bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-08 03:18:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

use ffmpeg -bitexact to reduce duplicate content storing

Browse Source
This commit is contained in:
msramalho
2025-06-02 19:33:53 +01:00
parent b9f7927a3b
commit dd4e372703
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/auto_archiver/modules/generic_extractor/generic_extractor.py
View File

@@ -394,12 +394,13 @@ class GenericExtractor(Extractor):
for entry in entries:
try:
filename = _helper_get_filename(entry)
logger.warning(f"Using filename {filename} for entry {entry.get('id', 'unknown')}")
if not filename or not os.path.exists(filename):
# file was not downloaded or could not be retrieved, example: sensitive videos on YT without using cookies.
continue
logger.debug(f"Using filename {filename} for entry {entry.get('id', 'unknown')}")
new_media = Media(filename)
for x in ["duration", "original_url", "fulltitle", "description", "upload_date"]:
if x in entry:
@@ -551,6 +552,7 @@ class GenericExtractor(Extractor):
"--write-subs" if self.subtitles else "--no-write-subs",
"--write-auto-subs" if self.subtitles else "--no-write-auto-subs",
"--live-from-start" if self.live_from_start else "--no-live-from-start",
"--postprocessor-args", "ffmpeg:-bitexact" # ensure bitexact output to avoid mismatching hashes for same video
]
# proxy handling