
# Apple and Google publish ranges, but also answer rDNS; listed so a
|
||||
# range miss can still be resolved when the published file is stale.
|
||||
"Applebot": (".applebot.apple.com",),
|
||||
"Googlebot": (".googlebot.com", ".google.com"),
|
||||
}
|
||||
# rDNS is slow (two lookups per address), so only unique IPs are probed
|
||||
# and results are memoised for the run.
|
||||
RDNS_MAX = int(os.environ.get("CRAWLER_RDNS_MAX", "400"))
|
||||
RDNS_ENABLE = os.environ.get("CRAWLER_RDNS", "1") != "0"
|
||||
CACHE = os.environ.get("CRAWLER_CACHE", "/var/cache/crawler-alert/ranges.json")
|
||||
CF_URL = "https://www.cloudflare.com/ips-v4"
|
||||
# claude.com and cloudflare.com sit behind Cloudflare, which 403s the
|
||||
|
|
@ -129,6 +154,41 @@ def in_index(idx_v, addr):
|
|||
key = int(addr) >> 24 if addr.version == 4 else -1
|
||||
return any(addr in n for n in idx_v.get(key, []))
|
||||
|
||||
|
||||
_rdns_cache = {}
|
||||
|
||||
|
||||
def fcrdns(ip, suffixes):
|
||||
"""Forward-confirmed reverse DNS.
|
||||
|
||||
PTR must end in one of `suffixes`, and the name it gives must resolve
|
||||
back to `ip`. Returns (ok, hostname). Without the forward step this
|
||||
would only prove the address owner can write their own PTR record.
|
||||
"""
|
||||
key = (ip, suffixes)
|
||||
if key in _rdns_cache:
|
||||
return _rdns_cache[key]
|
||||
result = (False, "")
|
||||
try:
|
||||
host = socket.gethostbyaddr(ip)[0].rstrip(".").lower()
|
||||
if any(host.endswith(s) or host == s.lstrip(".") for s in suffixes):
|
||||
_, _, addrs = socket.gethostbyname_ex(host)
|
||||
try:
|
||||
v6 = socket.getaddrinfo(host, None, socket.AF_INET6)
|
||||
addrs = addrs + [a[4][0] for a in v6]
|
||||
except OSError:
|
||||
pass
|
||||
if ip in addrs:
|
||||
result = (True, host)
|
||||
else:
|
||||
result = (False, host + " (no forward match)")
|
||||
else:
|
||||
result = (False, host)
|
||||
except OSError:
|
||||
result = (False, "")
|
||||
_rdns_cache[key] = result
|
||||
return result
|
||||
|
||||
days = [date.today() - timedelta(days=i) for i in range(7 if WEEKLY else 1, 0, -1)]
|
||||
stamps = [d.strftime("%d/%b/%Y") for d in days]
|
||||
|
||||
|
|
@ -142,6 +202,9 @@ spoofed = Counter() # bot -> UA claimed, IP outside vendor ranges
|
|||
proxied = Counter() # bot -> arrived via Cloudflare, unverifiable
|
||||
ver_paths = Counter() # paths fetched by verified bots
|
||||
ver_ips = {} # bot -> set of verified source IPs
|
||||
# rDNS-verified vendors: {bot: {ip: hits}}, resolved after the log pass
|
||||
rdns_hits = {b: Counter() for b in BOT_RDNS}
|
||||
rdns_proxied = Counter()
|
||||
for path in sorted(glob.glob(LOG_GLOB)):
|
||||
opener = gzip.open if path.endswith(".gz") else open
|
||||
with opener(path, "rt", errors="replace") as f:
|
||||
|
|
@ -182,11 +245,58 @@ for path in sorted(glob.glob(LOG_GLOB)):
|
|||
ver_paths[parts[6][:60]] += 1
|
||||
else:
|
||||
spoofed[bot] += 1
|
||||
if WEEKLY and RDNS_ENABLE:
|
||||
rb = next((b for b in sorted(BOT_RDNS, key=len, reverse=True)
|
||||
if b in u), None)
|
||||
# skip if already counted by IP-range check
|
||||
if rb and not (rb in BOT_VENDOR and rb == bot):
|
||||
try:
|
||||
a2 = ipaddress.ip_address(parts[0])
|
||||
except ValueError:
|
||||
a2 = None
|
||||
if a2 is None:
|
||||
pass
|
||||
elif any(a2 in n for n in CFNETS):
|
||||
rdns_proxied[rb] += 1
|
||||
else:
|
||||
rdns_hits[rb][parts[0]] += 1
|
||||
break
|
||||
|
||||
total = sum(v[0] for v in per_day.values())
|
||||
all_ips = set().union(*(v[1] for v in per_day.values()))
