From 79cb25776f46e0b9b1e95052fbd84a59440fa34f Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 21 Aug 2013 04:06:46 +0200 Subject: [PATCH] Cache suitable regular expressions This speeds up TestAllURLsMatching.test_no_duplicates by about 8000% at the cost of minimal memory overhead. --- youtube_dl/extractor/common.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index da50abfc1c..8009c2d857 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -77,7 +77,13 @@ class InfoExtractor(object): @classmethod def suitable(cls, url): """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url) is not None + + # This does not use has/getattr intentionally - we want to know whether + # we have cached the regexp for *this* class, whereas getattr would also + # match the superclass + if '_VALID_URL_RE' not in cls.__dict__: + cls._VALID_URL_RE = re.compile(cls._VALID_URL) + return cls._VALID_URL_RE.match(url) is not None @classmethod def working(cls):