Last active
August 28, 2021 20:54
-
-
Save chfour/3a307fef98c4d16a691a134c327be52e to your computer and use it in GitHub Desktop.
yt live chat downloader
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pytchat, argparse | |
parser = argparse.ArgumentParser() | |
parser.add_argument("vid_id", type=str, | |
help="video ID") | |
parser.add_argument("output", type=str, | |
help="output file") | |
args = parser.parse_args() | |
chat = pytchat.create(video_id=args.vid_id, processor=pytchat.JsonfileArchiver(args.output)) | |
while chat.is_alive(): | |
print(f"{chat.get()['total_lines']} lines so far") |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json, fileinput, sys, traceback | |
def parse_runs(runs): | |
content = "" | |
for run in runs: | |
if "emoji" in run.keys(): | |
if "shortcuts" in run["emoji"]: | |
content += run["emoji"]["shortcuts"][0] | |
else: | |
content += "{{" + repr(run["emoji"]["emojiId"]) + "}}" | |
else: | |
content += run["text"] | |
return content | |
try: | |
for l in fileinput.input(): | |
data = json.loads(l) | |
chat_data = data["addChatItemAction"]["item"] | |
if "liveChatTextMessageRenderer" in chat_data: | |
chat_data = chat_data["liveChatTextMessageRenderer"] | |
content = parse_runs(chat_data["message"]["runs"]) | |
author = chat_data["authorName"]["simpleText"] | |
elif "liveChatModeChangeMessageRenderer" in chat_data: | |
chat_data = chat_data["liveChatModeChangeMessageRenderer"] | |
content = parse_runs(chat_data["text"]["runs"]) + " | " + parse_runs(chat_data["subtext"]["runs"]) | |
author = "* SYSTEM *" | |
timestamp = chat_data["timestampText"]["simpleText"] | |
print(f"{timestamp} <{author}> {content}") | |
except Exception as e: | |
print(traceback.format_exc(), file=sys.stderr) | |
print(chat_data, file=sys.stderr) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
alright, I updated the json2txt script, should work now (failed on some emoji, possibly the transgender flag in some cases)