mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-14 15:14:31 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix usage of ARCHIVE_DIR if an exisiting archive is updated

Browse source
This commit is contained in:
Marco Rossi 2017-11-02 11:55:30 +01:00
parent eaaba8bb04
commit d2b8be28db
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
util.py
View file

@ -254,7 +254,7 @@ def find_link(folder, links):
timestamp = folder.split('.')[0] timestamp = folder.split('.')[0]
for link in links: for link in links:
if link['timestamp'].startswith(timestamp): if link['timestamp'].startswith(timestamp):
if link['domain'] in os.listdir('./html/archive/' + folder): if link['domain'] in os.listdir(os.path.join(ARCHIVE_DIR, 'html/archive', folder)):
return link # careful now, this isn't safe for most ppl return link # careful now, this isn't safe for most ppl
if link['domain'] in parse_url(folder): if link['domain'] in parse_url(folder):
return link return link
@ -263,7 +263,7 @@ def find_link(folder, links):
def parse_url(folder): def parse_url(folder):
"""for a given archive folder, figure out what url it's for""" """for a given archive folder, figure out what url it's for"""
link_json = os.path.join('./html/archive/' + folder, 'index.json') link_json = os.path.join(ARCHIVE_DIR, 'html/archive', folder, 'index.json')
if os.path.exists(link_json): if os.path.exists(link_json):
with open(link_json, 'r') as f: with open(link_json, 'r') as f:
try: try:
@ -274,7 +274,7 @@ def parse_url(folder):
except ValueError: except ValueError:
print('File contains invalid JSON: {}!'.format(link_json)) print('File contains invalid JSON: {}!'.format(link_json))
archive_org_txt = os.path.join('./html/archive/' + folder, 'archive.org.txt') archive_org_txt = os.path.join(ARCHIVE_DIR, 'html/archive' + folder, 'archive.org.txt')
if os.path.exists(archive_org_txt): if os.path.exists(archive_org_txt):
with open(archive_org_txt, 'r') as f: with open(archive_org_txt, 'r') as f:
original_link = f.read().strip().split('/http', 1)[-1] original_link = f.read().strip().split('/http', 1)[-1]