-
-
Save rebane2001/c77558b22de1b75a240ab522bd79f297 to your computer and use it in GitHub Desktop.
import json | |
import sys | |
if len(sys.argv) < 2: | |
print("infojsonredact - A simple script to redact private information from ytdl info.json files") | |
print("Output will be saved in info.json.redacted files") | |
print("Usage: infojsonredact.py file1.info.json [file2.info.json, file3.info.json...]") | |
sys.exit(2) | |
redacted = ["url","manifest_url","fragment_base_url","fragments","http_headers","User-Agent","Accept-Charset","Accept","Accept-Encoding","Accept-Language","player_url","playlist","playlist_id","playlist_title","playlist_uploader","playlist_uploader_id","playlist_index","thumbnail","_filename","downloader_options","http_chunk_size","initialization_url","annotations", "playlist_count","version","_version","repository","release_git_head","filesize_approx","_format_sort_fields"] | |
allowed = ["id","uploader","uploader_id","uploader_url","channel_id","channel_url","upload_date","license","creator","title","alt_title","thumbnails","width","height","resolution","description","categories","tags","subtitles","automatic_captions","duration","age_limit","chapters","webpage_url","view_count","like_count","dislike_count","average_rating","formats","ext","format_note","acodec","abr","container","format_id","tbr","asr","fps","language","filesize","vcodec","path","protocol","format","is_live","start_time","end_time","series","season_number","episode_number","track","artist","album","release_date","release_year","extractor","webpage_url_basename","extractor_key","n_entries","display_id","vbr","stretched_ratio","fulltitle","quality","ar","bs","bg","ca","zh","zh-TW","hr","cs","da","nl","en","fi","fr","de","el","iw","hi","hu","id","it","ja","ko","no","pl","pt","pt-BR","pt-PT","ro","ru","sr-Cyrl","sr-Latn","sk","es","sv","th","tr","vi","subscriber_count","live_chat","video_id","en-US","en-UK","en-GB","fr-FR","de-DE","hi-Latn","es-MX","es-419","es-US","zh-CN","preference","segment_urls","af","sq","am","ar","hy","az","bn","eu","be","bs","bg","my","ca","ceb","zh-Hans","zh-Hant","co","hr","cs","da","nl","en","eo","et","fil","fi","fr","gl","ka","de","el","gu","ht","ha","haw","iw","hi","hmn","hu","is","ig","id","ga","it","ja","jv","kn","kk","km","rw","ko","ku","ky","lo","la","lv","lt","lb","mk","mg","ms","ml","mt","mi","mr","mn","ne","no","ny","or","ps","fa","pl","pt","pa","ro","ru","sm","gd","sr","sn","sd","si","sk","sl","so","st","es","su","sw","sv","tg","ta","tt","te","th","tr","tk","uk","ur","ug","uz","vi","cy","fy","xh","yi","yo","zu","rows","columns","audio_ext","video_ext","source_preference","audio_channels","playable_in_embed","om","qu","ts","_type","was_live","webpage_url_domain","ti","sa","nso","name","ln","lg","kri","gn","en-orig","dynamic_range","dv","channel","channel_follower_count","comment_count","duration_string","bho","ay","as","aspect_ratio","ak","epoch","ee","availability","live_status","has_drm","language_preference","und","channel_is_verified"] | |
def redactRecursively(data, allowed, redacted): | |
if isinstance(data, (dict, list)): | |
for k, v in (data.items() if isinstance(data, dict) else enumerate(data)): | |
if k in redacted: | |
data[k] = "[REDACTED]" | |
continue | |
elif not k in allowed: | |
if not isinstance(k, int): | |
raise KeyError("Key", k, "not found in both the redacted and allowed keysets") | |
redactRecursively(v, allowed, redacted) | |
for filename in sys.argv[1:]: | |
print(filename) | |
with open(filename,"r",encoding="utf-8") as f: | |
infojson = json.load(f) | |
redactRecursively(infojson, allowed, redacted) | |
with open(filename + ".redacted","w",encoding="utf-8") as f: | |
json.dump(infojson,f) | |
as long as we're confident what's outside the mask is the contents of the other list
Yeah this is why we can't do that.
does it know about sensitive tags in use before 2020
I think I worked on files from 2017 when I first wrote this, but it's always possible there's something that slipped through the cracks at some point.
What you're proposing is pretty involved and would take a lot of effort to do. You can feel free to do that if you'd like, but this script here is just supposed to be quick and simple. I don't think it's worth it to go through all of that effort.
I think I worked on files from 2017 when I first wrote this, but it's always possible there's something that slipped through the cracks at some point.
Good to know.
What you're proposing is pretty involved and would take a lot of effort to do. You can feel free to do that if you'd like, but this script here is just supposed to be quick and simple. I don't think it's worth it to go through all of that effort.
It's no project of mine. I just wanted to make explicit what it would take for the script to be "complete". It's no life or death situation, even though the way I wrote that might've made it sound like that
Personally, the only change I would make (and did myself while running this tool) with regards to what's done when an unknown key is found is to print the contents of the unknown value before throwing the error, this made determining which category the key should be in a little easier.
I plan on adding that, as well as something to deal with language keys so they don't all need to be in the list one-by-one.
Strictly speaking, to those two goals you still don't need to compare against two lists. We can still have control where tags go whilst still only masking with one list, as long as we're confident what's outside the mask is the contents of the other list. The reason we can't do this however, is the uncertainty in the changing info.json format.
Which leads me a different question, this script was started in 2020, does it know about sensitive tags in use before 2020? Assuming the aim is to be able to redact private information from any info.json, that also includes info.json files created at any time. Can we know some youtube dl version in 2011 or at other time didn't write a tag that should be redacted?
Only when we've done an entire history of info.json files can we handle all info.json files.