Match a paid Substack post's "Read more" link tolerantly (review item 8)

A trailing slash, tracking query, fragment, other scheme or host case on
either link no longer lets a paid post through the paid filter.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
CedricandClaude Opus 5.5 committed 2026-10-16 16:04:20 +02:00
1 parent a47ff28ed1
commit 49982c5467
2 files changed
+43 -2

No files matched your search

+18 -2
View File
@@ -54,8 +54,24 @@ class PaywallService {
bool isPaid(Article a) =>
paidTitle.hasMatch(a.title) || _isCutSubstackPost(a) || (_checks[a.link]?.paid ?? false);
static bool _isCutSubstackPost(Article a) =>
_substackCut.firstMatch(a.contentHtml)?.group(1) == a.link;
static bool _isCutSubstackPost(Article a) {
final readMore = _substackCut.firstMatch(a.contentHtml)?.group(1);
return readMore != null && _samePost(readMore, a.link);
}
/// Whether two links point at the same post. Only host and path count:
/// scheme, host case, a trailing slash, the query (tracking parameters)
/// and the fragment don't.
static bool _samePost(String a, String b) {
String? key(String link) {
final uri = Uri.tryParse(link.trim());
if (uri == null || uri.host.isEmpty) return null;
return '${uri.host.toLowerCase()}${uri.path.replaceFirst(RegExp(r'/+$'), '')}';
}
final keyA = key(a);
return keyA != null && keyA == key(b);
}
bool isSponsored(Article a) => sponsoredTitle.hasMatch(a.title);