mirror of
https://github.com/ArchiveBox/ArchiveBox.git
synced 2025-05-15 07:34:27 -04:00
new compiled URL regex with better markdown support
This commit is contained in:
parent
b2c22a73e6
commit
ef4c446c8b
2 changed files with 40 additions and 3 deletions
|
@ -27,12 +27,15 @@ from util import (
|
|||
str_between,
|
||||
get_link_type,
|
||||
URL_REGEX,
|
||||
check_url_parsing,
|
||||
)
|
||||
|
||||
|
||||
def parse_links(path):
|
||||
"""parse a list of links dictionaries from a bookmark export file"""
|
||||
|
||||
check_url_parsing()
|
||||
|
||||
links = []
|
||||
with open(path, 'r', encoding='utf-8') as file:
|
||||
print('{green}[*] [{}] Parsing new links from output/sources/{}...{reset}'.format(
|
||||
|
@ -192,7 +195,6 @@ def parse_shaarli_rss_export(rss_file):
|
|||
|
||||
yield info
|
||||
|
||||
|
||||
def parse_netscape_html_export(html_file):
|
||||
"""Parse netscape-format bookmarks export files (produced by all browsers)"""
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue