From 077a54233f488ac1e3365d3e93b1ba5c3cf0a7f2 Mon Sep 17 00:00:00 2001 From: Sriram-Nambiar Date: Thu, 15 Oct 2026 18:26:56 +0530 Subject: [PATCH] Add fuzzy rule to rewrite URLs of lesbases.anct.gouv.fr (Fixes #334) --- CHANGELOG.md | 1 + rules/rules.yaml | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index c1edec26..41ff6fb3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Index ePub documents for full-text search, with a new `get_epub_index_data` helper and automatic indexing of ePub items, like PDFs already are (#333) - Send a Wikimedia-compliant default `User-Agent` in `stream_file` when downloading from `upload.wikimedia.org` (#214) +- Add fuzzy rule to rewrite URLs of lesbases.anct.gouv.fr (#334) ### Fixed diff --git a/rules/rules.yaml b/rules/rules.yaml index b1c27347..6a62cc24 100644 --- a/rules/rules.yaml +++ b/rules/rules.yaml @@ -212,3 +212,23 @@ fuzzyRules: fuzzified_url: iranwire.com/questions/detail/1723 - raw_url: iranwire.com/questions/detail/1725?foo=bar&_=1721804454220 fuzzified_url: iranwire.com/questions/detail/1725 + - name: lesbases_anct_gouv_fr + pattern: ((?:www\.)?lesbases\.anct\.gouv\.fr\/[^?]*(?:\?[^#]*?)?)_rsc=[^&]+(.*) + replace: \1_rsc=1\2 + tests: + - raw_url: lesbases.anct.gouv.fr/mentions-legales?_rsc=ut8ee + fuzzified_url: lesbases.anct.gouv.fr/mentions-legales?_rsc=1 + - raw_url: www.lesbases.anct.gouv.fr/mentions-legales?_rsc=ut8ee + fuzzified_url: www.lesbases.anct.gouv.fr/mentions-legales?_rsc=1 + - raw_url: lesbases.anct.gouv.fr/?_rsc=ut8ee + fuzzified_url: lesbases.anct.gouv.fr/?_rsc=1 + - raw_url: lesbases.anct.gouv.fr/cgu?foo=bar&_rsc=ut8ee + fuzzified_url: lesbases.anct.gouv.fr/cgu?foo=bar&_rsc=1 + - raw_url: lesbases.anct.gouv.fr/cgu?_rsc=ut8ee&foo=bar + fuzzified_url: lesbases.anct.gouv.fr/cgu?_rsc=1&foo=bar + - raw_url: lesbases.anct.gouv.fr/mentions-legales + unchanged: true + - raw_url: other.site.fr/mentions-legales?_rsc=ut8ee + unchanged: true + +