mirror of
https://github.com/Arrowar/StreamingCommunity.git
synced 2025-06-06 11:35:29 +00:00
Merge branch 'Arrowar:main' into enable-custom-config
This commit is contained in:
commit
c94e693545
634
.github/.domain/domain_update.py
vendored
634
.github/.domain/domain_update.py
vendored
@ -1,358 +1,360 @@
|
|||||||
import re
|
# 20.04.2024
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import json
|
import json
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from urllib.parse import urlparse, urlunparse
|
from urllib.parse import urlparse, unquote
|
||||||
|
|
||||||
|
|
||||||
|
# External libraries
|
||||||
import httpx
|
import httpx
|
||||||
|
import tldextract
|
||||||
import ua_generator
|
import ua_generator
|
||||||
|
import dns.resolver
|
||||||
JSON_FILE_PATH = os.path.join(".github", ".domain", "domains.json")
|
|
||||||
|
|
||||||
|
|
||||||
def load_domains(file_path):
|
# Variables
|
||||||
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
JSON_FILE_PATH = os.path.join(SCRIPT_DIR, "domains.json")
|
||||||
|
ua = ua_generator.generate(device='desktop', browser=('chrome', 'edge'))
|
||||||
|
|
||||||
|
|
||||||
|
def get_headers():
|
||||||
|
return ua.headers.get()
|
||||||
|
|
||||||
|
def get_tld(url_str):
|
||||||
|
try:
|
||||||
|
parsed = urlparse(unquote(url_str))
|
||||||
|
domain = parsed.netloc.lower().lstrip('www.')
|
||||||
|
parts = domain.split('.')
|
||||||
|
return parts[-1] if len(parts) >= 2 else None
|
||||||
|
|
||||||
|
except Exception:
|
||||||
|
return None
|
||||||
|
|
||||||
|
def get_base_domain(url_str):
|
||||||
|
try:
|
||||||
|
parsed = urlparse(url_str)
|
||||||
|
domain = parsed.netloc.lower().lstrip('www.')
|
||||||
|
parts = domain.split('.')
|
||||||
|
return '.'.join(parts[:-1]) if len(parts) > 2 else parts[0]
|
||||||
|
|
||||||
|
except Exception:
|
||||||
|
return None
|
||||||
|
|
||||||
|
def get_base_url(url_str):
|
||||||
|
try:
|
||||||
|
parsed = urlparse(url_str)
|
||||||
|
return f"{parsed.scheme}://{parsed.netloc}"
|
||||||
|
|
||||||
|
except Exception:
|
||||||
|
return None
|
||||||
|
|
||||||
|
def log(msg, level='INFO'):
|
||||||
|
levels = {
|
||||||
|
'INFO': '[ ]',
|
||||||
|
'SUCCESS': '[+]',
|
||||||
|
'WARNING': '[!]',
|
||||||
|
'ERROR': '[-]'
|
||||||
|
}
|
||||||
|
entry = f"{levels.get(level, '[?]')} {msg}"
|
||||||
|
print(entry)
|
||||||
|
|
||||||
|
def load_json_data(file_path):
|
||||||
if not os.path.exists(file_path):
|
if not os.path.exists(file_path):
|
||||||
print(f"Error: The file {file_path} was not found.")
|
log(f"Error: The file {file_path} was not found.", "ERROR")
|
||||||
return None
|
return None
|
||||||
|
|
||||||
try:
|
try:
|
||||||
with open(file_path, 'r', encoding='utf-8') as f:
|
with open(file_path, 'r', encoding='utf-8') as f:
|
||||||
return json.load(f)
|
return json.load(f)
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
print(f"Error reading the file {file_path}: {e}")
|
log(f"Error reading the file {file_path}: {e}", "ERROR")
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def save_domains(file_path, data):
|
def save_json_data(file_path, data):
|
||||||
try:
|
try:
|
||||||
with open(file_path, 'w', encoding='utf-8') as f:
|
with open(file_path, 'w', encoding='utf-8') as f:
|
||||||
json.dump(data, f, indent=2, ensure_ascii=False)
|
json.dump(data, f, indent=2, ensure_ascii=False)
|
||||||
print(f"Data successfully saved to {file_path}")
|
log(f"Data successfully saved to {file_path}", "SUCCESS")
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
print(f"Error saving the file {file_path}: {e}")
|
log(f"Error saving the file {file_path}: {e}", "ERROR")
|
||||||
|
|
||||||
|
def parse_url(url):
|
||||||
|
if not url.startswith(('http://', 'https://')):
|
||||||
|
url = 'https://' + url
|
||||||
|
|
||||||
def get_new_tld(full_url):
|
|
||||||
try:
|
try:
|
||||||
parsed_url = urlparse(full_url)
|
extracted = tldextract.extract(url)
|
||||||
hostname = parsed_url.hostname
|
parsed = urlparse(url)
|
||||||
if hostname:
|
clean_url = f"{parsed.scheme}://{parsed.netloc}/"
|
||||||
parts = hostname.split('.')
