mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 14:44:29 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

fix nested archive index page and improve wget output finding

Browse source
This commit is contained in:
Nick Sweeting 2019-03-19 18:10:05 -04:00
parent eb5cc8078a
commit 61ec4971e9
1 changed files with 24 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

29
archivebox/util.py
View file

@ -263,16 +263,29 @@ def wget_output_path(link):
# Since the wget algorithm to for -E (appending .html) is incredibly complex # 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 # 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 # to see what html file wget actually created as the output
wget_folder = base_url(link['url']).rsplit('/', 1)[0].split('/') url_path = without_fragment(without_query(path(link['url']))).strip('/')
look_in = os.path.join(ARCHIVE_DIR, link['timestamp'], *wget_folder) html_parent_folder = (domain(link['url']), *url_path.rsplit('/', 1)[0].split('/'))
look_in = os.path.join(ARCHIVE_DIR, link['timestamp'], *html_parent_folder)
if look_in and os.path.exists(look_in): # look inside innermost path folder for an html file
if os.path.exists(look_in):
html_files = [ html_files = [
f for f in os.listdir(look_in) f for f in os.listdir(look_in)
if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", f, re.I | re.M) if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", f, re.I | re.M)
] ]
if html_files: if html_files:
return urlencode(os.path.join(*wget_folder, html_files[0])) return urlencode(os.path.join(*html_parent_folder, html_files[0]))
# Look one level up in case last path fragment was a file and not a folder
look_in = look_in.rsplit('/', 1)[0]
html_parent_folder = html_parent_folder[:-1]
if os.path.exists(look_in):
html_files = [
f for f in os.listdir(look_in)
if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", f, re.I | re.M)
]
if html_files:
return urlencode(os.path.join(*html_parent_folder, html_files[0]))
return None return None
@ -397,6 +410,12 @@ def derived_link_info(link):
'path': path(url), 'path': path(url),
'basename': basename(url), 'basename': basename(url),
'base_url': base_url(url), 'base_url': base_url(url),
'is_archived': os.path.exists(os.path.join(
ARCHIVE_DIR,
link['timestamp'],
wget_output_path(link) or domain(url)
)),
'num_outputs': len([entry for entry in link['latest'].values() if entry]) if 'latest' in link else 0,
} }
# Archive Method Output URLs # Archive Method Output URLs
@ -405,7 +424,7 @@ def derived_link_info(link):
'index_url': 'index.html', 'index_url': 'index.html',
'favicon_url': 'favicon.ico', 'favicon_url': 'favicon.ico',
'google_favicon_url': 'https://www.google.com/s2/favicons?domain={domain}'.format(**extended_info), 'google_favicon_url': 'https://www.google.com/s2/favicons?domain={domain}'.format(**extended_info),
'archive_url': wget_output_path(link) or 'index.html', 'archive_url': wget_output_path(link),
'warc_url': 'warc', 'warc_url': 'warc',
'pdf_url': 'output.pdf', 'pdf_url': 'output.pdf',
'screenshot_url': 'screenshot.png', 'screenshot_url': 'screenshot.png',