Fix new regex pattern's flexibility

AngelikiBoura · AngelikiBoura · commit 80c1ea7bb6f1 · 2022-06-15T16:34:13.000+03:00
So the new pattern has the same flexibility with
the original regex pattern
diff --git a/w3lib/html.py b/w3lib/html.py
@@ -22,7 +22,7 @@
     re.DOTALL | re.IGNORECASE,
 )
 _meta_refresh_re2 = re.compile(
-    r'<meta\s[^>]*content\s*=\s*(?P<quote>["\'])(?P<int>(\d*\.)?\d+)\s*;\s*url=\s*(?P<url>.*?)(?P=quote)\shttp-equiv="refresh"',
+     r'<meta\s[^>]*content\s*=\s*(?P<quote>["\'])(?P<int>(\d*\.)?\d+)\s*;\s*url=\s*(?P<url>.*?)(?P=quote)[^>]*?\shttp-equiv\s*=[^>]*refresh',
     re.DOTALL | re.IGNORECASE,
 )
 

Original file line number	Diff line number	Diff line change
`@@ -22,7 +22,7 @@`
`22`	`22`	`re.DOTALL \| re.IGNORECASE,`
`23`	`23`	`)`
`24`	`24`	`_meta_refresh_re2 = re.compile(`
`25`		`- r'<meta\s[^>]content\s=\s(?P<quote>["\'])(?P<int>(\d\.)?\d+)\s;\surl=\s(?P<url>.?)(?P=quote)\shttp-equiv="refresh"',`
	`25`	`+ r'<meta\s[^>]content\s=\s(?P<quote>["\'])(?P<int>(\d\.)?\d+)\s;\surl=\s(?P<url>.?)(?P=quote)[^>]?\shttp-equiv\s=[^>]*refresh',`
`26`	`26`	`re.DOTALL \| re.IGNORECASE,`
`27`	`27`	`)`
`28`	`28`