|
full_domain = f"{extracted.domain}.{extracted.suffix}" if extracted.domain else extracted.suffix
|
||||||
return parts[-1]
|
domain_tld = extracted.suffix
|
||||||
|
result = {
|
||||||
except Exception:
|
'url': clean_url,
|
||||||
pass
|
'full_domain': full_domain,
|
||||||
|
'domain': domain_tld,
|
||||||
return None
|
'suffix': extracted.suffix,
|
||||||
|
'subdomain': extracted.subdomain or None
|
||||||
def get_enhanced_headers():
|
}
|
||||||
ua = ua_generator.generate(device='desktop', browser='chrome')
|
return result
|
||||||
headers = ua.headers.get()
|
|
||||||
|
|
||||||
additional_headers = {
|
except Exception as e:
|
||||||
'DNT': '1',
|
log(f"Error parsing URL: {e}", "ERROR")
|
||||||
'Upgrade-Insecure-Requests': '1',
|
return None
|
||||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
|
|
||||||
'Accept-Language': 'en-US,en;q=0.9,it;q=0.8',
|
def check_dns_resolution(domain):
|
||||||
'Accept-Encoding': 'gzip, deflate, br',
|
try:
|
||||||
'Cache-Control': 'max-age=0',
|
resolver = dns.resolver.Resolver()
|
||||||
'Connection': 'keep-alive',
|
resolver.timeout = 2
|
||||||
'Referer': 'https://www.google.com/',
|
resolver.lifetime = 2
|
||||||
|
|
||||||
|
try:
|
||||||
|
answers = resolver.resolve(domain, 'A')
|
||||||
|
return str(answers[0])
|
||||||
|
except:
|
||||||
|
try:
|
||||||
|
answers = resolver.resolve(domain, 'AAAA')
|
||||||
|
return str(answers[0])
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
return None
|
||||||
|
except:
|
||||||
|
return None
|
||||||
|
|
||||||
|
def find_new_domain(input_url, output_file=None, verbose=True, json_output=False):
|
||||||
|
log_buffer = []
|
||||||
|
original_info = parse_url(input_url)
|
||||||
|
|
||||||
|
if not original_info:
|
||||||
|
log(f"Could not parse original URL: {input_url}", "ERROR")
|
||||||
|
if json_output:
|
||||||
|
return {'full_url': input_url, 'domain': None}
|
||||||
|
return None
|
||||||
|
|
||||||
|
log(f"Starting analysis for: {original_info['full_domain']}")
|
||||||
|
orig_ip = check_dns_resolution(original_info['full_domain'])
|
||||||
|
if orig_ip:
|
||||||
|
log(f"Original domain resolves to: {orig_ip}", "SUCCESS")
|
||||||
|
else:
|
||||||
|
log(f"Original domain does not resolve to an IP address", "WARNING")
|
||||||
|
|
||||||
|
headers = get_headers()
|
||||||
|
new_domains = []
|
||||||
|
redirects = []
|
||||||
|
final_url = None
|
||||||
|
final_domain_info = None
|
||||||
|
url_to_test_in_loop = None
|
||||||
|
|
||||||
|
for protocol in ['https://', 'http://']:
|
||||||
|
try:
|
||||||
|
url_to_test_in_loop = f"{protocol}{original_info['full_domain']}"
|
||||||
|
log(f"Testing connectivity to {url_to_test_in_loop}")
|
||||||
|
redirect_chain = []
|
||||||
|
current_url = url_to_test_in_loop
|
||||||
|
max_redirects = 10
|
||||||
|
redirect_count = 0
|
||||||
|
|
||||||
|
while redirect_count < max_redirects:
|
||||||
|
with httpx.Client(verify=False, follow_redirects=False, timeout=5) as client:
|
||||||
|
response = client.get(current_url, headers=headers)
|
||||||
|
|
||||||
|
redirect_info = {'url': current_url, 'status_code': response.status_code}
|
||||||
|
redirect_chain.append(redirect_info)
|
||||||
|
log(f"Request to {current_url} - Status: {response.status_code}")
|
||||||
|
|
||||||
|
if response.status_code in (301, 302, 303, 307, 308):
|
||||||
|
if 'location' in response.headers:
|
||||||
|
next_url = response.headers['location']
|
||||||
|
if next_url.startswith('/'):
|
||||||
|
parsed_current = urlparse(current_url)
|
||||||
|
next_url = f"{parsed_current.scheme}://{parsed_current.netloc}{next_url}"
|
||||||
|
|
||||||
|
log(f"Redirect found: {next_url} (Status: {response.status_code})")
|
||||||
|
current_url = next_url
|
||||||
|
redirect_count += 1
|
||||||
|
redirect_domain_info_val = parse_url(next_url)
|
||||||
|
if redirect_domain_info_val and redirect_domain_info_val['full_domain'] != original_info['full_domain']:
|
||||||
|
