107 lines
3.5 KiB
Python
107 lines
3.5 KiB
Python
import subprocess
|
||
import os
|
||
import json
|
||
from datetime import datetime
|
||
import concurrent.futures
|
||
import tempfile
|
||
import shutil
|
||
|
||
# Конфигурация
|
||
formats = "18,599,140,133,134,135,136,137,298,299"
|
||
cookies_file = "cookies.txt"
|
||
output_template = "video/%(id)s.f%(format_id)s.%(ext)s"
|
||
num_threads = 4
|
||
|
||
url_file = "video_urls.txt"
|
||
log_file = "download_log.txt"
|
||
metadata_file = "metadata.json"
|
||
downloaded_videos_file = "downloaded_videos.json"
|
||
failed_urls_file = "failed_urls.json"
|
||
|
||
def load_json_file(file_path):
|
||
if os.path.exists(file_path):
|
||
with open(file_path, "r") as file:
|
||
return json.load(file)
|
||
return {}
|
||
|
||
def save_json_file(file_path, data):
|
||
with open(file_path, "w") as file:
|
||
json.dump(data, file, ensure_ascii=False, indent=4)
|
||
|
||
def download_video(url):
|
||
start_time = datetime.now()
|
||
try:
|
||
with tempfile.NamedTemporaryFile(delete=False, suffix='.txt') as temp_cookies:
|
||
temp_cookies_path = temp_cookies.name
|
||
shutil.copyfile(cookies_file, temp_cookies_path)
|
||
|
||
command = [
|
||
"yt-dlp",
|
||
"-f", formats,
|
||
"--cookies", temp_cookies_path,
|
||
"--output", output_template,
|
||
"--write-info-json",
|
||
url
|
||
]
|
||
print(f"START COMMAND: {' '.join(command)}")
|
||
subprocess.run(command, check=True)
|
||
end_time = datetime.now()
|
||
log_download(url, start_time, end_time)
|
||
update_metadata(url)
|
||
mark_as_downloaded(url)
|
||
except subprocess.CalledProcessError as e:
|
||
print(f"ERROR DOWNLOAD VIDEO {url}: {e}")
|
||
if "Sign in to confirm you’re not a bot" in str(e) or "Video unavailable" in str(e):
|
||
mark_as_failed(url)
|
||
finally:
|
||
if os.path.exists(temp_cookies_path):
|
||
os.remove(temp_cookies_path)
|
||
|
||
def log_download(url, start_time, end_time):
|
||
with open(log_file, "a") as log:
|
||
log.write(f"{url} Downloaded.\nStart: {start_time}\nEnd: {end_time}\n\n")
|
||
|
||
def update_metadata(url):
|
||
video_id = url.split('=')[-1]
|
||
metadata_path = f"video/{video_id}.info.json"
|
||
if os.path.exists(metadata_path):
|
||
with open(metadata_path, "r") as meta_file:
|
||
metadata = json.load(meta_file)
|
||
|
||
all_metadata = load_json_file(metadata_file)
|
||
all_metadata[url] = metadata
|
||
save_json_file(metadata_file, all_metadata)
|
||
|
||
def mark_as_downloaded(url):
|
||
downloaded_videos = load_json_file(downloaded_videos_file)
|
||
downloaded_videos[url] = datetime.now().isoformat()
|
||
save_json_file(downloaded_videos_file, downloaded_videos)
|
||
|
||
def mark_as_failed(url):
|
||
failed_urls = load_json_file(failed_urls_file)
|
||
failed_urls[url] = datetime.now().isoformat()
|
||
save_json_file(failed_urls_file, failed_urls)
|
||
|
||
def get_remaining_urls(video_urls):
|
||
downloaded_videos = load_json_file(downloaded_videos_file)
|
||
failed_urls = load_json_file(failed_urls_file)
|
||
return [url for url in video_urls if url not in downloaded_videos and url not in failed_urls]
|
||
|
||
if not os.path.exists(url_file):
|
||
print(f"File {url_file} Missing.")
|
||
exit(1)
|
||
|
||
with open(url_file, "r") as file:
|
||
video_urls = [line.strip() for line in file if line.strip()]
|
||
|
||
os.makedirs("video", exist_ok=True)
|
||
|
||
remaining_urls = get_remaining_urls(video_urls)
|
||
|
||
with concurrent.futures.ThreadPoolExecutor(max_workers=num_threads) as executor:
|
||
futures = [executor.submit(download_video, url) for url in remaining_urls]
|
||
for future in concurrent.futures.as_completed(futures):
|
||
try:
|
||
future.result()
|
||
except Exception as e:
|
||
print(f"ERROR: {e}") |