Add ripnsfw provider (Doodstream/Lulustream leak aggregator)
ripnsfw.com serves its entire catalogue as a published-Google-Sheet CSV with no native pagination/search API, so the provider fetches and parses that CSV once (cached 180s) and does feed/search/pagination/sort in memory. Each row's Doodstream/Lulustream embed links resolve to formats[] via the existing (previously unused) doodstream/lulustream redirect proxies. Also fixes check.py's follow_proxy_redirect, which used HEAD even though these redirect-proxy routes only accept GET/POST, so it never actually resolved the redirect; extends the CF-protected host list (suffix matching + ripnsfw.com's client-only-SPA 404 page, dood.video, tnmr.org) so known sandbox/CDN-IP-reputation failures are reported as warnings instead of errors. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QTqf6orbHZ9rFFpVpcgzcR
This commit is contained in:
Simon
391
src/providers/ripnsfw.rs
Normal file
391
src/providers/ripnsfw.rs
Normal file
@@ -0,0 +1,391 @@
|
||||
use std::sync::{Arc, RwLock};
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use async_trait::async_trait;
|
||||
use chrono::NaiveDate;
|
||||
use percent_encoding::{NON_ALPHANUMERIC, utf8_percent_encode};
|
||||
|
||||
use crate::DbPool;
|
||||
use crate::api::ClientVersion;
|
||||
use crate::providers::{
|
||||
Provider, build_proxy_url, report_provider_error, requester_or_default, strip_url_scheme,
|
||||
};
|
||||
use crate::status::*;
|
||||
use crate::videos::{ServerOptions, VideoFormat, VideoItem};
|
||||
|
||||
pub const CHANNEL_METADATA: crate::providers::ProviderChannelMetadata =
|
||||
crate::providers::ProviderChannelMetadata {
|
||||
group_id: "onlyfans",
|
||||
tags: &["onlyfans", "leaked", "amateur"],
|
||||
};
|
||||
|
||||
const CHANNEL_ID: &str = "ripnsfw";
|
||||
const BASE_URL: &str = "https://ripnsfw.com";
|
||||
const CSV_URL: &str = "https://ripnsfw.com/data.csv";
|
||||
const CDN_THUMB_BASE: &str = "https://cdn.ripnsfw.com/thumbs/";
|
||||
const CATALOG_TTL: Duration = Duration::from_secs(180);
|
||||
|
||||
// data.csv columns (0-indexed): THUMB,NEW,NOME,DOODSTREAM,LULUSTREAM,<link3>,DOOD,
|
||||
// <guests>,SITE(bunkr download mirrors),TITLE,ID,#(tags),POST(search text),<blank>,DATE,SIZE
|
||||
#[derive(Debug, Clone)]
|
||||
struct RipnsfwVideo {
|
||||
id: String,
|
||||
model_name: String,
|
||||
guests: Vec<String>,
|
||||
doodstream: Option<String>,
|
||||
lulustream: Option<String>,
|
||||
streamtape: Option<String>,
|
||||
tags: Vec<String>,
|
||||
thumb_file: String,
|
||||
date: Option<String>,
|
||||
uploaded_at: Option<u64>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
enum Target {
|
||||
Latest,
|
||||
Search(String),
|
||||
Tag(String),
|
||||
Model(String),
|
||||
}
|
||||
|
||||
pub struct RipnsfwProvider {
|
||||
catalog: Arc<RwLock<Option<(Instant, Vec<RipnsfwVideo>)>>>,
|
||||
}
|
||||
|
||||
impl RipnsfwProvider {
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
catalog: Arc::new(RwLock::new(None)),
|
||||
}
|
||||
}
|
||||
|
||||
fn build_channel(&self, _clientversion: ClientVersion) -> Channel {
|
||||
Channel {
|
||||
id: CHANNEL_ID.to_string(),
|
||||
name: "RIPNSFW".to_string(),
|
||||
description: "Leaked creator clips mirrored via Doodstream and Lulustream."
