Can we port Vinovo extractor #585

New issue

Closed

opened 2025-12-16 15:36:04 +00:00 by GLlgGL · 2 comments

GLlgGL commented

2025-12-16 15:36:04 +00:00

(Migrated from github.com)

I was trying to make the Vinovo extractor work(via mediaflow) and I am able to get the final url but is not playable...even on the same server where it was extracted...instead if I get the final link from browser and try it on same IP with curl it works lol

https://vinovo.to/e/r90rer94a7jy1

Addon
`import { NotFoundError } from '../error';
import { Context, Format, Meta, UrlResult } from '../types';
import { Extractor } from './Extractor';
import {
buildMediaFlowProxyExtractorStreamUrl,
supportsMediaFlowProxy,
} from '../utils';
import * as cheerio from 'cheerio';

const FIREFOX_UA =
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' +
'AppleWebKit/537.36 (KHTML, like Gecko) ' +
'Chrome/143.0.0.0 Safari/537.36';

export class Vinovo extends Extractor {
public readonly id = 'Vinovo';
public readonly label = 'Vinovo (MFP)';
public override readonly ttl = 10800000; // 3h
public override viaMediaFlowProxy = true;

private domains = ['vinovo.to', 'vinovo.si'];

public supports(ctx: Context, url: URL): boolean {
return (
this.domains.some(d => url.host.includes(d)) &&
supportsMediaFlowProxy(ctx)
);
}

// Normalize to embed URL
public override normalize(url: URL): URL {
// Accept /d/ or /e/, always normalize to /e/
return new URL(url.href.replace(//[de]//, '/e/'));
}

protected async extractInternal(
ctx: Context,
url: URL,
meta: Meta
): Promise<UrlResult[]> {
//const referer = meta.referer ?? url.href;

const headers: Record<string, string> = {

'User-Agent': FIREFOX_UA,
Referer: 'https://vinovo.to/',

};
;

// --- 1. Fetch embed page (existence check only) ---
let embedHtml: string;
try {
  embedHtml = await this.fetcher.text(ctx, url, headers);
} catch {
  // Fail fast so StreamResolver skips this source
  throw new NotFoundError('Vinovo: embed not responding');
}

if (!embedHtml) throw new NotFoundError();

// --- Detect removed / invalid video ---
if (
  embedHtml.includes('File Not Found') ||
  embedHtml.includes('Removed') ||
  embedHtml.includes('Not Found')
) {
  throw new NotFoundError('Vinovo: video removed');
}

// Optional: extract title (best-effort only)
let title = this.label;
try {
  const $ = cheerio.load(embedHtml);
  title =
    $('title')
      .text()
      .replace(/^Watch\s+/i, '')
      .trim() || this.label;
} catch {
  // ignore
}

// --- 2. MediaFlow proxy ---
const proxiedUrl = await buildMediaFlowProxyExtractorStreamUrl(
  ctx,
  this.fetcher,
  this.id,
  url,
  headers
);

return [
  {
    url: proxiedUrl,
    format: Format.mp4,
    label: this.label,
    sourceId: `${this.id}_${meta.countryCodes?.join('_') ?? 'all'}`,
    ttl: this.ttl,
    requestHeaders: headers,
    meta: {
      ...meta,
      title,
    },
  },
];

}
}`

Mediaflow
import re
import json
from typing import Dict, Any
from urllib.parse import urlparse

from mediaflow_proxy.extractors.base import BaseExtractor, ExtractorError
from mediaflow_proxy.utils.girc import girc

