pimpbunny

This commit is contained in:
Simon
2025-11-30 14:15:09 +00:00
parent 61e38caed5
commit 07b812be64
2 changed files with 557 additions and 0 deletions

View File

@@ -38,6 +38,7 @@ pub mod rule34gen;
pub mod xxdbx;
pub mod hqporner;
pub mod noodlemagazine;
pub mod pimpbunny;
// convenient alias
pub type DynProvider = Arc<dyn Provider>;
@@ -53,6 +54,7 @@ pub static ALL_PROVIDERS: Lazy<HashMap<&'static str, DynProvider>> = Lazy::new(|
m.insert("hqporner", Arc::new(hqporner::HqpornerProvider::new()) as DynProvider);
m.insert("pmvhaven", Arc::new(pmvhaven::PmvhavenProvider::new()) as DynProvider);
m.insert("noodlemagazine", Arc::new(noodlemagazine::NoodlemagazineProvider::new()) as DynProvider);
m.insert("pimpbunny", Arc::new(pimpbunny::PimpbunnyProvider::new()) as DynProvider);
// add more here as you migrate them
m
});

555
src/providers/pimpbunny.rs Normal file
View File

@@ -0,0 +1,555 @@
use crate::DbPool;
use crate::api::ClientVersion;
use crate::providers::Provider;
use crate::status::*;
use crate::util::cache::VideoCache;
use crate::util::requester::Requester;
use crate::util::time::parse_time_to_seconds;
use crate::videos::{ServerOptions, VideoFormat, VideoItem};
use async_trait::async_trait;
use error_chain::error_chain;
use futures::future::join_all;
use htmlentity::entity::{ICodedDataTrait, decode};
use std::sync::{Arc, RwLock};
use std::{thread, vec};
use titlecase::Titlecase;
use wreq::Version;
error_chain! {
foreign_links {
Io(std::io::Error);
HttpRequest(wreq::Error);
}
}
#[derive(Debug, Clone)]
pub struct PimpbunnyProvider {
url: String,
stars: Arc<RwLock<Vec<FilterOption>>>,
categories: Arc<RwLock<Vec<FilterOption>>>,
}
impl PimpbunnyProvider {
pub fn new() -> Self {
let provider = PimpbunnyProvider {
url: "https://pimpbunny.com".to_string(),
stars: Arc::new(RwLock::new(vec![])),
categories: Arc::new(RwLock::new(vec![])),
};
provider.spawn_initial_load();
provider
}
fn spawn_initial_load(&self) {
let url = self.url.clone();
let stars = Arc::clone(&self.stars);
let categories = Arc::clone(&self.categories);
thread::spawn(move || {
// Create a tiny runtime just for these async tasks
let rt = tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.expect("build tokio runtime");
rt.block_on(async move {
if let Err(e) = Self::load_stars(&url, stars).await {
eprintln!("load_stars failed: {e}");
}
if let Err(e) = Self::load_categories(&url, categories).await {
eprintln!("load_categories failed: {e}");
}
});
});
}
async fn load_stars(base_url: &str, stars: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
let mut requester = Requester::new();
let text = requester
.get(
format!("{}/onlyfans-models/?models_per_page=20", &base_url).as_str(),
Some(Version::HTTP_2),
)
.await
.unwrap();
let stars_div = text
.split("pb-list-models-block")
.collect::<Vec<&str>>()
.last()
.unwrap()
.split("pb-page-description")
.collect::<Vec<&str>>()[0];
for stars_element in stars_div
.split("<div class=\"col\">")
.collect::<Vec<&str>>()[1..]
.to_vec()
{
if stars_element.contains("pb-promoted-link") {
continue;
}
let star_id = stars_element
.split("href=\"https://pimpbunny.com/onlyfans-models/")
.collect::<Vec<&str>>()[1]
.split("/\"")
.collect::<Vec<&str>>()[0]
.to_string();
let star_name = stars_element
.split("<div class=\"pb-item-title-text\">")
.collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.to_string();
Self::push_unique(
&stars,
FilterOption {
id: star_id,
title: star_name,
},
);
}
return Ok(());
}
async fn load_categories(
base_url: &str,
categories: Arc<RwLock<Vec<FilterOption>>>,
) -> Result<()> {
let mut requester = Requester::new();
let text = requester
.get(
format!("{}/categories/?items_per_page=120", &base_url).as_str(),
Some(Version::HTTP_2),
)
.await
.unwrap();
let categories_div = text
.split("list_categories_categories_list_items")
.collect::<Vec<&str>>()
.last()
.unwrap()
.split("pb-pagination-wrapper")
.collect::<Vec<&str>>()[0];
for categories_element in categories_div
.split("<div class=\"col\">")
.collect::<Vec<&str>>()[1..]
.to_vec()
{
let category_id = categories_element
