mirror/archivebox
1
0
Fork 0
mirror of https://github.com/pirate/ArchiveBox.git synced 2025-08-21 21:57:26 +02:00
Code Issues Releases Wiki Activity

support finding multiple urls as substrings in text

Browse Source
This commit is contained in:
Nick Sweeting
2021-03-27 04:30:40 -04:00
parent f3a3d76439
commit 3e26ae4a66
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
archivebox/util.py
View File

@@ -56,11 +56,13 @@ ts_to_iso = lambda ts: ts and parse_date(ts).isoformat()
URL_REGEX = re.compile( URL_REGEX = re.compile(
r'(?=('
r'http[s]?://' # start matching from allowed schemes r'http[s]?://' # start matching from allowed schemes
r'(?:[a-zA-Z]|[0-9]' # followed by allowed alphanum characters r'(?:[a-zA-Z]|[0-9]' # followed by allowed alphanum characters
r'|[$-_@.&+]|[!*\(\),]' # or allowed symbols r'|[$-_@.&+]|[!*\(\),]' # or allowed symbols
r'|(?:%[0-9a-fA-F][0-9a-fA-F]))' # or allowed unicode bytes r'|(?:%[0-9a-fA-F][0-9a-fA-F]))' # or allowed unicode bytes
r'[^\]\[\(\)<>"\'\s]+', # stop parsing at these symbols r'[^\]\[\(\)<>"\'\s]+' # stop parsing at these symbols
r'))',
re.IGNORECASE, re.IGNORECASE,
) )