FIREFOX_UA = (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/143.0.0.0 Safari/537.36"
)

class VinovoExtractor(BaseExtractor):
"""
Vinovo extractor for MediaFlow Proxy

✔ MP4 stream (NOT HLS)
✔ Matches Kodi ResolveURL
✔ Correct reCAPTCHA handling
✔ Correct CDN headers (prevents 403)
"""

def __init__(self, *args, **kwargs):
    super().__init__(*args, **kwargs)
    self.mediaflow_endpoint = "proxy_stream_endpoint"

async def extract(self, url: str) -> Dict[str, Any]:
    referer = self.base_headers.get("Referer")
    if not referer:
        parsed = urlparse(url)
        referer = f"{parsed.scheme}://{parsed.netloc}/"
    parsed = urlparse(url)

    if not parsed.hostname or "vinovo" not in parsed.hostname:
        raise ExtractorError("VINOVO: Invalid domain")

    # Normalize /d/ → /e/
    url = re.sub(r"/[dD]/", "/e/", url)

    # -------------------------------------------------
    # Incoming headers (from MediaFlow)
    # -------------------------------------------------
    incoming = self.base_headers or {}

    embed_referer = incoming.get("referer")
    if not embed_referer:
        raise ExtractorError("VINOVO: Missing embed referer")

    user_agent = incoming.get("user-agent", FIREFOX_UA)

    vinovo_origin = f"{parsed.scheme}://{parsed.hostname}/"

    # -------------------------------------------------
    # 1) Fetch embed page (USES EMBED REFERER)
    # -------------------------------------------------
    page_headers = {
        "User-Agent": user_agent,
        "Referer": embed_referer,
    }

    response = await self._make_request(url, headers=page_headers)
    html = response.text or ""

    if not html:
        raise ExtractorError("VINOVO: Empty embed page")

    cookies = response.cookies or {}

    # -------------------------------------------------
    # 2) Extract token + base URL
    # -------------------------------------------------
    token_match = re.search(r'name="token"\s*content="([^"]+)', html)
    base_match = re.search(r'<video[^>]+data-base="([^"]+)', html)

    if not token_match or not base_match:
        raise ExtractorError("VINOVO: Token or base missing")

    token = token_match.group(1)
    base = base_match.group(1)

    # -------------------------------------------------
    # 3) Solve reCAPTCHA (MUST USE VINOVO ORIGIN)
    # -------------------------------------------------
    recaptcha = await girc(
        self._make_request,
        html,
        vinovo_origin,   # 🔑 CRITICAL
    )

    if not recaptcha:
        raise ExtractorError("VINOVO: reCAPTCHA failed")

    # -------------------------------------------------
    # 4) Call Vinovo API
    # -------------------------------------------------
    media_id = self._extract_id(url)
    api_url = f"https://{parsed.hostname}/api/file/url/{media_id}"

    api_headers = {
        "User-Agent": user_agent,
        "Referer": vinovo_origin,
        "Origin": vinovo_origin.rstrip("/"),
        "X-Requested-With": "XMLHttpRequest",
    }

    if cookies:
        api_headers["Cookie"] = "; ".join(
            f"{k}={v}" for k, v in cookies.items()
        )

    api_resp = await self._make_request(
        api_url,
        method="POST",
        headers=api_headers,
        data={
            "token": token,
            "recaptcha": recaptcha,
        },
    )

    if not api_resp.text:
        raise ExtractorError("VINOVO: Empty API response")

    try:
        api_json = json.loads(api_resp.text)
    except Exception:
        raise ExtractorError("VINOVO: Invalid API JSON")

    if api_json.get("status") != "ok":
        raise ExtractorError(f"VINOVO: API rejected {api_json}")

    # -------------------------------------------------
    # 5) Final MP4 URL + CDN headers
    # -------------------------------------------------
    final_url = f"{base}/stream/{api_json['token']}"


    
    #self.base_headers["origin"] = "https://vinovo.to"
    #self.base_headers["range"] = "bytes=0-"

    self.base_headers.update({
        "origin": "https://vinovo.to",
        "range": "bytes=0-",
        "accept": "*/*",
        "accept-encoding": "identity",
        "host": urlparse(base).hostname,
        # 🔑 CRITICAL — request fingerprint
        "sec-fetch-site": "cross-site",
        "sec-fetch-mode": "cors",
        "sec-fetch-dest": "video",
    })
    return {
        "destination_url": final_url,
        "request_headers": self.base_headers,
        "mediaflow_endpoint": self.mediaflow_endpoint,
    }

def _extract_id(self, url: str) -> str:
    match = re.search(r"/(?:e|d)/([0-9a-zA-Z]+)", url)
    if not match:
        raise ExtractorError("VINOVO: Invalid URL format")
    return match.group(1)

What could it be...

