Update app.py
Browse files
app.py
CHANGED
|
@@ -2,58 +2,88 @@ from fastapi import FastAPI, HTTPException
|
|
| 2 |
import requests
|
| 3 |
import re
|
| 4 |
import os
|
|
|
|
| 5 |
from urllib.parse import urlparse
|
| 6 |
|
| 7 |
app = FastAPI()
|
| 8 |
|
| 9 |
-
#
|
| 10 |
-
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
def get_buzz_info(buzz_url):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
try:
|
| 15 |
-
# 1. Fetch page
|
| 16 |
-
# We
|
| 17 |
-
|
|
|
|
|
|
|
| 18 |
r.raise_for_status()
|
| 19 |
|
| 20 |
-
# Regex for filename
|
| 21 |
name = re.search(r'<span class="text-2xl">([^<]+)</span>', r.text)
|
| 22 |
if name:
|
| 23 |
filename = name.group(1).strip()
|
| 24 |
else:
|
| 25 |
filename = os.path.basename(urlparse(buzz_url).path) or "buzzheavier_file"
|
| 26 |
|
| 27 |
-
# 2.
|
| 28 |
dl_url = buzz_url.rstrip("/") + "/download"
|
| 29 |
|
| 30 |
-
#
|
| 31 |
-
|
| 32 |
"HX-Request": "true",
|
| 33 |
-
"Referer": buzz_url
|
|
|
|
| 34 |
}
|
| 35 |
|
| 36 |
-
|
| 37 |
-
r2 = session.get(dl_url, headers=h, timeout=10, allow_redirects=False)
|
| 38 |
|
| 39 |
link = r2.headers.get("hx-redirect")
|
| 40 |
|
| 41 |
if not link:
|
| 42 |
-
# Fallback if status is 200 but no redirect header
|
| 43 |
if r2.status_code == 200:
|
| 44 |
print("Warning: No redirect, but got 200 OK.")
|
| 45 |
else:
|
| 46 |
raise ValueError(f"No hx-redirect header found. Status: {r2.status_code}")
|
| 47 |
|
| 48 |
-
# 3. Extract Cookies
|
| 49 |
-
# Convert cookie jar to a standard "Cookie: name=value;" string
|
| 50 |
cookie_dict = session.cookies.get_dict()
|
| 51 |
cookie_string = "; ".join([f"{k}={v}" for k, v in cookie_dict.items()])
|
| 52 |
|
| 53 |
return {
|
| 54 |
"filename": filename,
|
| 55 |
"download_url": link,
|
| 56 |
-
"cookies": cookie_string
|
|
|
|
| 57 |
}
|
| 58 |
|
| 59 |
except Exception as e:
|
|
@@ -62,13 +92,10 @@ def get_buzz_info(buzz_url):
|
|
| 62 |
|
| 63 |
@app.get("/")
|
| 64 |
def home():
|
| 65 |
-
return {"status": "Running"
|
| 66 |
|
| 67 |
@app.get("/resolve")
|
| 68 |
def resolve_url(url: str):
|
| 69 |
-
# Clear cookies between requests to ensure a fresh session for every user
|
| 70 |
-
session.cookies.clear()
|
| 71 |
-
|
| 72 |
data = get_buzz_info(url)
|
| 73 |
if not data:
|
| 74 |
raise HTTPException(status_code=500, detail="Failed to resolve URL")
|
|
|
|
| 2 |
import requests
|
| 3 |
import re
|
| 4 |
import os
|
| 5 |
+
import random
|
| 6 |
from urllib.parse import urlparse
|
| 7 |
|
| 8 |
app = FastAPI()
|
| 9 |
|
| 10 |
+
# --- 1. RANDOMIZATION TOOLS ---
|
| 11 |
+
|
| 12 |
+
# A pool of realistic User-Agents to rotate through
|
| 13 |
+
USER_AGENTS = [
|
| 14 |
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
| 15 |
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
|
| 16 |
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:120.0) Gecko/20100101 Firefox/120.0",
|
| 17 |
+
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
|
| 18 |
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:109.0) Gecko/20100101 Firefox/118.0"
|
| 19 |
+
]
|
| 20 |
+
|
| 21 |
+
def get_random_ip():
|
| 22 |
+
"""Generates a random IP address to bypass simple IP counters."""