|
||||
.to_string(),
|
||||
premium: false,
|
||||
favicon: "https://www.google.com/s2/favicons?sz=64&domain=ripnsfw.com".to_string(),
|
||||
status: "active".to_string(),
|
||||
categories: vec![],
|
||||
options: vec![ChannelOption {
|
||||
id: "sort".to_string(),
|
||||
title: "Sort".to_string(),
|
||||
description: "Newest or oldest leaks first.".to_string(),
|
||||
systemImage: "list.number".to_string(),
|
||||
colorName: "pink".to_string(),
|
||||
options: vec![
|
||||
FilterOption {
|
||||
id: "new".to_string(),
|
||||
title: "Newest".to_string(),
|
||||
},
|
||||
FilterOption {
|
||||
id: "oldest".to_string(),
|
||||
title: "Oldest".to_string(),
|
||||
},
|
||||
],
|
||||
multiSelect: false,
|
||||
}],
|
||||
nsfw: true,
|
||||
cacheDuration: Some(600),
|
||||
ytdlpCommand: Some("yt-dlp --impersonate chrome-120".to_string()),
|
||||
}
|
||||
}
|
||||
|
||||
fn resolve_target(query: &str) -> Target {
|
||||
let q = query.trim();
|
||||
if let Some(value) = q
|
||||
.strip_prefix("tag:")
|
||||
.or_else(|| q.strip_prefix("category:"))
|
||||
.or_else(|| q.strip_prefix("cat:"))
|
||||
{
|
||||
let value = value.trim();
|
||||
if !value.is_empty() {
|
||||
return Target::Tag(value.to_string());
|
||||
}
|
||||
}
|
||||
if let Some(value) = q.strip_prefix("model:").or_else(|| q.strip_prefix("uploader:")) {
|
||||
let value = value.trim();
|
||||
if !value.is_empty() {
|
||||
return Target::Model(value.to_string());
|
||||
}
|
||||
}
|
||||
if !q.is_empty() {
|
||||
return Target::Search(q.to_string());
|
||||
}
|
||||
Target::Latest
|
||||
}
|
||||
|
||||
fn slugify(value: &str) -> String {
|
||||
let mut slug = String::new();
|
||||
let mut last_dash = false;
|
||||
for ch in value.trim().to_lowercase().chars() {
|
||||
if ch.is_ascii_alphanumeric() {
|
||||
slug.push(ch);
|
||||
last_dash = false;
|
||||
} else if !last_dash {
|
||||
slug.push('-');
|
||||
last_dash = true;
|
||||
}
|
||||
}
|
||||
slug.trim_matches('-').to_string()
|
||||
}
|
||||
|
||||
fn csv_split(line: &str) -> Vec<String> {
|
||||
let mut cols = Vec::new();
|
||||
let mut cur = String::new();
|
||||
let mut in_quotes = false;
|
||||
for ch in line.chars() {
|
||||
match ch {
|
||||
'"' => in_quotes = !in_quotes,
|
||||
',' if !in_quotes => {
|
||||
cols.push(cur.trim().to_string());
|
||||
cur.clear();
|
||||
}
|
||||
_ => cur.push(ch),
|
||||
}
|
||||
}
|
||||
cols.push(cur.trim().to_string());
|
||||
cols
|
||||
}
|
||||
|
||||
fn parse_date(raw: &str) -> Option<u64> {
|
||||
let date = NaiveDate::parse_from_str(raw.trim(), "%Y-%m-%d").ok()?;
|
||||
let dt = date.and_hms_opt(0, 0, 0)?;
|
||||
u64::try_from(dt.and_utc().timestamp()).ok()
|
||||
}
|
||||
|
||||
fn parse_tags(raw: &str) -> Vec<String> {
|
||||
raw.split(',')
|
||||
.map(|t| t.trim().trim_start_matches('#').trim().to_string())
|
||||
.filter(|t| !t.is_empty())
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn parse_guests(raw: &str, model_name: &str) -> Vec<String> {
|
||||
let model_upper = model_name.trim().to_uppercase();
|
||||
raw.split(|c| c == ',' || c == '&' || c == '/')
|
||||
.map(|g| g.trim().to_string())
|
||||
.filter(|g| !g.is_empty() && g.to_uppercase() != model_upper)
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn parse_csv(text: &str) -> Vec<RipnsfwVideo> {
|
||||
let normalized = text.replace('\r', "");
|
||||
let mut out = Vec::new();
|
||||
for (idx, line) in normalized.lines().enumerate() {
|
||||
