fix(list): Repair PhishTank filter

Author: T145

data/v2/manifest.json

@@ -8378,7 +8378,7 @@
     "checksums": {},
     "content": {
       "filter": "NONE",
-      "retriever": "LYNX",
+      "retriever": "ARIA2",
       "type": "CSV"
     },
     "formats": [

docker/Dockerfile

@@ -110,10 +110,10 @@ USER root
 WORKDIR /root
 
 LABEL maintainer="T145" \
-      version="7.1.1" \
+      version="7.1.3" \
       description="Runs the \"Black Mirror\" project! Check it out GitHub!" \
       org.opencontainers.image.created="2025-11-01" \
-      org.opencontainers.image.revision="7.1.1" \
+      org.opencontainers.image.revision="7.1.3" \
       org.opencontainers.image.source="https://github.com/T145/black-mirror" \
       org.opencontainers.image.url="https://github.com/T145/black-mirror" \
       org.opencontainers.image.vendor="T145" \
@@ -194,6 +194,7 @@ RUN apk add --no-cache --virtual .perl-build build-base curl gnutar xz perl-util
     make -j"$(nproc)"; \
     TEST_JOBS="$(nproc)" make test_harness || true; \
     make install; \
+    ln -sf /usr/local/bin/perl /usr/bin/perl; \
     apk del .perl-build
 
 WORKDIR /usr/src

logs/aria2.log

@@ -0,0 +1,12 @@
+2026-01-21 20:58:00.305701 [NOTICE] [Context.cc:310] Downloading 1 item(s)
+2026-01-21 20:58:00.313030 [NOTICE] [ServerStatMan.cc:230] ServerStat file logs/server-stats.txt loaded successfully.
+2026-01-21 20:58:00.388268 [NOTICE] [HttpResponse.cc:168] CUID#7 - Redirecting to https://cdn.phishtank.com/datadumps/verified_online.csv?Expires=1769028790&Signature=MKUQigJidNgZ397xQp0ax9jfTmYX3-8VdCJ400GIiUQ3Ic7iff5wKevZv42c7w-wxADHbAVemYavMvBWecUWXmVWnJrS3m2VSCP7ctO6KdsFO76OohBQGesdtQuL2Ont4K~Teqo4QTrNINoEAkcftRsjD6hSdwFuZT-raJKYvmY9GVlaQlVZmJG27wXITFoud9edU7p5I091YzVYKyWOgkcr3B788vY35Eju7OSjVZPfA1~kNT0PJ1k0EpI9JRo8q4p46DQZ~AYowqIBJb9TWmNOSQJgIDzbFRHWDfZwrLeARCjPi11RBk~CqnimBicUswmYoFUwVZBR5xVnTjf90g__&Key-Pair-Id=APKAILB45UG3RB4CSOJA
+2026-01-21 20:58:00.740747 [NOTICE] [RequestGroup.cc:1214] Download complete: /tmp/phishtank_aria2.csv
+2026-01-21 20:58:00.744948 [NOTICE] [ServerStatMan.cc:110] ServerStat file logs/server-stats.txt saved successfully.
+2026-01-21 20:58:15.776673 [NOTICE] [Context.cc:310] Downloading 1 item(s)
+2026-01-21 20:58:15.782912 [NOTICE] [ServerStatMan.cc:230] ServerStat file logs/server-stats.txt loaded successfully.
+2026-01-21 20:58:15.984072 [ERROR] [AbstractCommand.cc:401] CUID#7 - Download aborted. URI=https://phishstats.info/phish_score.csv
+Exception: [AbstractCommand.cc:403] errorCode=4 URI=https://phishstats.info/phish_score.csv
+  -> [RequestGroup.cc:1266] errorCode=4 Reached max-file-not-found count=1
+2026-01-21 20:58:15.984263 [NOTICE] [RequestGroupMan.cc:424] Download GID#049ba6c9e563a68f not complete: /tmp/phishstats.csv
+2026-01-21 20:58:15.987903 [NOTICE] [ServerStatMan.cc:110] ServerStat file logs/server-stats.txt saved successfully.

logs/server-stats.txt

@@ -0,0 +1 @@
+host=data.phishtank.com, protocol=https, dl_speed=6003128, sc_avg_speed=6003128, mc_avg_speed=0, last_updated=1769029080, counter=1, status=OK

scripts/v2/apply_filters.bash

@@ -212,8 +212,8 @@ process_list() {
 			'WATCHLIST_INTERNET') mlr --mmap --csv --ifs ';' -N cut -f 1 ;;
 			'CRUZ_IT') mlr --mmap --csv --headerless-csv-output clean-whitespace then cut -f ip_address ;;
 			# PhishTank often includes large hashes in its URLs, which may lead to parsing issues.
-			# Therefore use regex that ignores paths and queries after the domain.
-			'PHISHTANK') mlr --mmap --csv --headerless-csv-output --lazy-quotes put -S '$url =~ "https?://([^/]+)"; $Domain = "\1"' then cut -f Domain ;;
+			# Therefore use a robust regex that ignores paths and queries after the domain.
+			'PHISHTANK') mlr --mmap --csv --headerless-csv-output --lazy-quotes --skip-comments clean-whitespace then cut -f url | get_domains_from_urls ;;
 			'BLOCKLIST_UA') mlr --mmap --csv --headerless-csv-output --ifs ';' cut -f IP ;;
 			# The C2 feed has malformed CSVs.
 			'THREATVIEW_C2_HOSTS') mawk -F, '/^[^#]/{print $3}' ;;