chore: cleanup debug scripts and logs

This commit is contained in:
KV-Tube Deployer 2026-01-18 21:47:31 +07:00
parent a16d3481bd
commit eefc5120e6
10 changed files with 0 additions and 357 deletions

View file

@ -1,55 +0,0 @@
import time
import sys
import subprocess
import json
import yt_dlp
QUERY = "latest smart technology gadgets reviews"
LIMIT = 20
def test_subprocess():
start = time.time()
cmd = [
sys.executable, "-m", "yt_dlp",
f"ytsearch{LIMIT}:{QUERY}",
"--dump-json",
"--flat-playlist",
"--no-playlist",
"--no-warnings"
]
proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
out, err = proc.communicate()
end = time.time()
count = len(out.splitlines())
return end - start, count
def test_library():
start = time.time()
ydl_opts = {
'headers': {'User-Agent': 'Mozilla/5.0'},
'skip_download': True,
'extract_flat': True,
'noplaylist': True,
'quiet': True,
'no_warnings': True,
}
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
res = ydl.extract_info(f"ytsearch{LIMIT}:{QUERY}", download=False)
count = len(res.get('entries', []))
end = time.time()
return end - start, count
if __name__ == "__main__":
print("Benchmarking Subprocess...")
try:
sub_time, sub_count = test_subprocess()
print(f"Subprocess: {sub_time:.4f}s (Fetched {sub_count} items)")
except Exception as e:
print(f"Subprocess Failed: {e}")
print("\nBenchmarking Library...")
try:
lib_time, lib_count = test_library()
print(f"Library: {lib_time:.4f}s (Fetched {lib_count} items)")
except Exception as e:
print(f"Library Failed: {e}")

View file

@ -1,8 +0,0 @@
Batch fetching for: ['IpqiLXy4im8', 'o_rtfAazE5s', 'VexXHSzibxY', 'U2oEJKsPdHo', 'dQw4w9WgXcQ', 'h22z894ThnQ', 'Fp7FcfGNpWg', 'z_G_8i95SMA']
Using python: C:\Program Files\Python312\python.exe
Command prepared: ['C:\\Program Files\\Python312\\python.exe', '-m', 'yt_dlp'] ... [len:16]
Result lines: 8
Batch fetching for: ['IpqiLXy4im8', 'o_rtfAazE5s', 'VexXHSzibxY', 'U2oEJKsPdHo', 'dQw4w9WgXcQ', 'h22z894ThnQ', 'Fp7FcfGNpWg', 'z_G_8i95SMA']
Using python: C:\Program Files\Python312\python.exe
Command prepared: ['C:\\Program Files\\Python312\\python.exe', '-m', 'yt_dlp'] ... [len:16]
Result lines: 8

View file

@ -1,3 +0,0 @@
Fetching for qZvqydUEzqA...
Results type: <class 'list'>
Results is empty/None.

View file

@ -1,2 +0,0 @@
APP: C:\Users\Admin\Documents\Projects-Khoa.vo\kv-tube\current\kv-tube\app\__init__.py
API: C:\Users\Admin\Documents\Projects-Khoa.vo\kv-tube\current\kv-tube\app\routes\api.py

View file

@ -1,81 +0,0 @@
from ytfetcher import YTFetcher
from ytfetcher.config import HTTPConfig
import random
import os
import http.cookiejar
import logging
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
def debug_fetch(video_id):
try:
# 1. Prepare Cookies if available
cookie_header = ""
cookies_path = 'cookies.txt'
if os.path.exists(cookies_path):
try:
cj = http.cookiejar.MozillaCookieJar(cookies_path)
cj.load()
cookies_list = []
for cookie in cj:
cookies_list.append(f"{cookie.name}={cookie.value}")
cookie_header = "; ".join(cookies_list)
logger.info(f"Loaded {len(cookies_list)} cookies for YTFetcher")
except Exception as e:
logger.warning(f"Failed to process cookies: {e}")
# 2. Configuration to look like a real browser
user_agents = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.2 Safari/605.1.15",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0"
]
headers = {
"User-Agent": random.choice(user_agents),
"Accept-Language": "en-US,en;q=0.9",
}
# Inject cookie header if we have it
if cookie_header:
headers["Cookie"] = cookie_header
config = HTTPConfig(headers=headers)
print(f"Initializing YTFetcher for {video_id}...")
# Initialize Fetcher
fetcher = YTFetcher.from_video_ids(
video_ids=[video_id],
http_config=config,
languages=['en', 'en-US', 'vi']
)
# Fetch
print(f"Fetching transcripts...")
results = fetcher.fetch_transcripts()
print(f"Results type: {type(results)}")
print(f"Results length: {len(results) if results else 0}")
if results:
data = results[0]
if data.transcripts:
print("Transcript found!")
text_lines = [t.text.strip() for t in data.transcripts if t.text.strip()]
print(f"First 3 lines: {text_lines[:3]}")
else:
print("No transcripts inside data object.")
# Maybe print available tracks if possible?
else:
print("Results is empty.")
except Exception as e:
import traceback
print(f"CRITICAL ERROR: {e}")
print(traceback.format_exc())
if __name__ == "__main__":
debug_fetch("qZvqydUEzqA")

