There are many tool to find url audio stream from radio station's page, here are a few list:
- playwright
- Selenium
- Puppeteer
To use Wget to find url audo on statik and simple web
$ wget --spider -r -l 5 -nv -w 1 --no-clobber -A .mp3,.m3u8 "https://www.example.com/audio/stations" 2>&1 | grep -E '\.(mp3|m3u8)$' | awk '{print $3}' | sort -u > out_audio_urls.txt
Install playwright on debian with virtual environment:
myuser@mypc:~$ mkdir spider_playwright
myuser@mypc:~$ cd spider_playwright/
myuser@mypc:~/spider_playwright$ python3 -m venv venv
myuser@mypc:~/spider_playwright$ source venv/bin/activate
(venv) myuser@mypc:~/spider_playwright$ pip install playwright
Collecting playwright
Downloading playwright-1.56.0-py3-none-manylinux1_x86_64.whl.metadata (3.5 kB)
Collecting pyee<14,>=13 (from playwright)
Downloading pyee-13.0.0-py3-none-any.whl.metadata (2.9 kB)
Collecting greenlet<4.0.0,>=3.1.1 (from playwright)
Using cached greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl.metadata (4.1 kB)
Collecting typing-extensions (from pyee<14,>=13->playwright)
Using cached typing_extensions-4.15.0-py3-none-any.whl.metadata (3.3 kB)
Downloading playwright-1.56.0-py3-none-manylinux1_x86_64.whl (46.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 46.3/46.3 MB 2.5 MB/s eta 0:00:00
Using cached greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (610 kB)
Downloading pyee-13.0.0-py3-none-any.whl (15 kB)
Using cached typing_extensions-4.15.0-py3-none-any.whl (44 kB)
Installing collected packages: typing-extensions, greenlet, pyee, playwright
Successfully installed greenlet-3.2.4 playwright-1.56.0 pyee-13.0.0 typing-extensions-4.15.0
(venv) myuser@mypc:~/spider_playwright$ playwright install
Downloading Chromium 141.0.7390.37 (playwright build v1194) from https://cdn.playwright.dev/dbazure/download/playwright/builds/chromium/1194/chromium-linux.zip
173.9 MiB [====================] 100% 0.0s
Chromium 141.0.7390.37 (playwright build v1194) downloaded to /home/myuser/.cache/ms-playwright/chromium-1194
Downloading Chromium Headless Shell 141.0.7390.37 (playwright build v1194) from https://cdn.playwright.dev/dbazure/download/playwright/builds/chromium/1194/chromium-headless-shell-linux.zip
104.3 MiB [====================] 100% 0.0s
Chromium Headless Shell 141.0.7390.37 (playwright build v1194) downloaded to /home/myuser/.cache/ms-playwright/chromium_headless_shell-1194
Downloading Firefox 142.0.1 (playwright build v1495) from https://cdn.playwright.dev/dbazure/download/playwright/builds/firefox/1495/firefox-debian-13.zip
96.7 MiB [====================] 100% 0.0s
Firefox 142.0.1 (playwright build v1495) downloaded to /home/myuser/.cache/ms-playwright/firefox-1495
Downloading Webkit 26.0 (playwright build v2215) from https://cdn.playwright.dev/dbazure/download/playwright/builds/webkit/2215/webkit-debian-13.zip
88.1 MiB [====================] 100% 0.0s
Webkit 26.0 (playwright build v2215) downloaded to /home/myuser/.cache/ms-playwright/webkit-2215
Downloading FFMPEG playwright build v1011 from https://cdn.playwright.dev/dbazure/download/playwright/builds/ffmpeg/1011/ffmpeg-linux.zip
2.3 MiB [====================] 100% 0.0s
FFMPEG playwright build v1011 downloaded to /home/myuser/.cache/ms-playwright/ffmpeg-1011
create file myspider.py and customize to your requirements, make it executable
(venv) myuser@mypc:~/spider_playwright$ chmod u+x myspider.py
source code myspider.py modify it to meet your requirements
import asyncio
from playwright.async_api import async_playwright
# generated and adjust by chatgpt.com
AUDIO_HINTS = [
".mp3", ".aac", ".m3u8", ".ogg", ".opus", ".wav",
"stream", "/proxy/", "/live", "radio"
]
async def scan_audio_stream(url: str, listen_seconds: int = 15):
async with async_playwright() as p:
browser = await p.chromium.launch(headless=False)
page = await browser.new_page()
# ----- Detect manual browser close -----
browser_disconnected = asyncio.Event()
def on_browser_disconnect():
print("\n[BROWSER CLOSED] Exiting application.")
browser_disconnected.set()
browser.on("disconnected", on_browser_disconnect)
# ---------------------------------------
found = set()
async def on_response(res):
u = res.url.lower()
ct = res.headers.get("content-type", "").lower()
if "audio" in ct or any(k in u for k in AUDIO_HINTS):
if u not in found:
print(f"[NEW AUDIO STREAM] {u}")
found.add(u)
page.on("response", on_response)
print("Opening page...")
await page.goto(url, wait_until="domcontentloaded")
await asyncio.sleep(2)
# ---- Find audio player iframe ----
candidate_frames = [
f for f in page.frames
if any(kw in f.url.lower() for kw in ["player", "radio", "embed"])
]
if not candidate_frames:
candidate_frames = page.frames # fallback
print("Attempting to click play...")
for f in candidate_frames:
try:
for sel in ["button[aria-label='Play']", "button.play", ".jp-play", "button"]:
btn = await f.query_selector(sel)
if btn:
print(f"Clicked play in iframe → {f.url}")
await btn.click()
break
except:
pass
print(f"\nListening for audio streams up to {listen_seconds} seconds...\n")
# ----- Wait for 15 seconds OR browser close -----
try:
await asyncio.wait_for(browser_disconnected.wait(), timeout=listen_seconds)
except asyncio.TimeoutError:
print("\n[TIMEOUT] Done scanning.")
# -------------------------------------------------
await browser.close()
return list(found)
if __name__ == "__main__":
results = asyncio.run(scan_audio_stream(
"https://www.example.com", # CHANGE HERE
listen_seconds=15 # ← Fast scan
))
print("\n===== ALL STREAMS FOUND =====")
for s in results:
print(s)
Code
from playwright.sync_api import sync_playwright
def main():
with sync_playwright() as p:
browser = p.chromium.launch(
headless=False # <-- You can manually interact
)
context = browser.new_context()
page = context.new_page()
print("🚀 Browser launched. Type the radio station URL manually.")
print("👉 When you press Play, audio stream URLs will appear here.\n")
# Capture outgoing requests
def on_request(request):
url = request.url
if (
".mp3" in url or
".aac" in url or
".m3u8" in url or
".ogg" in url or
"stream" in url.lower() or
request.resource_type == "media"
):
print("🎧 AUDIO STREAM REQUEST FOUND:")
print(url, "\n")
page.on("request", on_request)
# Capture responses containing audio
def on_response(response):
url = response.url
headers = response.headers
content_type = headers.get("content-type", "")
if any(fmt in content_type for fmt in ["audio", "mpeg", "aac", "ogg"]):
print("🎧 AUDIO STREAM RESPONSE FOUND:")
print(url, "\n")
page.on("response", on_response)
# Open a blank page — you will type the URL manually
page.goto("about:blank")
# Keep browser open
browser.wait_for_event("disconnected")
if __name__ == "__main__":
main()
Enjoy