new_domains.append({'domain': redirect_domain_info_val['full_domain'], 'url': next_url, 'source': 'redirect'})
|
||||||
|
|
||||||
|
else:
|
||||||
|
log(f"Redirect status code but no Location header", "WARNING")
|
||||||
|
break
|
||||||
|
else:
|
||||||
|
break
|
||||||
|
|
||||||
|
if redirect_chain:
|
||||||
|
final_url = redirect_chain[-1]['url']
|
||||||
|
final_domain_info = parse_url(final_url)
|
||||||
|
redirects.extend(redirect_chain)
|
||||||
|
log(f"Final URL after redirects: {final_url}", "SUCCESS")
|
||||||
|
if final_domain_info and final_domain_info['full_domain'] != original_info['full_domain']:
|
||||||
|
new_domains.append({'domain': final_domain_info['full_domain'], 'url': final_url, 'source': 'final_url'})
|
||||||
|
|
||||||
|
final_status = redirect_chain[-1]['status_code'] if redirect_chain else None
|
||||||
|
|
||||||
|
if final_status and final_status < 400 and final_status != 403:
|
||||||
|
break
|
||||||
|
|
||||||
|
if final_status == 403 and redirect_chain and len(redirect_chain) > 1:
|
||||||
|
log(f"Got 403 Forbidden, but captured {len(redirect_chain)-1} redirects before that", "SUCCESS")
|
||||||
|
break
|
||||||
|
|
||||||
|
except httpx.RequestError as e:
|
||||||
|
log(f"Error connecting to {protocol}{original_info['full_domain']}: {str(e)}", "ERROR")
|
||||||
|
|
||||||
|
url_for_auto_redirect = input_url
|
||||||
|
if url_to_test_in_loop:
|
||||||
|
url_for_auto_redirect = url_to_test_in_loop
|
||||||
|
elif original_info and original_info.get('url'):
|
||||||
|
url_for_auto_redirect = original_info['url']
|
||||||
|
|
||||||
|
if not redirects or not new_domains:
|
||||||
|
log("Trying alternate method with automatic redirect following")
|
||||||
|
|
||||||
|
try:
|
||||||
|
with httpx.Client(verify=False, follow_redirects=True, timeout=5) as client:
|
||||||
|
response_auto = client.get(url_for_auto_redirect, headers=headers)
|
||||||
|
|
||||||
|
log(f"Connected with auto-redirects: Status {response_auto.status_code}")
|
||||||
|
|
||||||
|
if response_auto.history:
|
||||||
|
log(f"Found {len(response_auto.history)} redirects with auto-following", "SUCCESS")
|
||||||
|
|
||||||
|
for r_hist in response_auto.history:
|
||||||
|
redirect_info_auto = {'url': str(r_hist.url), 'status_code': r_hist.status_code}
|
||||||
|
redirects.append(redirect_info_auto)
|
||||||
|
log(f"Auto-redirect: {r_hist.url} (Status: {r_hist.status_code})")
|
||||||
|
|
||||||
|
final_url = str(response_auto.url)
|
||||||
|
final_domain_info = parse_url(final_url)
|
||||||
|
for redirect_hist_item in response_auto.history:
|
||||||
|
redirect_domain_val = parse_url(str(redirect_hist_item.url))
|
||||||
|
if redirect_domain_val and original_info and redirect_domain_val['full_domain'] != original_info['full_domain']:
|
||||||
|
new_domains.append({'domain': redirect_domain_val['full_domain'], 'url': str(redirect_hist_item.url), 'source': 'auto-redirect'})
|
||||||
|
|
||||||
|
current_final_url_info = parse_url(str(response_auto.url))
|
||||||
|
|
||||||
|
if current_final_url_info and original_info and current_final_url_info['full_domain'] != original_info['full_domain']:
|
||||||
|
is_already_added = any(d['domain'] == current_final_url_info['full_domain'] and d['source'] == 'auto-redirect' for d in new_domains)
|
||||||
|
if not is_already_added:
|
||||||
|
new_domains.append({'domain': current_final_url_info['full_domain'], 'url': str(response_auto.url), 'source': 'final_url_auto'})
|
||||||
|
final_url = str(response_auto.url)
|
||||||
|
final_domain_info = current_final_url_info
|
||||||
|
log(f"Final URL from auto-redirect: {final_url}", "SUCCESS")
|
||||||
|
|
||||||
|
except httpx.RequestError as e:
|
||||||
|
log(f"Error with auto-redirect attempt: {str(e)}", "ERROR")
|
||||||
|
except NameError:
|
||||||
|
log(f"Error: URL for auto-redirect attempt was not defined.", "ERROR")
|
||||||
|
|
||||||
|
unique_domains = []
|
||||||
|
seen_domains = set()
|
||||||
|