.split("href=\"https://pimpbunny.com/categories/")
.collect::<Vec<&str>>()[1]
.split("/\"")
.collect::<Vec<&str>>()[0]
.to_string();
let category_name = categories_element
.split("<div class=\"pb-item-title pb-heading-h3 title\">")
.collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.titlecase();
Self::push_unique(
&categories,
FilterOption {
id: category_id,
title: category_name,
},
);
}
return Ok(());
}
fn build_channel(&self, clientversion: ClientVersion) -> Channel {
let _ = clientversion;
Channel {
id: "pimpbunny".to_string(),
name: "Pimpbunny".to_string(),
description: "Watch Porn!".to_string(),
premium: false,
favicon: "https://www.google.com/s2/favicons?sz=64&domain=pimpbunny.com".to_string(),
status: "active".to_string(),
categories: self
.categories
.read()
.unwrap()
.iter()
.map(|c| c.title.clone())
.collect(),
options: vec![ChannelOption {
id: "sort".to_string(),
title: "Sort".to_string(),
description: "Sort the Videos".to_string(),
systemImage: "list.number".to_string(),
colorName: "blue".to_string(),
options: vec![
FilterOption {
id: "featured".into(),
title: "Featured".into(),
},
FilterOption {
id: "most recent".into(),
title: "Most Recent".into(),
},
FilterOption {
id: "most viewed".into(),
title: "Most Viewed".into(),
},
FilterOption {
id: "best rated".into(),
title: "Best Rated".into(),
},
],
multiSelect: false,
}],
nsfw: true,
cacheDuration: None,
}
}
// Push one item with minimal lock time and dedup by id
fn push_unique(target: &Arc<RwLock<Vec<FilterOption>>>, item: FilterOption) {
if let Ok(mut vec) = target.write() {
if !vec.iter().any(|x| x.id == item.id) {
vec.push(item);
// Optional: keep it sorted for nicer UX
// vec.sort_by(|a,b| a.title.cmp(&b.title));
}
}
}
async fn get(
&self,
cache: VideoCache,
page: u8,
sort: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let sort_string = match sort {
"best rated" => "&sort_by=rating",
"most viewed" => "&sort_by=video_viewed",
_ => "&sort_by=post_date",
};
let video_url = format!(
"{}/videos/{}/?videos_per_page=20{}",
self.url, page, sort_string
);
let old_items = match cache.get(&video_url) {
Some((time, items)) => {
if time.elapsed().unwrap_or_default().as_secs() < 60 * 5 {
println!("Cache hit for URL: {}", video_url);
return Ok(items.clone());
} else {
items.clone()
}
}
None => {
vec![]
}
};
let mut requester = options.requester.clone().unwrap();
let text = requester.get(&video_url, Some(Version::HTTP_2)).await.unwrap();
let video_items: Vec<VideoItem> = self
.get_video_items_from_html(text.clone(), &mut requester)
.await;
if !video_items.is_empty() {
cache.remove(&video_url);
cache.insert(video_url.clone(), video_items.clone());
} else {
return Ok(old_items);
}
Ok(video_items)
}
async fn query(
&self,
cache: VideoCache,
page: u8,
query: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let search_string = query.trim().to_string();
let mut video_url = format!(
"{}/search/{}/?mode=async&function=get_block&block_id=list_videos_videos_list_search_result&videos_per_page=20&from_videos={}",
self.url, search_string.replace(" ","-"), page
);
let sort_string = match options.sort.as_deref().unwrap_or("") {
"best rated" => "&sort_by=rating",
"most viewed" => "&sort_by=video_viewed",
_ => "&sort_by=post_date",
};
if let Some(star) = self
.stars
.read()
.unwrap()
.iter()
.find(|s| s.title.to_ascii_lowercase() == search_string.to_ascii_lowercase())
{
video_url = format!(
"{}/onlyfans-models/{}/{}/?videos_per_page=20{}",
self.url, star.id, page, sort_string
);
}
if let Some(cat) = self
.categories
.read()
.unwrap()
.iter()
.find(|c| c.title.to_ascii_lowercase() == search_string.to_ascii_lowercase())
{
video_url = format!(
"{}/categories/{}/{}/?videos_per_page=20{}",
self.url, cat.id, page, sort_string
);
}
// Check our Video Cache. If the result is younger than 1 hour, we return it.
let old_items = match cache.get(&video_url) {
Some((time, items)) => {
if time.elapsed().unwrap_or_default().as_secs() < 60 * 5 {
return Ok(items.clone());
} else {
let _ = cache.check().await;
return Ok(items.clone());
}
}
None => {
vec![]
}
};