View file

@ -1,3 +0,0 @@
Unique videos count: 5
IDs to hydrate: ['AlGfj9JBdAI', 'MhQGDAGVIa8', 'Fp7FcfGNpWg', 'Z2KlYnsPaIk', 'f_4uUX9n538']
Metadata map keys: ['MhQGDAGVIa8', 'Fp7FcfGNpWg', 'AlGfj9JBdAI', 'Z2KlYnsPaIk', 'f_4uUX9n538']

View file

@ -1,185 +0,0 @@
import json
import time
cookies_data = [
{
"domain": ".youtube.com",
"expirationDate": 1802692356.635205,
"hostOnly": False,
"httpOnly": True,
"name": "__Secure-3PSID",
"path": "/",
"sameSite": "no_restriction",
"secure": True,
"session": False,
"storeId": None,
"value": "g.a0005gie1lAkmYZc-EPeGx77pCrXo_Cz5eAi-e9aryb9Qoz967v4Caiou6Tt5ZyLR4iMp5I51wACgYKASISARESFQHGX2MiopTeGBKXybppZWNr7JzmKhoVAUF8yKrgfPx-gEb02gGAV3ZaVOGr0076"
},
{
"domain": ".youtube.com",
"expirationDate": 1800281710.070798,
"hostOnly": False,
"httpOnly": True,
"name": "__Secure-1PSIDTS",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "sidts-CjQB7I_69DRJdiQQGddE6tt-GHilv2IjDZd8S6FlWCjx2iReOoNtQMUkb55vaBdl8vBK7J_DEAA"
},
{
"domain": ".youtube.com",
"expirationDate": 1802692356.635439,
"hostOnly": False,
"httpOnly": False,
"name": "SAPISID",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "DP6iRyLCM_cFV1Gw/AN2nemkVrvJ2p8MWb"
},
{
"domain": ".youtube.com",
"expirationDate": 1800281710.070999,
"hostOnly": False,
"httpOnly": True,
"name": "__Secure-1PSIDCC",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "AKEyXzU66C7YKqYKgxpR8BbWvDlICFaXQCERc_NLnU_QLkcHrmR0aPQJTFLW1WesYcSYtIJYW3o"
},
{
"domain": ".youtube.com",
"expirationDate": 1802692356.635327,
"hostOnly": False,
"httpOnly": True,
"name": "SSID",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "A4isk9AE9xActvzYy"
},
{
"domain": ".youtube.com",
"expirationDate": 1802692356.635505,
"hostOnly": False,
"httpOnly": False,
"name": "__Secure-1PAPISID",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "DP6iRyLCM_cFV1Gw/AN2nemkVrvJ2p8MWb"
},
{
"domain": ".youtube.com",
"expirationDate": 1802692356.635139,
"hostOnly": False,
"httpOnly": True,
"name": "__Secure-1PSID",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "g.a0005gie1lAkmYZc-EPeGx77pCrXo_Cz5eAi-e9aryb9Qoz967v4-rF3xTavVHrJoyJAqShH6gACgYKAX0SARESFQHGX2MiOdAbUPmCj4MueYyh-2km5RoVAUF8yKp2ehWQC6tX8n-9UNg11RV60076"
},
{
"domain": ".youtube.com",
"expirationDate": 1802692356.635559,
"hostOnly": False,
"httpOnly": False,
"name": "__Secure-3PAPISID",
"path": "/",
"sameSite": "no_restriction",
"secure": True,
"session": False,
"storeId": None,
"value": "DP6iRyLCM_cFV1Gw/AN2nemkVrvJ2p8MWb"
},
{
"domain": ".youtube.com",
"expirationDate": 1800281710.071036,
"hostOnly": False,
"httpOnly": True,
"name": "__Secure-3PSIDCC",
"path": "/",
"sameSite": "no_restriction",
"secure": True,
"session": False,
"storeId": None,