for domain_info_item in new_domains:
|
||||||
|
if domain_info_item['domain'] not in seen_domains:
|
||||||
|
seen_domains.add(domain_info_item['domain'])
|
||||||
|
unique_domains.append(domain_info_item)
|
||||||
|
|
||||||
|
if not final_url:
|
||||||
|
final_url = input_url
|
||||||
|
if not final_domain_info:
|
||||||
|
final_domain_info = original_info
|
||||||
|
|
||||||
|
if final_domain_info:
|
||||||
|
parsed_final_url_info = parse_url(final_url)
|
||||||
|
if parsed_final_url_info:
|
||||||
|
final_url = parsed_final_url_info['url']
|
||||||
|
final_domain_info = parsed_final_url_info
|
||||||
|
else:
|
||||||
|
final_domain_info = original_info
|
||||||
|
final_url = original_info['url'] if original_info else input_url
|
||||||
|
|
||||||
|
results_original_domain = original_info['full_domain'] if original_info else None
|
||||||
|
results_final_domain_tld = final_domain_info['domain'] if final_domain_info and 'domain' in final_domain_info else None
|
||||||
|
|
||||||
|
results = {
|
||||||
|
'timestamp': datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||||
|
'original_url': input_url,
|
||||||
|
'original_domain': results_original_domain,
|
||||||
|
'original_ip': orig_ip,
|
||||||
|
'new_domains': unique_domains,
|
||||||
|
'redirects': redirects,
|
||||||
|
'log': log_buffer
|
||||||
}
|
}
|
||||||
|
simplified_json_output = {'full_url': final_url, 'domain': results_final_domain_tld}
|
||||||
|
|
||||||
headers.update(additional_headers)
|
if verbose:
|
||||||
return headers
|
log(f"DEBUG - Simplified output: {simplified_json_output}", "INFO")
|
||||||
|
|
||||||
|
if output_file:
|
||||||
|
try:
|
||||||
|
with open(output_file, 'w', encoding='utf-8') as f:
|
||||||
|
json.dump(results, f, indent=2, ensure_ascii=False)
|
||||||
|
log(f"Results saved to {output_file}", "SUCCESS")
|
||||||
|
except Exception as e:
|
||||||
|
log(f"Error writing to output file: {str(e)}", "ERROR")
|
||||||
|
|
||||||
|
if json_output:
|
||||||
|
return simplified_json_output
|
||||||
|
else:
|
||||||
|
return results
|
||||||
|
|
||||||
def extract_redirect_from_403(response, original_url):
|
def update_site_entry(site_name: str, all_domains_data: dict):
|
||||||
redirect_headers = ['location', 'refresh', 'x-redirect-to', 'x-location', 'redirect']
|
site_config = all_domains_data.get(site_name, {})
|
||||||
for header in redirect_headers:
|
log(f"Processing site: {site_name}", "INFO")
|
||||||
if header in response.headers:
|
if not site_config.get('full_url'):
|
||||||
return response.headers[header]
|
log(f"Site {site_name} has no full_url in config. Skipping.", "WARNING")
|
||||||
|
|
||||||
try:
|
|
||||||
content = response.text
|
|
||||||
|
|
||||||
js_patterns = [
|
|
||||||
r'window\.location\.href\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'window\.location\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'location\.href\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'document\.location\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'top\.location\.href\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'parent\.location\s*=\s*["\']([^"\']+)["\']'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in js_patterns:
|
|
||||||
match = re.search(pattern, content, re.IGNORECASE)
|
|
||||||
if match:
|
|
||||||
return match.group(1)
|
|
||||||
|
|
||||||
meta_patterns = [
|
|
||||||
r'<meta[^>]*http-equiv=["\']?refresh["\']?[^>]*content=["\'][^"\']*url=([^"\'>\s]+)',
|
|
||||||
r'<meta[^>]*content=["\'][^"\']*url=([^"\'>\s]+)[^>]*http-equiv=["\']?refresh["\']?'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in meta_patterns:
|
|
||||||
match = re.search(pattern, content, re.IGNORECASE)
|
|
||||||
if match:
|
|
||||||
return match.group(1)
|
|
||||||
|
|
||||||
text_patterns = [
|
|
||||||