Hi I was trying to make the Vinovo extractor work(via mediaflow) and I am able to get the final url but is not playable...even on the same server where it was extracted...instead if I get the final link from browser and try it on same IP with curl it works lol `https://vinovo.to/e/r90rer94a7jy1` Addon `import { NotFoundError } from '../error'; import { Context, Format, Meta, UrlResult } from '../types'; import { Extractor } from './Extractor'; import { buildMediaFlowProxyExtractorStreamUrl, supportsMediaFlowProxy, } from '../utils'; import * as cheerio from 'cheerio'; const FIREFOX_UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' + 'AppleWebKit/537.36 (KHTML, like Gecko) ' + 'Chrome/143.0.0.0 Safari/537.36'; export class Vinovo extends Extractor { public readonly id = 'Vinovo'; public readonly label = 'Vinovo (MFP)'; public override readonly ttl = 10800000; // 3h public override viaMediaFlowProxy = true; private domains = ['vinovo.to', 'vinovo.si']; public supports(ctx: Context, url: URL): boolean { return ( this.domains.some(d => url.host.includes(d)) && supportsMediaFlowProxy(ctx) ); } // Normalize to embed URL public override normalize(url: URL): URL { // Accept /d/ or /e/, always normalize to /e/ return new URL(url.href.replace(/\/[de]\//, '/e/')); } protected async extractInternal( ctx: Context, url: URL, meta: Meta ): Promise<UrlResult[]> { //const referer = meta.referer ?? url.href; const headers: Record<string, string> = { 'User-Agent': FIREFOX_UA, Referer: 'https://vinovo.to/', }; ; // --- 1. Fetch embed page (existence check only) --- let embedHtml: string; try { embedHtml = await this.fetcher.text(ctx, url, headers); } catch { // Fail fast so StreamResolver skips this source throw new NotFoundError('Vinovo: embed not responding'); } if (!embedHtml) throw new NotFoundError(); // --- Detect removed / invalid video --- if ( embedHtml.includes('File Not Found') || embedHtml.includes('Removed') || embedHtml.includes('Not Found') ) { throw new NotFoundError('Vinovo: video removed'); } // Optional: extract title (best-effort only) let title = this.label; try { const $ = cheerio.load(embedHtml); title = $('title') .text() .replace(/^Watch\s+/i, '') .trim() || this.label; } catch { // ignore } // --- 2. MediaFlow proxy --- const proxiedUrl = await buildMediaFlowProxyExtractorStreamUrl( ctx, this.fetcher, this.id, url, headers ); return [ { url: proxiedUrl, format: Format.mp4, label: this.label, sourceId: `${this.id}_${meta.countryCodes?.join('_') ?? 'all'}`, ttl: this.ttl, requestHeaders: headers, meta: { ...meta, title, }, }, ]; } }` Mediaflow import re import json from typing import Dict, Any from urllib.parse import urlparse from mediaflow_proxy.extractors.base import BaseExtractor, ExtractorError from mediaflow_proxy.utils.girc import girc FIREFOX_UA = ( "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " "AppleWebKit/537.36 (KHTML, like Gecko) " "Chrome/143.0.0.0 Safari/537.36" ) class VinovoExtractor(BaseExtractor): """ Vinovo extractor for MediaFlow Proxy ✔ MP4 stream (NOT HLS) ✔ Matches Kodi ResolveURL ✔ Correct reCAPTCHA handling ✔ Correct CDN headers (prevents 403) """ def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.mediaflow_endpoint = "proxy_stream_endpoint" async def extract(self, url: str) -> Dict[str, Any]: referer = self.base_headers.get("Referer") if not referer: parsed = urlparse(url) referer = f"{parsed.scheme}://{parsed.netloc}/" parsed = urlparse(url) if not parsed.hostname or "vinovo" not in parsed.hostname: raise ExtractorError("VINOVO: Invalid