Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-29 23:50:22 +00:00
Code Issues Projects Releases Packages Wiki Activity

Don't be strict on unicode errors

Browse source
This commit is contained in:
Joseph Turian 2022-09-12 20:40:45 +00:00
parent dba423a568
commit b864c38d9e
1 changed files with 10 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
archivebox/extractors/media.py
View file

@ -74,7 +74,16 @@ def save_media(link: Link, out_dir: Optional[Path]=None, timeout: int=MEDIA_TIME
# add video description and subtitles to full-text index # add video description and subtitles to full-text index
# Let's try a few different # Let's try a few different
index_texts = [ index_texts = [
text_file.read_text(encoding='utf-8').strip() # errors:
# * 'strict' to raise a ValueError exception if there is an
# encoding error. The default value of None has the same effect.
# * 'ignore' ignores errors. Note that ignoring encoding errors
# can lead to data loss.
# * 'xmlcharrefreplace' is only supported when writing to a
# file. Characters not supported by the encoding are replaced with
# the appropriate XML character reference &#nnn;.
# There are a few more options described in https://docs.python.org/3/library/functions.html#open
text_file.read_text(encoding='utf-8', errors='xmlcharrefreplace').strip()
for text_file in ( for text_file in (
*output_path.glob('*.description'), *output_path.glob('*.description'),
*output_path.glob('*.srt'), *output_path.glob('*.srt'),