r'[Rr]edirect(?:ed)?\s+to:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Nn]ew\s+[Uu][Rr][Ll]:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Mm]oved\s+to:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Ff]ound\s+at:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Gg]o\s+to:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Vv]isit:?\s*([^\s<>"\']+)',
|
|
||||||
r'https?://[^\s<>"\']+\.[a-z]{2,}[^\s<>"\']*'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in text_patterns:
|
|
||||||
match = re.search(pattern, content)
|
|
||||||
if match:
|
|
||||||
potential_url = match.group(1) if '(' in pattern else match.group(0)
|
|
||||||
if potential_url.startswith(('http://', 'https://', '//')):
|
|
||||||
return potential_url
|
|
||||||
|
|
||||||
link_patterns = [
|
|
||||||
r'<a[^>]*href=["\']([^"\']+)["\'][^>]*>(?:click here|continue|proceed|go here)',
|
|
||||||
r'<link[^>]*rel=["\']?canonical["\']?[^>]*href=["\']([^"\']+)["\']',
|
|
||||||
r'<base[^>]*href=["\']([^"\']+)["\']'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in link_patterns:
|
|
||||||
match = re.search(pattern, content, re.IGNORECASE)
|
|
||||||
if match:
|
|
||||||
return match.group(1)
|
|
||||||
|
|
||||||
except Exception:
|
|
||||||
pass
|
|
||||||
|
|
||||||
return None
|
|
||||||
|
|
||||||
def extract_domain_from_response(response, original_url):
|
|
||||||
if 'location' in response.headers:
|
|
||||||
return response.headers['location']
|
|
||||||
|
|
||||||
if str(response.url) != original_url:
|
|
||||||
return str(response.url)
|
|
||||||
|
|
||||||
try:
|
|
||||||
content_type = response.headers.get('content-type', '').lower()
|
|
||||||
if 'text/html' in content_type or 'text/plain' in content_type:
|
|
||||||
response_text = response.text
|
|
||||||
|
|
||||||
js_redirect_patterns = [
|
|
||||||
r'window\.location\.href\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'window\.location\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'location\.href\s*=\s*["\']([^"\']+)["\']',
|
|
||||||
r'document\.location\s*=\s*["\']([^"\']+)["\']'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in js_redirect_patterns:
|
|
||||||
js_match = re.search(pattern, response_text, re.IGNORECASE)
|
|
||||||
if js_match:
|
|
||||||
return js_match.group(1)
|
|
||||||
|
|
||||||
meta_patterns = [
|
|
||||||
r'<meta[^>]*http-equiv=["\']?refresh["\']?[^>]*content=["\'][^"\']*url=([^"\'>\s]+)',
|
|
||||||
r'<meta[^>]*content=["\'][^"\']*url=([^"\'>\s]+)[^>]*http-equiv=["\']?refresh["\']?'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in meta_patterns:
|
|
||||||
meta_match = re.search(pattern, response_text, re.IGNORECASE)
|
|
||||||
if meta_match:
|
|
||||||
return meta_match.group(1)
|
|
||||||
|
|
||||||
canonical_match = re.search(r'<link[^>]*rel=["\']?canonical["\']?[^>]*href=["\']([^"\']+)["\']', response_text, re.IGNORECASE)
|
|
||||||
if canonical_match:
|
|
||||||
return canonical_match.group(1)
|
|
||||||
|
|
||||||
base_match = re.search(r'<base[^>]*href=["\']([^"\']+)["\']', response_text, re.IGNORECASE)
|
|
||||||
if base_match:
|
|
||||||
return base_match.group(1)
|
|
||||||
|
|
||||||
error_redirect_patterns = [
|
|
||||||
r'[Rr]edirect(?:ed)?\s+to:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Nn]ew\s+[Uu][Rr][Ll]:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Mm]oved\s+to:?\s*([^\s<>"\']+)',
|
|
||||||
r'[Ff]ound\s+at:?\s*([^\s<>"\']+)'
|
|
||||||
]
|
|
||||||
|
|
||||||
for pattern in error_redirect_patterns:
|
|
||||||
error_match = re.search(pattern, response_text)
|
|
||||||
if error_match:
|
|
||||||
potential_url = error_match.group(1)
|
|
||||||
if potential_url.startswith(('http://', 'https://', '//')):
|
|
||||||
return potential_url
|
|
||||||
|
|
||||||
except Exception as e:
|
|
||||||
print(f" [!] Error extracting from response content: {e}")
|
|
||||||
|
|
||||||
return None
|
|
||||||
|
|
||||||
def try_url(url_to_try, headers=None, timeout=15):
|
|
||||||
if headers is None:
|
|
||||||
headers = get_enhanced_headers()
|
|
||||||
|
|
||||||
try:
|
|
||||||