domain") # Normalize /d/ → /e/ url = re.sub(r"/[dD]/", "/e/", url) # ------------------------------------------------- # Incoming headers (from MediaFlow) # ------------------------------------------------- incoming = self.base_headers or {} embed_referer = incoming.get("referer") if not embed_referer: raise ExtractorError("VINOVO: Missing embed referer") user_agent = incoming.get("user-agent", FIREFOX_UA) vinovo_origin = f"{parsed.scheme}://{parsed.hostname}/" # ------------------------------------------------- # 1) Fetch embed page (USES EMBED REFERER) # ------------------------------------------------- page_headers = { "User-Agent": user_agent, "Referer": embed_referer, } response = await self._make_request(url, headers=page_headers) html = response.text or "" if not html: raise ExtractorError("VINOVO: Empty embed page") cookies = response.cookies or {} # ------------------------------------------------- # 2) Extract token + base URL # ------------------------------------------------- token_match = re.search(r'name="token"\s*content="([^"]+)', html) base_match = re.search(r'<video[^>]+data-base="([^"]+)', html) if not token_match or not base_match: raise ExtractorError("VINOVO: Token or base missing") token = token_match.group(1) base = base_match.group(1) # ------------------------------------------------- # 3) Solve reCAPTCHA (MUST USE VINOVO ORIGIN) # ------------------------------------------------- recaptcha = await girc( self._make_request, html, vinovo_origin, # 🔑 CRITICAL ) if not recaptcha: raise ExtractorError("VINOVO: reCAPTCHA failed") # ------------------------------------------------- # 4) Call Vinovo API # ------------------------------------------------- media_id = self._extract_id(url) api_url = f"https://{parsed.hostname}/api/file/url/{media_id}" api_headers = { "User-Agent": user_agent, "Referer": vinovo_origin, "Origin": vinovo_origin.rstrip("/"), "X-Requested-With": "XMLHttpRequest", } if cookies: api_headers["Cookie"] = "; ".join( f"{k}={v}" for k, v in cookies.items() ) api_resp = await self._make_request( api_url, method="POST", headers=api_headers, data={ "token": token, "recaptcha": recaptcha, }, ) if not api_resp.text: raise ExtractorError("VINOVO: Empty API response") try: api_json = json.loads(api_resp.text) except Exception: raise ExtractorError("VINOVO: Invalid API JSON") if api_json.get("status") != "ok": raise ExtractorError(f"VINOVO: API rejected {api_json}") # ------------------------------------------------- # 5) Final MP4 URL + CDN headers # ------------------------------------------------- final_url = f"{base}/stream/{api_json['token']}" #self.base_headers["origin"] = "https://vinovo.to" #self.base_headers["range"] = "bytes=0-" self.base_headers.update({ "origin": "https://vinovo.to", "range": "bytes=0-", "accept": "*/*", "accept-encoding": "identity", "host": urlparse(base).hostname, # 🔑 CRITICAL — request fingerprint "sec-fetch-site": "cross-site", "sec-fetch-mode": "cors", "sec-fetch-dest": "video", }) return { "destination_url": final_url, "request_headers": self.base_headers, "mediaflow_endpoint": self.mediaflow_endpoint, } def _extract_id(self, url: str) -> str: match = re.search(r"/(?:e|d)/([0-9a-zA-Z]+)", url) if not match: raise ExtractorError("VINOVO: Invalid URL format") return match.group(1) What could it be...

👍 1

GLlgGL commented

2025-12-21 08:35:39 +00:00

(Migrated from github.com)

No link to test.The link i had expired or was removed

GLlgGL commented

2025-12-22 14:26:49 +00:00

(Migrated from github.com)

Link seems to be again up and working