|
| 23 |
+
return f"{random.randint(1, 200)}.{random.randint(1, 255)}.{random.randint(1, 255)}.{random.randint(1, 255)}"
|
| 24 |
+
|
| 25 |
+
# ------------------------------
|
| 26 |
|
| 27 |
def get_buzz_info(buzz_url):
|
| 28 |
+
session = requests.Session()
|
| 29 |
+
|
| 30 |
+
# Generate a fresh identity for this request
|
| 31 |
+
current_ua = random.choice(USER_AGENTS)
|
| 32 |
+
fake_ip = get_random_ip()
|
| 33 |
+
|
| 34 |
+
# Headers that mimic a unique user coming from a unique IP
|
| 35 |
+
headers = {
|
| 36 |
+
"User-Agent": current_ua,
|
| 37 |
+
"X-Forwarded-For": fake_ip,
|
| 38 |
+
"X-Real-IP": fake_ip,
|
| 39 |
+
"Referer": "https://buzzheavier.com/"
|
| 40 |
+
}
|
| 41 |
+
|
| 42 |
+
session.headers.update(headers)
|
| 43 |
+
|
| 44 |
try:
|
| 45 |
+
# 1. Fetch page (View Count)
|
| 46 |
+
# We add a random query param to prevent caching on their side: ?cachebuster=123
|
| 47 |
+
url_with_prevention = f"{buzz_url}?cb={random.randint(1, 100000)}"
|
| 48 |
+
|
| 49 |
+
r = session.get(url_with_prevention, timeout=10)
|
| 50 |
r.raise_for_status()
|
| 51 |
|
|
|
|
| 52 |
name = re.search(r'<span class="text-2xl">([^<]+)</span>', r.text)
|
| 53 |
if name:
|
| 54 |
filename = name.group(1).strip()
|
| 55 |
else:
|
| 56 |
filename = os.path.basename(urlparse(buzz_url).path) or "buzzheavier_file"
|
| 57 |
|
| 58 |
+
# 2. Trigger Download (Download Count)
|
| 59 |
dl_url = buzz_url.rstrip("/") + "/download"
|
| 60 |
|
| 61 |
+
# Headers specifically for the download trigger
|
| 62 |
+
dl_headers = {
|
| 63 |
"HX-Request": "true",
|
| 64 |
+
"Referer": buzz_url,
|
| 65 |
+
"X-Forwarded-For": fake_ip # Keep the IP consistent for this session
|
| 66 |
}
|
| 67 |
|
| 68 |
+
r2 = session.get(dl_url, headers=dl_headers, timeout=10, allow_redirects=False)
|
|
|
|
| 69 |
|
| 70 |
link = r2.headers.get("hx-redirect")
|
| 71 |
|
| 72 |
if not link:
|
|
|
|
| 73 |
if r2.status_code == 200:
|
| 74 |
print("Warning: No redirect, but got 200 OK.")
|
| 75 |
else:
|
| 76 |
raise ValueError(f"No hx-redirect header found. Status: {r2.status_code}")
|
| 77 |
|
| 78 |
+
# 3. Extract Cookies
|
|
|
|
| 79 |
cookie_dict = session.cookies.get_dict()
|
| 80 |
cookie_string = "; ".join([f"{k}={v}" for k, v in cookie_dict.items()])
|
| 81 |
|
| 82 |
return {
|
| 83 |
"filename": filename,
|
| 84 |
"download_url": link,
|
| 85 |
+
"cookies": cookie_string,
|
| 86 |
+
"user_agent": current_ua # Pass this to Worker so it matches!
|
| 87 |
}
|
| 88 |
|
| 89 |
except Exception as e:
|
|
|
|
| 92 |
|
| 93 |
@app.get("/")
|
| 94 |
def home():
|
| 95 |
+
return {"status": "Running"}
|
| 96 |
|
| 97 |
@app.get("/resolve")
|
| 98 |
def resolve_url(url: str):
|
|
|
|
|
|
|
|
|
|
| 99 |
data = get_buzz_info(url)
|
| 100 |
if not data:
|
| 101 |
raise HTTPException(status_code=500, detail="Failed to resolve URL")
|