mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 06:34:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

check for non html files from wget

Browse source
This commit is contained in:
Nick Sweeting 2021-01-22 14:06:01 -05:00
parent c6f0b8e6b3
commit 9764a8ed9b
1 changed files with 11 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
archivebox/extractors/wget.py
View file

@ -175,11 +175,22 @@ def wget_output_path(link: Link) -> Optional[str]:
if html_files: if html_files:
return str(html_files[0].relative_to(link.link_dir)) return str(html_files[0].relative_to(link.link_dir))
# sometimes wget'd URLs have no ext and return non-html
# e.g. /some/example/rss/all -> some RSS XML content)
# /some/other/url.o4g -> some binary unrecognized ext)
# test this with archivebox add --depth=1 https://getpocket.com/users/nikisweeting/feed/all
last_part_of_url = urldecode(full_path.rsplit('/', 1)[-1])
for file_present in os.listdir(search_dir):
if file_present == last_part_of_url:
return os.path.join(path_from_link_dir, file_present)
# Move up one directory level # Move up one directory level
search_dir = search_dir.parent search_dir = search_dir.parent
if str(search_dir) == link.link_dir: if str(search_dir) == link.link_dir:
break break
search_dir = Path(link.link_dir) / domain(link.url).replace(":", "+") / urldecode(full_path) search_dir = Path(link.link_dir) / domain(link.url).replace(":", "+") / urldecode(full_path)
if not search_dir.is_dir(): if not search_dir.is_dir():