instance1 / hf_scrapper.py
ChandimaPrabath's picture
update
aeed8f1
raw
history blame
4.12 kB
import os
import requests
import json
import urllib.request
from requests.exceptions import RequestException
from tqdm import tqdm
from concurrent.futures import ThreadPoolExecutor, as_completed
CACHE_DIR = os.getenv("CACHE_DIR")
CACHE_JSON_PATH = os.path.join(CACHE_DIR, "cached_films.json")
MAX_WORKERS = 4 # Adjust the number of threads for concurrent downloads
def get_system_proxies():
try:
proxies = urllib.request.getproxies()
print("System proxies:", proxies)
return {
"http": proxies.get("http"),
"https": proxies.get("http")
}
except Exception as e:
print(f"Error getting system proxies: {e}")
return {}
def download_file_chunk(url, headers, proxies, start, end):
headers['Range'] = f"bytes={start}-{end}"
response = requests.get(url, headers=headers, proxies=proxies, stream=True)
response.raise_for_status()
return response.content
def download_and_cache_file(file_url, token, cache_path, proxies=None):
print(f"Downloading file from URL: {file_url} to {cache_path} with proxies: {proxies}")
headers = {'Authorization': f'Bearer {token}'}
try:
response = requests.head(file_url, headers=headers, proxies=proxies)
response.raise_for_status()
total_size = int(response.headers.get('content-length', 0))
os.makedirs(os.path.dirname(cache_path), exist_ok=True)
chunk_size = total_size // MAX_WORKERS
ranges = [(i, min(i + chunk_size, total_size) - 1) for i in range(0, total_size, chunk_size)]
with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
futures = [executor.submit(download_file_chunk, file_url, headers, proxies, start, end) for start, end in ranges]
with open(cache_path, 'wb') as f, tqdm(total=total_size, unit='B', unit_scale=True, desc=cache_path) as pbar:
for future in as_completed(futures):
chunk = future.result()
f.write(chunk)
pbar.update(len(chunk))
print(f'File cached to {cache_path} successfully.')
update_cache_json(file_url, cache_path)
return True
except RequestException as e:
print(f"Error downloading file: {e}")
except IOError as e:
print(f"Error writing file {cache_path}: {e}")
return False
def update_cache_json(file_url, cache_path):
cache_data = {}
if os.path.exists(CACHE_JSON_PATH):
with open(CACHE_JSON_PATH, 'r') as json_file:
cache_data = json.load(json_file)
film_title = os.path.basename(cache_path)
cache_data[film_title] = cache_path
with open(CACHE_JSON_PATH, 'w') as json_file:
json.dump(cache_data, json_file, indent=2)
print(f'Updated cache JSON: {CACHE_JSON_PATH} with {film_title}: {cache_path}')
def get_file_structure(repo, token, path="", proxies=None):
api_url = f"https://huggingface.co/api/models/{repo}/tree/main/{path}"
headers = {'Authorization': f'Bearer {token}'}
print(f"Fetching file structure from URL: {api_url} with proxies: {proxies}")
try:
response = requests.get(api_url, headers=headers, proxies=proxies)
response.raise_for_status()
return response.json()
except RequestException as e:
print(f"Error fetching file structure: {e}")
return []
def write_file_structure_to_json(file_structure, file_path):
try:
with open(file_path, 'w') as json_file:
json.dump(file_structure, json_file, indent=2)
print(f'File structure written to {file_path}')
except IOError as e:
print(f"Error writing file structure to JSON: {e}")
if __name__ == "__main__":
file_url = "https://huggingface.co/Unicone-Studio/jellyfin_media/resolve/main/films/Funky%20Monkey%202004/Funky%20Monkey%20(2004)%20Web-dl%201080p.mp4"
token = os.getenv("TOKEN")
cache_path = os.path.join(CACHE_DIR, "films/Funky Monkey 2004/Funky Monkey (2004) Web-dl 1080p.mp4")
proxy = get_system_proxies()
download_and_cache_file(file_url, token, cache_path, proxies=proxy)