mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 22:54:27 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

improve title extractor

Browse source
This commit is contained in:
papersnake 2022-02-08 23:17:52 +08:00
parent bf432d4931
commit de8e22efb7
3 changed files with 26 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

23
archivebox/extractors/title.py
View file

@ -58,6 +58,27 @@ class TitleParser(HTMLParser):
if tag.lower() == "title":
self.inside_title_tag = False
@enforce_types
def get_html(link: Link, path: Path, timeout: int=TIMEOUT) -> str:
"""
Try to find wget, singlefile and then dom files.
If none is found, download the url again.
"""
canonical = link.canonical_outputs()
abs_path = path.absolute()
sources = [canonical["singlefile_path"], canonical["wget_path"], canonical["dom_path"]]
document = None
for source in sources:
try:
with open(abs_path / source, "r", encoding="utf-8") as f:
document = f.read()
break
except (FileNotFoundError, TypeError):
continue
if document is None:
return download_url(link.url, timeout=timeout)
else:
return document
@enforce_types
def should_save_title(link: Link, out_dir: Optional[str]=None, overwrite: Optional[bool]=False) -> bool:
@ -90,7 +111,7 @@ def save_title(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) -
status = 'succeeded'
timer = TimedProgress(timeout, prefix=' ')
try:
html = download_url(link.url, timeout=timeout)
html = get_html(link, out_dir, timeout=timeout)
try:
# try using relatively strict html parser first
parser = TitleParser()