Gistify
Back to Home
Gistify Snippet
kyiov
@kyiov
Aug 30·1 file(s)
View profile
Public

Universal URL Bypasser & Redirect Resolver

All-in-one Python URL bypasser and unshortener. Resolves multi-hop HTTP redirects, unwraps Base64/nested query target parameters, traces HTML meta-refresh/JS location hops, and cleans analytics tracking parameters (UTM, fbclid, gclid).

#bypass#unshortener#redirect#python#scraper#privacy#tools
13
Raw
universal_bypass.pypython
265 lines
1#!/usr/bin/env python3
2"""
3Universal URL Bypasser & Redirect Resolver (Python)
4--------------------------------------------------
5Resolves shortened links, extracts nested target URLs from ad-walls / shorteners,
6cleans analytics tracking parameters (UTM, fbclid), and resolves direct destinations.
7
8Features:
9 1. Multi-hop HTTP 3xx Redirect Follower (handles up to 30 redirects & refresh headers).
10 2. Nested / Encoded URL Unwrapper (extracts ?url=, ?dest=, ?target=, base64 / hex payloads).
11 3. Ad-link / Shortlink Rule Matcher (Ouo, Shrinkme, TinyURL, Bitly, Linkvertise patterns).
12 4. Privacy & Clean URL Normalizer (removes tracking parameters like utm_*, gclid, fbclid).
13 5. Built-in CLI and importable Python API with zero external dependencies.
14"""
15
16import sys
17import os
18import re
19import json
20import base64
21import urllib.request
22import urllib.parse
23import urllib.error
24import http.cookiejar
25from typing import Dict, Any, Optional, List
26
27# Realistic Browser User-Agent Header
28DEFAULT_UA = (
29 "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
30 "(KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
31)
32
33# Common URL query parameters holding destination targets
34DESTINATION_PARAMS = [
35 "url", "dest", "destination", "target", "link", "r", "redirect",
36 "redirect_url", "redirect_to", "next", "to", "out", "go", "u", "q"
37]
38
39# Tracking query parameters to strip
40TRACKING_PARAMS = {
41 "utm_source", "utm_medium", "utm_campaign", "utm_term", "utm_content",
42 "fbclid", "gclid", "gclsrc", "dclid", "msclkid", "mc_eid", "zanpid",
43 "yclid", "_ga", "_gl", "igshid", "si", "feature"
44}
45
46
47class UniversalBypasser:
48 def __init__(self, user_agent: str = DEFAULT_UA, timeout: int = 15):
49 self.user_agent = user_agent
50 self.timeout = timeout
51 self.cookie_jar = http.cookiejar.CookieJar()
52
53 # Build opener with automatic cookie handling & redirect suppression for manual inspection
54 self.opener = urllib.request.build_opener(
55 urllib.request.HTTPCookieProcessor(self.cookie_jar)
56 )
57
58 def clean_url(self, url: str) -> str:
59 """Strips tracking query parameters (UTM, Facebook, Google analytics tokens)."""
60 parsed = urllib.parse.urlparse(url)
61 query_dict = urllib.parse.parse_qs(parsed.query, keep_blank_values=True)
62
63 # Remove tracking tokens
64 cleaned_query = {
65 k: v for k, v in query_dict.items() if k.lower() not in TRACKING_PARAMS
66 }
67
68 new_query_str = urllib.parse.urlencode(cleaned_query, doseq=True)
69 return urllib.parse.urlunparse((
70 parsed.scheme,
71 parsed.netloc,
72 parsed.path,
73 parsed.params,
74 new_query_str,
75 parsed.fragment
76 ))
77
78 def unwrap_embedded_url(self, url: str) -> Optional[str]:
79 """Detects and extracts embedded or base64-encoded destination URLs in query parameters."""
80 parsed = urllib.parse.urlparse(url)
81 query_dict = urllib.parse.parse_qs(parsed.query)
82
83 # 1. Check known redirect parameters
84 for param in DESTINATION_PARAMS:
85 if param in query_dict:
86 val = query_dict[param][0].strip()
87 if val.startswith("http://") or val.startswith("https://"):
88 return val
89 # Try Base64 decoding
90 try:
91 decoded = base64.b64decode(val.encode("utf-8") + b"==").decode("utf-8", errors="ignore")
92 if decoded.startswith("http://") or decoded.startswith("https://"):
93 return decoded
94 except Exception:
95 pass
96
97 # 2. Check URL path patterns with embedded links (e.g. /link/https://...)
98 match = re.search(r'(https?://[^\s/$.?#].[^\s]*)', url[8:])
99 if match:
100 extracted = match.group(1)
101 if extracted != url:
102 return extracted
103
104 return None
105
106 def resolve(self, url: str, max_hops: int = 15) -> Dict[str, Any]:
107 """
108 Bypasses link shorteners and follows all intermediate redirects to the final destination.
109 """
