Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-26 14:10:20 +00:00
Code Issues Projects Releases Packages Wiki Activity

fix wget_output_path relative location building

Browse source
This commit is contained in:
Nick Sweeting 2019-03-20 02:37:27 -04:00
parent 9c166d5bcf
commit ac56023bfd
1 changed files with 22 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
archivebox/util.py
View file

@ -263,29 +263,30 @@ 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
url_path = without_fragment(without_query(path(link['url']))).strip('/') link_dir = os.path.join(ARCHIVE_DIR, link['timestamp'])
html_parent_folder = (domain(link['url']), *url_path.rsplit('/', 1)[0].split('/')) full_path = without_fragment(without_query(path(link['url']))).strip('/')
look_in = os.path.join(ARCHIVE_DIR, link['timestamp'], *html_parent_folder) search_dir = os.path.join(
link_dir,
domain(link['url']),
full_path,
)
# look inside innermost path folder for an html file for _ in range(4):
if os.path.exists(look_in): if os.path.exists(search_dir):
html_files = [ if os.path.isdir(search_dir):
f for f in os.listdir(look_in) html_files = [
if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", f, re.I | re.M) f for f in os.listdir(search_dir)
] if re.search(".+\\.[Hh][Tt][Mm][Ll]?$", f, re.I | re.M)
if html_files: ]
return urlencode(os.path.join(*html_parent_folder, html_files[0])) if html_files:
relative_path = search_dir.split(link_dir)[-1].strip('/')
return urlencode(os.path.join(relative_path, html_files[0]))
# Look one level up in case last path fragment was a file and not a folder # Move up one directory level
look_in = look_in.rsplit('/', 1)[0] search_dir = search_dir.rsplit('/', 1)[0]
html_parent_folder = html_parent_folder[:-1]
if os.path.exists(look_in): if search_dir == link_dir:
html_files = [ break
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