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

also set snapshot title inside of fetch_title directly

Browse source
This commit is contained in:
Nick Sweeting 2020-07-28 05:56:34 -04:00
parent 273059f054
commit 55a237a435
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
archivebox/extractors/title.py
View file

@ -63,7 +63,10 @@ def save_title(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) ->
html = download_url(link.url, timeout=timeout) html = download_url(link.url, timeout=timeout)
match = re.search(HTML_TITLE_REGEX, html) match = re.search(HTML_TITLE_REGEX, html)
output = htmldecode(match.group(1).strip()) if match else None output = htmldecode(match.group(1).strip()) if match else None
if not output: if output:
if not link.title or len(output) >= len(link.title):
Snapshot.objects.filter(url=link.url, timestamp=link.timestamp).update(title=output)
else:
raise ArchiveError('Unable to detect page title') raise ArchiveError('Unable to detect page title')
except Exception as err: except Exception as err:
status = 'failed' status = 'failed'