merge #3870: [blogger] update 'sub' regex to get the highest resolution url

pull/3871/head
Mike Fährmann 1 year ago
commit 5ca9d55595
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

@ -40,7 +40,7 @@ class BloggerExtractor(Extractor):
blog["date"] = text.parse_datetime(blog["published"]) blog["date"] = text.parse_datetime(blog["published"])
del blog["selfLink"] del blog["selfLink"]
sub = re.compile(r"(/|=)(?:s\d+|w\d+-h\d+)(?=/|$)").sub sub = re.compile(r"(/|=)(?:[sw]\d+|w\d+-h\d+)(?=/|$)").sub
findall_image = re.compile( findall_image = re.compile(
r'src="(https?://(?:' r'src="(https?://(?:'
r'blogger\.googleusercontent\.com/img|' r'blogger\.googleusercontent\.com/img|'

Loading…
Cancel
Save