更新: 109 个文件 - 2026-03-18 10:55:52

scripts/intel/sources/vendor_index.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import re
 from html import unescape
+from html.parser import HTMLParser
 from typing import Any, Dict, List
 from urllib.parse import urljoin
 
@@ -9,7 +10,42 @@ from intel.http_client import request
 from intel.models import Candidate
 from intel.utils import unique
 
-from .html_links import ANCHOR_RE, TAG_RE, canonicalize_url
+from .html_links import canonicalize_url
+
+
+class _AnchorCollector(HTMLParser):
+    def __init__(self) -> None:
+        super().__init__()
+        self.links: List[tuple[str, str]] = []
+        self._href: str | None = None
+        self._chunks: List[str] = []
+
+    def handle_starttag(self, tag: str, attrs) -> None:
+        if tag.lower() != "a":
+            return
+        href = dict(attrs).get("href")
+        if href:
+            self._href = href
+            self._chunks = []
+
+    def handle_data(self, data: str) -> None:
+        if self._href is not None:
+            self._chunks.append(data)
+
+    def handle_endtag(self, tag: str) -> None:
+        if tag.lower() != "a" or self._href is None:
+            return
+        text = unescape(" ".join(self._chunks)).strip()
+        self.links.append((self._href, text))
+        self._href = None
+        self._chunks = []
+
+
+def extract_links(html: str) -> List[tuple[str, str]]:
+    parser = _AnchorCollector()
+    parser.feed(html)
+    parser.close()
+    return parser.links
 
 
 def _matches(value: str, patterns: List[str]) -> bool:
@@ -29,9 +65,9 @@ def fetch(system: Dict[str, Any], source: Dict[str, Any]) -> List[Candidate]:
 
     candidates: List[Candidate] = []
     seen = set()
-    for href, text in ANCHOR_RE.findall(html):
+    for href, text in extract_links(html):
         absolute = canonicalize_url(urljoin(source["url"], href))
-        title = unescape(TAG_RE.sub(" ", text)).strip()
+        title = unescape(text).strip()
         if not title:
             continue
         haystack = " ".join(filter(None, [absolute, title])).lower()