mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 06:34:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

fix URL_REGEX 2

Browse source
This commit is contained in:
longzai 2024-04-11 15:51:55 +08:00
parent 4ae765ec27
commit e4dc2701ef
1 changed files with 4 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

9
archivebox/util.py
View file

@ -59,12 +59,11 @@ ts_to_iso = lambda ts: ts and parse_date(ts).isoformat()
URL_REGEX = re.compile( URL_REGEX = re.compile(
r'(?=(' r'(?=('
r'https?://' #match schemes http and https,but can't match ftp r'https?://' #match schemes http and https,but can't match ftp
r'(?:[A-Za-z0-9-]+\.)+[A-Za-z0-9-]+'#match domain r'(?:[A-Za-z0-9-]+\.)*[A-Za-z0-9-]+'#match domain
r'(?::\d+)?' #match port,mabey not occur r'[^\\#\f\n\r\t\v?&]*' #exclude '#' because don't need fragment,
r'(?:/[^\\#\f\n\r\t\v]*)?' #match path and query,maybe not occur #exclude '?' and '&' because url is invalid when '&' appear before '?'
## r'(?:#[^\]\[\(\)<>"\'\s]*){0,1}' #match fragment,but we don't need it actually r'(?:\?[^\\#\f\n\r\t\v]*)*'
r'))', r'))',
## re.IGNORECASE, #don't need to consider case problem
) )
COLOR_REGEX = re.compile(r'\[(?P<arg_1>\d+)(;(?P<arg_2>\d+)(;(?P<arg_3>\d+))?)?m') COLOR_REGEX = re.compile(r'\[(?P<arg_1>\d+)(;(?P<arg_2>\d+)(;(?P<arg_3>\d+))?)?m')