with httpx.Client(headers=headers, timeout=timeout, follow_redirects=False) as client:
|
|
||||||
response = client.get(url_to_try)
|
|
||||||
|
|
||||||
if response.status_code in [301, 302, 303, 307, 308]:
|
|
||||||
location = response.headers.get('location')
|
|
||||||
if location:
|
|
||||||
print(f" [+] Found redirect ({response.status_code}) to: {location}")
|
|
||||||
try:
|
|
||||||
final_response = client.get(location)
|
|
||||||
if 200 <= final_response.status_code < 400:
|
|
||||||
return final_response
|
|
||||||
else:
|
|
||||||
return httpx.Response(
|
|
||||||
status_code=200,
|
|
||||||
headers={"location": location},
|
|
||||||
content=b"",
|
|
||||||
request=response.request
|
|
||||||
)
|
|
||||||
except Exception:
|
|
||||||
return httpx.Response(
|
|
||||||
status_code=200,
|
|
||||||
headers={"location": location},
|
|
||||||
content=b"",
|
|
||||||
request=response.request
|
|
||||||
)
|
|
||||||
|
|
||||||
elif response.status_code == 403:
|
|
||||||
print(f" [!] HTTP 403 - attempting enhanced extraction")
|
|
||||||
|
|
||||||
redirect_url = extract_redirect_from_403(response, url_to_try)
|
|
||||||
if redirect_url:
|
|
||||||
print(f" [+] Found redirect URL in 403 response: {redirect_url}")
|
|
||||||
return httpx.Response(
|
|
||||||
status_code=200,
|
|
||||||
headers={"location": redirect_url},
|
|
||||||
content=b"",
|
|
||||||
request=response.request
|
|
||||||
)
|
|
||||||
|
|
||||||
elif response.status_code in [409, 429, 503]:
|
|
||||||
print(f" [!] HTTP {response.status_code} - attempting to extract redirect info")
|
|
||||||
|
|
||||||
location = response.headers.get('location')
|
|
||||||
if location:
|
|
||||||
print(f" [+] Found location header in error response: {location}")
|
|
||||||
return httpx.Response(
|
|
||||||
status_code=200,
|
|
||||||
headers={"location": location},
|
|
||||||
content=b"",
|
|
||||||
request=response.request
|
|
||||||
)
|
|
||||||
|
|
||||||
new_url = extract_domain_from_response(response, url_to_try)
|
|
||||||
if new_url and new_url != url_to_try:
|
|
||||||
print(f" [+] Found redirect URL in error response content: {new_url}")
|
|
||||||
return httpx.Response(
|
|
||||||
status_code=200,
|
|
||||||
headers={"location": new_url},
|
|
||||||
content=b"",
|
|
||||||
request=response.request
|
|
||||||
)
|
|
||||||
|
|
||||||
if 200 <= response.status_code < 400:
|
|
||||||
return response
|
|
||||||
|
|
||||||
print(f" [!] HTTP {response.status_code} for {url_to_try}")
|
|
||||||
|
|
||||||
except httpx.HTTPStatusError as http_err:
|
|
||||||
new_url = extract_domain_from_response(http_err.response, url_to_try)
|
|
||||||
if new_url:
|
|
||||||
print(f" [+] Found new URL from HTTPStatusError response: {new_url}")
|
|
||||||
return httpx.Response(
|
|
||||||
status_code=200,
|
|
||||||
headers={"location": new_url},
|
|
||||||
content=b"",
|
|
||||||
request=http_err.request
|
|
||||||
)
|
|
||||||
except Exception as e:
|
|
||||||
print(f" [!] Error for {url_to_try}: {type(e).__name__}")
|
|
||||||
|
|
||||||
return None
|
|
||||||
|
|
||||||
def update_domain_entries(data):
|
|
||||||
if not data:
|
|
||||||
return False
|
return False
|
||||||
|
|
||||||
updated_count = 0
|
current_full_url = site_config.get('full_url')
|
||||||
|
current_domain_tld = site_config.get('domain')
|
||||||
|
found_domain_info = find_new_domain(current_full_url, verbose=False, json_output=True)
|
||||||
|
|
||||||
for key, entry in data.items():
|
if found_domain_info and found_domain_info.get('full_url') and found_domain_info.get('domain'):
|
||||||
print(f"\n--- [DOMAIN] {key} ---")
|
new_full_url = found_domain_info['full_url']
|
||||||
original_full_url = entry.get("full_url")
|
new_domain_tld = found_domain_info['domain']
|
||||||
original_domain_in_entry = entry.get("domain")
|
|
||||||
|
|
||||||
if not original_full_url:
|
if new_full_url != current_full_url or new_domain_tld != current_domain_tld:
|
||||||
print(f" [!] 'full_url' missing. Skipped.")