if idx == 0 || line.trim().is_empty() {
|
||||
continue;
|
||||
}
|
||||
let cols = Self::csv_split(line);
|
||||
if cols.len() < 16 {
|
||||
continue;
|
||||
}
|
||||
let model_name = cols[2].trim().to_string();
|
||||
if model_name.is_empty() {
|
||||
continue;
|
||||
}
|
||||
let upper = model_name.to_uppercase();
|
||||
if matches!(upper.as_str(), "NAME" | "TEST" | "MODEL" | "EMPTY") {
|
||||
continue;
|
||||
}
|
||||
let id = cols[10].trim().to_string();
|
||||
if id.is_empty() {
|
||||
continue;
|
||||
}
|
||||
|
||||
let opt = |s: &str| -> Option<String> {
|
||||
let t = s.trim();
|
||||
if t.is_empty() { None } else { Some(t.to_string()) }
|
||||
};
|
||||
|
||||
let date_raw = cols[14].trim().to_string();
|
||||
out.push(RipnsfwVideo {
|
||||
id,
|
||||
guests: Self::parse_guests(&cols[7], &model_name),
|
||||
doodstream: opt(&cols[3]),
|
||||
lulustream: opt(&cols[4]),
|
||||
streamtape: opt(&cols[5]),
|
||||
tags: Self::parse_tags(&cols[11]),
|
||||
thumb_file: cols[0].trim().to_string(),
|
||||
uploaded_at: Self::parse_date(&date_raw),
|
||||
date: if date_raw.is_empty() { None } else { Some(date_raw) },
|
||||
model_name,
|
||||
});
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
fn request_headers(&self) -> Vec<(String, String)> {
|
||||
vec![
|
||||
("accept".to_string(), "text/csv,*/*;q=0.8".to_string()),
|
||||
(
|
||||
"user-agent".to_string(),
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
|
||||
.to_string(),
|
||||
),
|
||||
("referer".to_string(), format!("{BASE_URL}/")),
|
||||
]
|
||||
}
|
||||
|
||||
async fn fetch_catalog(&self, options: &ServerOptions) -> Vec<RipnsfwVideo> {
|
||||
if let Ok(guard) = self.catalog.read() {
|
||||
if let Some((fetched_at, rows)) = guard.as_ref() {
|
||||
if fetched_at.elapsed() < CATALOG_TTL {
|
||||
return rows.clone();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let mut requester = requester_or_default(options, CHANNEL_ID, "fetch_catalog");
|
||||
match requester
|
||||
.get_with_headers(CSV_URL, self.request_headers(), None)
|
||||
.await
|
||||
{
|
||||
Ok(text) => {
|
||||
let rows = Self::parse_csv(&text);
|
||||
if let Ok(mut guard) = self.catalog.write() {
|
||||
*guard = Some((Instant::now(), rows.clone()));
|
||||
}
|
||||
rows
|
||||
}
|
||||
Err(error) => {
|
||||
report_provider_error(CHANNEL_ID, "fetch_catalog", &error.to_string()).await;
|
||||
if let Ok(guard) = self.catalog.read() {
|
||||
if let Some((_, rows)) = guard.as_ref() {
|
||||
return rows.clone();
|
||||
}
|
||||
}
|
||||
vec![]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn matches_target(video: &RipnsfwVideo, target: &Target) -> bool {
|
||||
match target {
|
||||
Target::Latest => true,
|
||||
Target::Tag(tag) => {
|
||||
let needle = tag.trim().to_lowercase();
|
||||
video.tags.iter().any(|t| t.to_lowercase() == needle)
|
||||
}
|
||||
Target::Model(name) => {
|
||||
let needle_slug = Self::slugify(name);
|
||||
video.model_name.trim().to_lowercase() == name.trim().to_lowercase()
|
||||
|| Self::slugify(&video.model_name) == needle_slug
|
||||
}
|
||||
Target::Search(query) => {
|
||||
let needle = query.trim().to_lowercase();
|
||||
video.model_name.to_lowercase().contains(&needle)
|
||||
|| video
|
||||
.guests
|
||||
.iter()
|
||||
.any(|g| g.to_lowercase().contains(&needle))
|
||||
|| video.tags.iter().any(|t| t.to_lowercase().contains(&needle))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn build_item(&self, options: &ServerOptions, video: &RipnsfwVideo) -> VideoItem {
