Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-26 06:00:22 +00:00
Code Issues Projects Releases Packages Wiki Activity

append content of referenced files to imports

Browse source
This commit is contained in:
Nick Sweeting 2022-05-09 21:21:39 -07:00
parent f6d6a06c78
commit a6767671fb
1 changed files with 11 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
archivebox/parsers/__init__.py
View file

@ -150,7 +150,17 @@ def run_parser_functions(to_parse: IO[str], timer, root_url: Optional[str]=None,
def save_text_as_source(raw_text: str, filename: str='{ts}-stdin.txt', out_dir: Path=OUTPUT_DIR) -> str:
ts = str(datetime.now(timezone.utc).timestamp()).split('.', 1)[0]
source_path = str(out_dir / SOURCES_DIR_NAME / filename.format(ts=ts))
atomic_write(source_path, raw_text)
referenced_texts = ''
for entry in raw_text.split():
try:
if Path(entry).exists:
referenced_texts += Path(entry).read_text()
except Exception as err:
print(err)
atomic_write(source_path, raw_text + '\n' + referenced_texts)
log_source_saved(source_file=source_path)
return source_path