|
||||
|
||||
# --- resolve rDNS candidates ---------------------------------------------
|
||||
# One pass over unique addresses, busiest first, capped by RDNS_MAX so a
|
||||
# flood of distinct forgeries cannot stall the report on DNS timeouts.
|
||||
rdns_ok = Counter() # bot -> hits from forward-confirmed addresses
|
||||
rdns_bad = Counter() # bot -> hits that failed confirmation
|
||||
rdns_skipped = Counter() # bot -> hits left unresolved by the cap
|
||||
rdns_private = Counter() # bot -> hits from RFC1918/loopback (see below)
|
||||
rdns_ok_ips = {}
|
||||
if WEEKLY and RDNS_ENABLE:
|
||||
socket.setdefaulttimeout(3)
|
||||
for bot, counter in rdns_hits.items():
|
||||
budget = RDNS_MAX
|
||||
for ip, hits in counter.most_common():
|
||||
# A private source address means the real client IP never
|
||||
# reached the log: something in front (Docker's bridge
|
||||
# gateway, a local proxy) is rewriting it. Neither verified
|
||||
# nor spoofed - the evidence simply is not there.
|
||||
if ipaddress.ip_address(ip).is_private:
|
||||
rdns_private[bot] += hits
|
||||
continue
|
||||
if budget <= 0:
|
||||
rdns_skipped[bot] += hits
|
||||
continue
|
||||
budget -= 1
|
||||
ok, _host = fcrdns(ip, BOT_RDNS[bot])
|
||||
if ok:
|
||||
rdns_ok[bot] += hits
|
||||
rdns_ok_ips.setdefault(bot, set()).add(ip)
|
||||
else:
|
||||
rdns_bad[bot] += hits
|
||||
socket.setdefaulttimeout(None)
|
||||
|
||||
if not WEEKLY:
|
||||
s0 = stamps[0]
|
||||
count, ips = per_day[s0][0], len(per_day[s0][1])
|
||||
|
|
@ -241,6 +351,33 @@ else:
|
|||
lines.append(" Top paths fetched by verified crawlers:")
|
||||
for p, c in ver_paths.most_common(8):
|
||||
lines.append(f" {c:>6} {p}")
|
||||
|
||||
# --- vendors verified by reverse DNS ---------------------------------
|
||||
if RDNS_ENABLE and (rdns_ok or rdns_bad or rdns_proxied):
|
||||
lines.append("")
|
||||
lines.append("-" * 62)
|
||||
lines.append("VERIFIED BY REVERSE DNS (vendors publishing no IP ranges)")
|
||||
lines.append("-" * 62)
|
||||
lines.append(f" {'bot':<22}{'confirmed':>10}{'failed':>8}{'via CF':>8}"
|
||||
f"{'private':>8} {'IPs':>4}")
|
||||
for bot in sorted(set(rdns_ok) | set(rdns_bad) | set(rdns_proxied) | set(rdns_private),
|
||||
key=lambda b: -(rdns_ok[b] + rdns_bad[b] + rdns_proxied[b]
|
||||
+ rdns_private[b])):
|
||||
lines.append(f" {bot:<22}{rdns_ok[bot]:>10}{rdns_bad[bot]:>8}"
|
||||
f"{rdns_proxied[bot]:>8}{rdns_private[bot]:>8}"
|
||||
f" {len(rdns_ok_ips.get(bot, ())):>4}")
|
||||
if rdns_skipped:
|
||||
sk = ", ".join(f"{b} {c}" for b, c in rdns_skipped.most_common(4))
|
||||
lines.append(f" (unresolved, over CRAWLER_RDNS_MAX={RDNS_MAX}: {sk})")
|
||||
lines.append("")
|
||||
lines.append(" Forward-confirmed: the address's PTR record ends in a vendor")
|
||||
lines.append(" domain AND that hostname resolves back to the same address.")
|
||||
lines.append(" 'failed' means the PTR was absent, pointed elsewhere, or did")
|
||||
lines.append(" not confirm - i.e. the user-agent is unsupported by DNS.")
|
||||
if sum(rdns_private.values()):
|
||||
lines.append(" 'private' means the logged source was an RFC1918 address:")
|
||||
lines.append(" a proxy or Docker bridge is masking the real client, so")
|
||||
lines.append(" these cannot be judged either way. See README.")
|
||||
body = "\n".join(lines) + "\n"
|
||||
subject = f"{SITE} weekly crawler report: {total} requests, {len(all_ips)} IPs"
|
||||
if DRY:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue