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

save the url as title for staticfiles or non html files

Browse source
This commit is contained in:
Nick Sweeting 2021-01-30 22:01:49 -05:00
parent 24e24934f7
commit 385daf9af8
1 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
archivebox/extractors/title.py
View file

@ -62,9 +62,6 @@ class TitleParser(HTMLParser):
@enforce_types @enforce_types
def should_save_title(link: Link, out_dir: Optional[str]=None, overwrite: Optional[bool]=False) -> bool: def should_save_title(link: Link, out_dir: Optional[str]=None, overwrite: Optional[bool]=False) -> bool:
if is_static_file(link.url):
return False
# if link already has valid title, skip it # if link already has valid title, skip it
if not overwrite and link.title and not link.title.lower().startswith('http'): if not overwrite and link.title and not link.title.lower().startswith('http'):
return False return False
@ -113,7 +110,11 @@ def save_title(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) -
timestamp=link.timestamp)\ timestamp=link.timestamp)\
.update(title=output) .update(title=output)
else: else:
raise ArchiveError('Unable to detect page title') # if no content was returned, dont save a title (because it might be a temporary error)
if not html:
raise ArchiveError('Unable to detect page title')
# output = html[:128] # use first bit of content as the title
output = link.base_url # use the filename as the title (better UX)
except Exception as err: except Exception as err:
status = 'failed' status = 'failed'
output = err output = err