"value": "AKEyXzUv06PBPrBxCnsrFCJPVRWYCKjXadcrSQPokD-DHGumtiOBRC96ipf2COBQcX_7RjiO8g"
},
{
"domain": ".youtube.com",
"expirationDate": 1800281710.070914,
"hostOnly": False,
"httpOnly": True,
"name": "__Secure-3PSIDTS",
"path": "/",
"sameSite": "no_restriction",
"secure": True,
"session": False,
"storeId": None,
"value": "sidts-CjQB7I_69DRJdiQQGddE6tt-GHilv2IjDZd8S6FlWCjx2iReOoNtQMUkb55vaBdl8vBK7J_DEAA"
},
{
"domain": ".youtube.com",
"expirationDate": 1792154873.499957,
"hostOnly": False,
"httpOnly": True,
"name": "LOGIN_INFO",
"path": "/",
"sameSite": "no_restriction",
"secure": True,
"session": False,
"storeId": None,
"value": "AFmmF2swRQIgVjJk8Mho4_JuKr6SZzrhBdlL1LdxWxcwDMu4cjaRRgcCIQCTtJpmYKJH54Tiei3at3f4YT3US7gSL0lW_TZ04guKjQ:QUQ3MjNmeWlwRDJSNDl2NE9uX2JWWG5tWllHN0RsNUVZVUhsLVp4N2dWbldaeC14SnNybWVERnNoaXFpanFJczhKTjJSRGN6MEs3c1VkLTE1TGJVeFBPT05BY29NMFh0Q1VPdFU3dUdvSUpET3lQbU1ZMUlHUGltajlXNDllNUQxZHdzZko1WXF1UUJWclNxQVJ0TXVEYnF2bXJRY2V6Vl9n"
},
{
"domain": ".youtube.com",
"expirationDate": 1803304605.839449,
"hostOnly": False,
"httpOnly": False,
"name": "PREF",
"path": "/",
"sameSite": None,
"secure": True,
"session": False,
"storeId": None,
"value": "tz=Etc.GMT-7&f7=150"
}
]
def json_to_netscape(json_cookies, output_file):
with open(output_file, 'w') as f:
f.write("# Netscape HTTP Cookie File\n")
f.write("# This file is generated by a script.\n\n")
for cookie in json_cookies:
domain = cookie.get('domain', '')
# Netscape format requires domain to start with . for subdomains usually,
# flag TRUE/FALSE depends on if it's a domain cookie.
# Simplified:
flag = "TRUE" if domain.startswith('.') else "FALSE"
path = cookie.get('path', '/')
secure = "TRUE" if cookie.get('secure', False) else "FALSE"
expiration = str(int(cookie.get('expirationDate', 0)))
name = cookie.get('name', '')
value = cookie.get('value', '')
f.write(f"{domain}\t{flag}\t{path}\t{secure}\t{expiration}\t{name}\t{value}\n")
print(f"Successfully converted {len(json_cookies)} cookies to {output_file}")
if __name__ == "__main__":
json_to_netscape(cookies_data, 'cookies.txt')

Binary file not shown.

Binary file not shown.

View file

@ -1,20 +0,0 @@
import requests
import time
print("Waiting for server to be ready...")
for i in range(10):
try:
requests.get("http://127.0.0.1:5002/health") # Assuming health check or just root
break
except:
time.sleep(2)
print("Invoking Summarize API...")
try:
# Use a longer timeout for the genai processing
r = requests.get("http://127.0.0.1:5002/api/summarize?v=qZvqydUEzqA&title=Disturbed%20-%20The%20Sound%20Of%20Silence&lang=vi", timeout=60)
print(f"Status Code: {r.status_code}")
print("Response Body Snippet:")
print(r.text[:500])
except Exception as e:
print(f"Request Failed: {e}")