Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-10 06:34:16 +00:00
Code Issues Projects Releases Packages Wiki Activity

fix urldecoding of titles

Browse source
This commit is contained in:
Nick Sweeting 2018-04-17 10:30:25 -04:00
parent 650380efce
commit dbe4660da3
2 changed files with 16 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
index.py
View file

@ -146,7 +146,7 @@ def write_html_link_index(out_dir, link):
'bookmarked': datetime.fromtimestamp(float(link['timestamp'])).strftime('%Y-%m-%d %H:%M'),
'updated': datetime.fromtimestamp(float(link['updated'])).strftime('%Y-%m-%d %H:%M'),
'archive_org': link['latest'].get('archive_org') or 'https://web.archive.org/save/{}'.format(link['url']),
'wget': link['latest'].get('wget') or link['domain'],
'wget': link['latest'].get('wget') or wget_output_path(link),
}))
chmod_file(path)

17
links.py
View file

@ -33,7 +33,7 @@ Link {
"""
import datetime
from urllib.parse import unquote
from html import unescape
from util import (
domain,
@ -41,6 +41,7 @@ from util import (
str_between,
get_link_type,
merge_links,
wget_output_path,
)
from config import ANSI
@ -54,6 +55,19 @@ def validate_links(links):
print('[X] No links found :(')
raise SystemExit(1)
for link in links:
link['title'] = unescape(link['title'])
link['latest'] = link.get('latest') or {}
if not link['latest'].get('wget'):
link['latest']['wget'] = wget_output_path(link)
if not link['latest'].get('pdf'):
link['latest']['pdf'] = wget_output_path(link)
if not link['latest'].get('screenshot'):
link['latest']['screenshot'] = wget_output_path(link)
return list(links)
@ -86,7 +100,6 @@ def uniquefied_links(sorted_links):
unique_timestamps = {}
for link in unique_urls.values():
link['timestamp'] = lowest_uniq_timestamp(unique_timestamps, link['timestamp'])
link['title'] = unquote(link['title'])
unique_timestamps[link['timestamp']] = link
return unique_timestamps.values()