|
||||
let slug = Self::slugify(&video.model_name);
|
||||
let page_url = format!("{BASE_URL}/model/{slug}/{}", video.id);
|
||||
let thumb = format!(
|
||||
"{CDN_THUMB_BASE}{}",
|
||||
utf8_percent_encode(&video.thumb_file, NON_ALPHANUMERIC)
|
||||
);
|
||||
|
||||
let title = if video.guests.is_empty() {
|
||||
video.model_name.trim().to_string()
|
||||
} else {
|
||||
format!("{} & {}", video.model_name.trim(), video.guests.join(", "))
|
||||
};
|
||||
|
||||
let mut item = VideoItem::new(
|
||||
video.id.clone(),
|
||||
title,
|
||||
page_url,
|
||||
CHANNEL_ID.to_string(),
|
||||
thumb,
|
||||
0,
|
||||
);
|
||||
|
||||
item = item.uploader(video.model_name.trim().to_string());
|
||||
item = item.uploader_url(format!("{BASE_URL}/model/{slug}"));
|
||||
item.uploaderId = Some(format!("{CHANNEL_ID}:{slug}"));
|
||||
|
||||
if !video.tags.is_empty() {
|
||||
item = item.tags(video.tags.clone());
|
||||
}
|
||||
if let Some(ts) = video.uploaded_at {
|
||||
item = item.uploaded_at(ts);
|
||||
}
|
||||
|
||||
let mut formats = Vec::new();
|
||||
if let Some(url) = &video.lulustream {
|
||||
let proxy_url = build_proxy_url(options, "lulustream", &strip_url_scheme(url));
|
||||
formats.push(
|
||||
VideoFormat::m3u8(proxy_url, "high".to_string(), "hls".to_string())
|
||||
.format_note("Lulustream".to_string()),
|
||||
);
|
||||
}
|
||||
if let Some(url) = &video.doodstream {
|
||||
let proxy_url = build_proxy_url(options, "doodstream", &strip_url_scheme(url));
|
||||
formats.push(
|
||||
VideoFormat::new(proxy_url, "high".to_string(), "mp4".to_string())
|
||||
.format_note("Doodstream".to_string()),
|
||||
);
|
||||
}
|
||||
// Streamtape rows are rare in this feed and have no local resolver proxy
|
||||
// wired up yet, so they are intentionally not surfaced as a format.
|
||||
let _ = &video.streamtape;
|
||||
|
||||
if !formats.is_empty() {
|
||||
item = item.formats(formats);
|
||||
}
|
||||
|
||||
item
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl Provider for RipnsfwProvider {
|
||||
async fn get_videos(
|
||||
&self,
|
||||
_cache: crate::util::cache::VideoCache,
|
||||
_pool: DbPool,
|
||||
sort: String,
|
||||
query: Option<String>,
|
||||
page: String,
|
||||
per_page: String,
|
||||
options: ServerOptions,
|
||||
) -> Vec<VideoItem> {
|
||||
let page_num = page.parse::<usize>().unwrap_or(1).max(1);
|
||||
let per_page_num = per_page.parse::<usize>().unwrap_or(24).clamp(1, 60);
|
||||
let sort_value = if sort.trim().is_empty() {
|
||||
options.sort.clone().unwrap_or_else(|| "new".to_string())
|
||||
} else {
|
||||
sort
|
||||
};
|
||||
let query_value = query.unwrap_or_default();
|
||||
let target = Self::resolve_target(&query_value);
|
||||
|
||||
let mut rows = self.fetch_catalog(&options).await;
|
||||
rows.retain(|video| Self::matches_target(video, &target));
|
||||
rows.sort_by(|a, b| b.date.cmp(&a.date));
|
||||
if sort_value == "oldest" {
|
||||
rows.reverse();
|
||||
}
|
||||
|
||||
let start = (page_num - 1) * per_page_num;
|
||||
rows.into_iter()
|
||||
.skip(start)
|
||||
.take(per_page_num)
|
||||
.map(|video| self.build_item(&options, &video))
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn get_channel(&self, clientversion: ClientVersion) -> Option<Channel> {
|
||||
Some(self.build_channel(clientversion))
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user