summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2013-08-21 04:06:46 +0200
committerPhilipp Hagemeister <[email protected]>2013-08-21 04:06:48 +0200
commit79cb25776f46e0b9b1e95052fbd84a59440fa34f (patch)
tree215f70461585e3f4275aff64a4ba0047b8845435
parent87f78946a56d19fe3696725fe7329767fd910320 (diff)
downloadyoutube-dl-79cb25776f46e0b9b1e95052fbd84a59440fa34f.tar.gz
youtube-dl-79cb25776f46e0b9b1e95052fbd84a59440fa34f.zip
Cache suitable regular expressions
This speeds up TestAllURLsMatching.test_no_duplicates by about 8000% at the cost of minimal memory overhead.
-rw-r--r--youtube_dl/extractor/common.py8
1 files changed, 7 insertions, 1 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index da50abfc1..8009c2d85 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):