From b8fe25c580a8cafc14c32890f0635c7daecafc4d Mon Sep 17 00:00:00 2001 From: I-Al-Istannen Date: Wed, 4 May 2022 14:13:39 +0200 Subject: [PATCH] Add `.cpp` to ipd link regex --- CHANGELOG.md | 3 +++ PFERD/crawl/kit_ipd_crawler.py | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 310059a..22fdd29 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -22,6 +22,9 @@ ambiguous situations. ## Unreleased +### Changed +- Add `.cpp` to IPD link regex + ## 3.4.0 - 2022-05-01 ### Added diff --git a/PFERD/crawl/kit_ipd_crawler.py b/PFERD/crawl/kit_ipd_crawler.py index 1a5314b..e5ec58f 100644 --- a/PFERD/crawl/kit_ipd_crawler.py +++ b/PFERD/crawl/kit_ipd_crawler.py @@ -27,7 +27,7 @@ class KitIpdCrawlerSection(HttpCrawlerSection): return target def link_regex(self) -> Pattern[str]: - regex = self.s.get("link_regex", r"^.*/[^/]*\.(?:pdf|zip|c|java)$") + regex = self.s.get("link_regex", r"^.*/[^/]*\.(?:pdf|zip|c|cpp|java)$") return re.compile(regex)