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 handling of wget file paths

Browse source
This commit is contained in:
Nick Sweeting 2018-04-17 17:16:29 -04:00
parent dbe4660da3
commit b926b1affc
3 changed files with 30 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

7
archive_methods.py
View file

@ -70,7 +70,7 @@ def archive_links(archive_path, links, source=None, resume=None):
raise SystemExit(1)
def archive_link(link_dir, link, overwrite=False):
def archive_link(link_dir, link, overwrite=True):
"""download the DOM, PDF, and a screenshot into a folder named after the link's timestamp"""
update_existing = os.path.exists(link_dir)
@ -183,8 +183,9 @@ def fetch_wget(link_dir, link, requisites=FETCH_WGET_REQUISITES, timeout=TIMEOUT
"""download full site using wget"""
domain_dir = os.path.join(link_dir, link['domain'])
if os.path.exists(domain_dir):
return {'output': wget_output_path(link, look_in=domain_dir), 'status': 'skipped'}
existing_file = wget_output_path(link)
if os.path.exists(domain_dir) and existing_file:
return {'output': existing_file, 'status': 'skipped'}
CMD = [
# WGET CLI Docs: https://www.gnu.org/software/wget/manual/wget.html

4
links.py
View file

@ -63,10 +63,10 @@ def validate_links(links):
link['latest']['wget'] = wget_output_path(link)
if not link['latest'].get('pdf'):
link['latest']['pdf'] = wget_output_path(link)
link['latest']['pdf'] = None
if not link['latest'].get('screenshot'):
link['latest']['screenshot'] = wget_output_path(link)
link['latest']['screenshot'] = None
return list(links)

44
util.py
View file

@ -411,8 +411,8 @@ def wget_output_path(link, look_in=None):
# Since the wget algorithm to for -E (appending .html) is incredibly complex
# instead of trying to emulate it here, we just look in the output folder
# to see what html file wget actually created as the output
wget_folder = link['base_url'].rsplit('/', 1)[0]
look_in = look_in or os.path.join(HTML_FOLDER, 'archive', link['timestamp'], wget_folder)
wget_folder = link['base_url'].rsplit('/', 1)[0].split('/')
look_in = os.path.join(HTML_FOLDER, 'archive', link['timestamp'], *wget_folder)
if look_in and os.path.exists(look_in):
html_files = [
@ -420,29 +420,31 @@ def wget_output_path(link, look_in=None):
if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", f, re.I | re.M)
]
if html_files:
return urlencode(os.path.join(wget_folder, html_files[0]))
return urlencode(os.path.join(*wget_folder, html_files[0]))
return None
# If finding the actual output file didn't work, fall back to the buggy
# implementation of the wget .html appending algorithm
split_url = link['url'].split('#', 1)
query = ('%3F' + link['url'].split('?', 1)[-1]) if '?' in link['url'] else ''
# split_url = link['url'].split('#', 1)
# query = ('%3F' + link['url'].split('?', 1)[-1]) if '?' in link['url'] else ''
if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", split_url[0], re.I | re.M):
# already ends in .html
return urlencode(link['base_url'])
else:
# .html needs to be appended
without_scheme = split_url[0].split('://', 1)[-1].split('?', 1)[0]
if without_scheme.endswith('/'):
if query:
return urlencode('#'.join([without_scheme + 'index.html' + query + '.html', *split_url[1:]]))
return urlencode('#'.join([without_scheme + 'index.html', *split_url[1:]]))
else:
if query:
return urlencode('#'.join([without_scheme + '/index.html' + query + '.html', *split_url[1:]]))
elif '/' in without_scheme:
return urlencode('#'.join([without_scheme + '.html', *split_url[1:]]))
return urlencode(link['base_url'] + '/index.html')
# if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", split_url[0], re.I | re.M):
# # already ends in .html
# return urlencode(link['base_url'])
# else:
# # .html needs to be appended
# without_scheme = split_url[0].split('://', 1)[-1].split('?', 1)[0]
# if without_scheme.endswith('/'):
# if query:
# return urlencode('#'.join([without_scheme + 'index.html' + query + '.html', *split_url[1:]]))
# return urlencode('#'.join([without_scheme + 'index.html', *split_url[1:]]))
# else:
# if query:
# return urlencode('#'.join([without_scheme + '/index.html' + query + '.html', *split_url[1:]]))
# elif '/' in without_scheme:
# return urlencode('#'.join([without_scheme + '.html', *split_url[1:]]))
# return urlencode(link['base_url'] + '/index.html')
def derived_link_info(link):