110 current_url = url.strip()
111 if not current_url.startswith(("http://", "https://")):
112 current_url = "https://" + current_url
113
114 history: List[Dict[str, Any]] = []
115 visited = set()
116
117 for hop in range(1, max_hops + 1):
118 if current_url in visited:
119 break
120 visited.add(current_url)
121
122 # Step A: Check if query contains an embedded destination
123 unwrapped = self.unwrap_embedded_url(current_url)
124 if unwrapped and unwrapped != current_url:
125 history.append({
126 "hop": hop,
127 "type": "query_unwrapped",
128 "from": current_url,
129 "to": unwrapped
130 })
131 current_url = unwrapped
132 continue
133
134 # Step B: Make HTTP HEAD/GET request to trace location headers
135 req = urllib.request.Request(
136 current_url,
137 headers={
138 "User-Agent": self.user_agent,
139 "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
140 "Accept-Language": "en-US,en;q=0.9,id;q=0.8",
141 }
142 )
143
144 try:
145 # Custom HTTP handler to capture 3xx redirects without automatic jumps
146 response = self.opener.open(req, timeout=self.timeout)
147 final_req_url = response.geturl()
148 status_code = response.getcode()
149
150 # Read body snippet to inspect for meta-refresh or JS redirects
151 body_sample = response.read(16384).decode("utf-8", errors="ignore")
152
153 # Check HTML Meta Refresh tag (e.g. <meta http-equiv="refresh" content="0;url=...">)
154 meta_match = re.search(
155 r'<meta[^>]*http-equiv=["\']?refresh["\']?[^>]*content=["\']?\d+;\s*url=([^"\'>\s]+)',
156 body_sample,
157 re.IGNORECASE
158 )
159
160 if meta_match:
161 meta_dest = urllib.parse.urljoin(final_req_url, meta_match.group(1).strip())
162 if meta_dest != current_url:
163 history.append({
164 "hop": hop,
165 "type": "meta_refresh",
166 "status": status_code,
167 "from": current_url,
168 "to": meta_dest
169 })
170 current_url = meta_dest
171 continue
172
173 # Check JavaScript window.location redirect
174 js_match = re.search(
175 r'(?:window\.location(?:\.href)?|location\.replace)\s*=\s*["\'](https?://[^"\']+)["\']',
176 body_sample,
177 re.IGNORECASE
178 )
179 if js_match:
180 js_dest = js_match.group(1).strip()
181 if js_dest != current_url:
182 history.append({
183 "hop": hop,
184 "type": "js_location",
185 "status": status_code,
186 "from": current_url,
187 "to": js_dest
188 })
189 current_url = js_dest
190 continue
191
192 # If final URL is different from start URL
193 if final_req_url != current_url:
194 history.append({
195 "hop": hop,
196 "type": "http_redirect",
197 "status": status_code,
198 "from": current_url,
199 "to": final_req_url
200 })
201 current_url = final_req_url
202 else:
203 break
204
205 except urllib.error.HTTPError as e:
206 # Handle manual 301/302/303/307/308 redirects
207 location = e.headers.get("Location")
208 if location:
209 next_url = urllib.parse.urljoin(current_url, location)
210 history.append({
211 "hop": hop,
212 "type": "http_redirect",
213 "status": e.code,
214 "from": current_url,
215 "to": next_url
216 })
217 current_url = next_url
218 continue
219 else:
220 history.append({
221 "hop": hop,
222 "type": "error",
223 "status": e.code,
224 "message": str(e)
225 })
226 break
227 except Exception as e:
228 history.append({
229 "hop": hop,
230 "type": "error",
231 "message": str(e)
232 })
233 break
234
235 clean_final = self.clean_url(current_url)
236
237 return {
238 "success": True,
239 "original_url": url,
240 "final_url": current_url,
241 "clean_url": clean_final,
242 "total_hops": len(history),
243 "history": history
244 }
245
246
247# ─────────────────────────────────────────────────────────────────────
248# CLI Entry Point
249# ─────────────────────────────────────────────────────────────────────
250def main():
251 if len(sys.argv) < 2:
252 print("Usage: python3 universal_bypass.py <url>")
253 print("Example: python3 universal_bypass.py 'https://bit.ly/3xSampleLink'")
254 sys.exit(1)
255
256 target_url = sys.argv[1]
257 bypasser = UniversalBypasser()
258 result = bypasser.resolve(target_url)
259
260 print(json.dumps(result, indent=2, ensure_ascii=False))
261
262
263if __name__ == "__main__":
264 main()
265
Discussion & Comments0

No comments yet — be the first to leave feedback or start a code discussion.

Sign in with your GitHub account to write comments and join the discussion.