|
log(f"Update found for {site_name}: URL '{current_full_url}' -> '{new_full_url}', TLD '{current_domain_tld}' -> '{new_domain_tld}'", "SUCCESS")
|
||||||
continue
|
updated_entry = site_config.copy()
|
||||||
|
updated_entry['full_url'] = new_full_url
|
||||||
|
updated_entry['domain'] = new_domain_tld
|
||||||
|
if new_domain_tld != current_domain_tld :
|
||||||
|
updated_entry['old_domain'] = current_domain_tld if current_domain_tld else ""
|
||||||
|
|
||||||
print(f" [] Stored URL: {original_full_url}")
|
updated_entry['time_change'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
if original_domain_in_entry:
|
all_domains_data[site_name] = updated_entry
|
||||||
print(f" [] Stored Domain (TLD): {original_domain_in_entry}")
|
return True
|
||||||
|
|
||||||
print(f" [] Testing URL: {original_full_url}")
|
|
||||||
response = try_url(original_full_url)
|
|
||||||
|
|
||||||
if response:
|
|
||||||
final_url_from_request = str(response.url)
|
|
||||||
print(f" [+] Redirect/Response to: {final_url_from_request}")
|
|
||||||
|
|
||||||
parsed_final_url = urlparse(final_url_from_request)
|
|
||||||
normalized_full_url = urlunparse(parsed_final_url._replace(path='/', params='', query='', fragment=''))
|
|
||||||
if parsed_final_url.path == '' and not normalized_full_url.endswith('/'):
|
|
||||||
normalized_full_url += '/'
|
|
||||||
|
|
||||||
if normalized_full_url != final_url_from_request:
|
|
||||||
print(f" [+] Normalized URL: {normalized_full_url}")
|
|
||||||
|
|
||||||
if normalized_full_url != original_full_url:
|
|
||||||
new_tld_val = get_new_tld(final_url_from_request)
|
|
||||||
|
|
||||||
if new_tld_val:
|
|
||||||
entry["full_url"] = normalized_full_url
|
|
||||||
|
|
||||||
if new_tld_val != original_domain_in_entry:
|
|
||||||
print(f" [-] Domain TLD Changed: '{original_domain_in_entry}' -> '{new_tld_val}'")
|
|
||||||
entry["old_domain"] = original_domain_in_entry if original_domain_in_entry else entry.get("old_domain", "")
|
|
||||||
entry["domain"] = new_tld_val
|
|
||||||
entry["time_change"] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
|
|
||||||
print(f" [-] Domain & URL Updated: New TLD '{new_tld_val}', New URL '{normalized_full_url}'")
|
|
||||||
else:
|
|
||||||
entry["domain"] = new_tld_val
|
|
||||||
print(f" [-] URL Updated (TLD Unchanged '{new_tld_val}'): New URL '{normalized_full_url}'")
|
|
||||||
|
|
||||||
updated_count += 1
|
|
||||||
|
|
||||||
else:
|
|
||||||
print(f" [!] Could not extract TLD from {final_url_from_request}. URL not updated despite potential change.")
|
|
||||||
else:
|
|
||||||
print(f" [] Same Domain: {final_url_from_request}")
|
|
||||||
|
|
||||||
else:
|
else:
|
||||||
print(f" [-] No response for {key}")
|
log(f"No changes detected for {site_name}.", "INFO")
|
||||||
|
return False
|
||||||
return updated_count > 0
|
else:
|
||||||
|
log(f"Could not reliably find new domain info for {site_name} from URL: {current_full_url}. No search fallback.", "WARNING")
|
||||||
|
return False
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
print("Starting domain update script...")
|
log("Starting domain update script...")
|
||||||
domain_data = load_domains(JSON_FILE_PATH)
|
all_domains_data = load_json_data(JSON_FILE_PATH)
|
||||||
|
if not all_domains_data:
|
||||||
|
log("Cannot proceed: Domain data is missing or could not be loaded.", "ERROR")
|
||||||
|
log("Script finished.")
|
||||||
|
return
|
||||||
|
|
||||||
if domain_data:
|
any_updates_made = False
|
||||||
if update_domain_entries(domain_data):
|
for site_name_key in list(all_domains_data.keys()):
|
||||||
save_domains(JSON_FILE_PATH, domain_data)
|
if update_site_entry(site_name_key, all_domains_data):
|
||||||
print("\nUpdate complete. Some entries were modified.")
|
any_updates_made = True
|
||||||
else:
|
print("\n")
|
||||||
print("\nUpdate complete. No domains were modified.")
|
|
||||||
else:
|
|
||||||
print("\nCannot proceed without domain data.")
|
|
||||||
|
|
||||||
print("Script finished.")
|
if any_updates_made:
|
||||||
|
save_json_data(JSON_FILE_PATH, all_domains_data)
|
||||||
|
log("Update complete. Some entries were modified.", "SUCCESS")
|
||||||
|
else:
|
||||||
|
log("Update complete. No domains were modified.", "INFO")
|
||||||
|
log("Script finished.")
