mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-06-01 15:28:24 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Add generic_jsonl parser

Browse source 
Resolves #1369
This commit is contained in:
jim winstead 2024-02-29 18:15:06 -08:00
parent 7b042c854a
commit 89ab18c772
6 changed files with 168 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

2
archivebox/parsers/__init__.py
View file

@ -44,6 +44,7 @@ from . import medium_rss
from . import netscape_html
from . import generic_rss
from . import generic_json
from . import generic_jsonl
from . import generic_html
from . import generic_txt
from . import url_list
@ -63,6 +64,7 @@ PARSERS = {
netscape_html.KEY: (netscape_html.NAME, netscape_html.PARSER),
generic_rss.KEY: (generic_rss.NAME, generic_rss.PARSER),
generic_json.KEY: (generic_json.NAME, generic_json.PARSER),
generic_jsonl.KEY: (generic_jsonl.NAME, generic_jsonl.PARSER),
generic_html.KEY: (generic_html.NAME, generic_html.PARSER),
# Catchall fallback parser