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
8
.github/.domain/domains.json
vendored
8
.github/.domain/domains.json
vendored
@ -54,9 +54,9 @@
|
|||||||
"time_change": "2025-05-31 12:17:33"
|
"time_change": "2025-05-31 12:17:33"
|
||||||
},
|
},
|
||||||
"altadefinizionegratis": {
|
"altadefinizionegratis": {
|
||||||
"domain": "icu",
|
"domain": "cc",
|
||||||
"full_url": "https://altadefinizionegratis.icu/",
|
"full_url": "https://altadefinizionegratis.cc/",
|
||||||
"old_domain": "taipei",
|
"old_domain": "icu",
|
||||||
"time_change": "2025-05-18 11:21:05"
|
"time_change": "2025-06-02 10:35:25"
|
||||||
}
|
}
|
||||||
}
|
}
|
@ -4,6 +4,7 @@ import os
|
|||||||
import sys
|
import sys
|
||||||
import time
|
import time
|
||||||
import asyncio
|
import asyncio
|
||||||
|
import importlib.metadata
|
||||||
|
|
||||||
# External library
|
# External library
|
||||||
import httpx
|
import httpx
|
||||||
@ -11,7 +12,7 @@ from rich.console import Console
|
|||||||
|
|
||||||
|
|
||||||
# Internal utilities
|
# Internal utilities
|
||||||
from .version import __version__, __author__, __title__
|
from .version import __version__ as source_code_version, __author__, __title__
|
||||||
from StreamingCommunity.Util.config_json import config_manager
|
from StreamingCommunity.Util.config_json import config_manager
|
||||||
from StreamingCommunity.Util.headers import get_userAgent
|
from StreamingCommunity.Util.headers import get_userAgent
|
||||||
|
|
||||||
@ -75,7 +76,11 @@ def update():
|
|||||||
percentual_stars = 0
|
percentual_stars = 0
|
||||||
|
|
||||||
# Get the current version (installed version)
|
# Get the current version (installed version)
|
||||||
current_version = __version__
|
try:
|
||||||
|
current_version = importlib.metadata.version(__title__)
|
||||||
|
except importlib.metadata.PackageNotFoundError:
|
||||||
|
console.print(f"[yellow]Warning: Could not determine installed version for '{__title__}' via importlib.metadata. Falling back to source version.[/yellow]")
|
||||||
|
current_version = source_code_version
|
||||||
|
|
||||||
# Get commit details
|
# Get commit details
|
||||||
latest_commit = response_commits[0] if response_commits else None
|
latest_commit = response_commits[0] if response_commits else None
|
||||||
|
@ -2,4 +2,4 @@ __title__ = 'StreamingCommunity'
|
|||||||
__version__ = '3.0.9'
|
__version__ = '3.0.9'
|
||||||
__author__ = 'Arrowar'
|
__author__ = 'Arrowar'
|
||||||
__description__ = 'A command-line program to download film'
|
__description__ = 'A command-line program to download film'
|
||||||
__copyright__ = 'Copyright 2024'
|
__copyright__ = 'Copyright 2025'
|
17
setup.py
17
setup.py
@ -1,4 +1,5 @@
|
|||||||
import os
|
import os
|
||||||
|
import re
|
||||||
from setuptools import setup, find_packages
|
from setuptools import setup, find_packages
|
||||||
|
|
||||||
def read_readme():
|
def read_readme():
|
||||||
@ -8,9 +9,21 @@ def read_readme():
|
|||||||
with open(os.path.join(os.path.dirname(__file__), "requirements.txt"), "r", encoding="utf-8-sig") as f:
|
with open(os.path.join(os.path.dirname(__file__), "requirements.txt"), "r", encoding="utf-8-sig") as f:
|
||||||
required_packages = f.read().splitlines()
|
required_packages = f.read().splitlines()
|
||||||
|
|
||||||
|
def get_version():
|
||||||
|
try:
|
||||||
|
import pkg_resources
|
||||||
|
return pkg_resources.get_distribution('StreamingCommunity').version
|
||||||
|
except:
|
||||||
|
version_file_path = os.path.join(os.path.dirname(__file__), "StreamingCommunity", "Upload", "version.py")
|
||||||
|
with open(version_file_path, "r", encoding="utf-8") as f:
|
||||||
|
version_match = re.search(r"^__version__\s*=\s*['\"]([^'\"]*)['\"]", f.read(), re.M)
|
||||||
|
if version_match:
|
||||||
|
return version_match.group(1)
|
||||||
|
raise RuntimeError("Unable to find version string in StreamingCommunity/Upload/version.py.")
|
||||||
|
|
||||||
setup(
|
setup(
|
||||||
name="StreamingCommunity",
|
name="StreamingCommunity",
|
||||||
version="3.0.9",
|
version=get_version(),
|
||||||
long_description=read_readme(),
|
long_description=read_readme(),
|
||||||
long_description_content_type="text/markdown",
|
long_description_content_type="text/markdown",
|
||||||
author="Lovi-0",
|
author="Lovi-0",
|
||||||
@ -29,4 +42,4 @@ setup(
|
|||||||
"Bug Reports": "https://github.com/Lovi-0/StreamingCommunity/issues",
|
"Bug Reports": "https://github.com/Lovi-0/StreamingCommunity/issues",
|
||||||
"Source": "https://github.com/Lovi-0/StreamingCommunity",
|
"Source": "https://github.com/Lovi-0/StreamingCommunity",
|
||||||
}
|
}
|
||||||
)
|
)
|
Loading…
x
Reference in New Issue
Block a user