let mut requester = options.requester.clone().unwrap();
let text = requester.get(&video_url, Some(Version::HTTP_2)).await.unwrap();
let video_items: Vec<VideoItem> = self
.get_video_items_from_html(text.clone(), &mut requester)
.await;
if !video_items.is_empty() {
cache.remove(&video_url);
cache.insert(video_url.clone(), video_items.clone());
} else {
return Ok(old_items);
}
Ok(video_items)
}
async fn get_video_items_from_html(
&self,
html: String,
requester: &mut Requester,
) -> Vec<VideoItem> {
if html.is_empty() || html.contains("404 Not Found") {
return vec![];
}
let raw_videos = html.split("pb-pagination-wrapper").collect::<Vec<&str>>()[0]
.split("pb-list-items")
.collect::<Vec<&str>>()[1]
.split("<div class=\"col\">")
.collect::<Vec<&str>>()[1..]
.to_vec();
let futures = raw_videos
.into_iter()
.map(|el| self.get_video_item(el.to_string(), requester.clone()));
let results: Vec<Result<VideoItem>> = join_all(futures).await;
let video_items: Vec<VideoItem> = results.into_iter().filter_map(Result::ok).collect();
return video_items;
}
async fn get_video_item(
&self,
video_segment: String,
mut requester: Requester,
) -> Result<VideoItem> {
let video_url: String = video_segment.split(" href=\"").collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.to_string();
let mut title = video_segment.split("pb-item-title").collect::<Vec<&str>>()[1]
.split(">")
.collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.trim()
.to_string();
// html decode
title = decode(title.as_bytes())
.to_string()
.unwrap_or(title)
.titlecase();
let id = video_url.split("/").collect::<Vec<&str>>()[4]
.split(".")
.collect::<Vec<&str>>()[0]
.to_string();
let mut thumb = video_segment.split("pb-thumbnail").collect::<Vec<&str>>()[1]
.split("src=\"")
.collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.to_string();
if thumb.starts_with("data:image/jpg;base64") {
thumb = video_segment.split("pb-thumbnail").collect::<Vec<&str>>()[1]
.split("data-webp=\"")
.collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.to_string();
}
let preview = video_segment.split("pb-thumbnail").collect::<Vec<&str>>()[1]
.split("data-preview=\"")
.collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.to_string();
let (tags, formats, views, duration) = match self.extract_media(&video_url, &mut requester).await {
Ok((t, f, v, d)) => (t, f, v, d),
Err(_) => return Err(Error::from("Video media extraction failed")),
};
if formats.is_empty() {
return Err(Error::from("No formats found for video"));
}
let video_item = VideoItem::new(
id,
title,
video_url,
"pimpbunny".to_string(),
thumb,
duration,
)
.formats(formats)
.tags(tags)
.preview(preview)
.views(views)
;
return Ok(video_item);
}
async fn extract_media(
&self,
video_page_url: &str,
requester: &mut Requester,
) -> Result<(Vec<String>, Vec<VideoFormat>, u32, u32)> {
let mut formats = vec![];
let mut tags = vec![];
let text = requester
.get(&video_page_url, Some(Version::HTTP_2))
.await
.unwrap();
if text.contains("pb-video-models"){
let stars_elements = text.split("pb-video-models").collect::<Vec<&str>>()[1]
.split("pb-video-statistic")
.collect::<Vec<&str>>()[0]
.split("pb-models-item pb-models-item")
.collect::<Vec<&str>>()[1..]
.to_vec();
for star_el in stars_elements {
let star_id = star_el
.split("href=\"https://pimpbunny.com/onlyfans-models/")
.collect::<Vec<&str>>()[1]
.split("/\"")
.collect::<Vec<&str>>()[0]
.to_string();
let star_name = star_el
.split("<span class=\"pb-item-title pb-heading-h3\">")
.collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.to_string();
tags.push(star_name.clone());
Self::push_unique(
&self.stars,
FilterOption {
id: star_id,
title: star_name.clone(),
},
);
}
}
if text.contains("pb-video-tags") {
let categories_elements = text.split("pb-tags-list").collect::<Vec<&str>>()[1]
.split("</div>")
.collect::<Vec<&str>>()[0]
.split("href=\"https://pimpbunny.com/tags/")
.collect::<Vec<&str>>()[1..]
.to_vec();
for categories_el in categories_elements {
let category_id = categories_el.split("\"").collect::<Vec<&str>>()[0].to_string();
let category_name = categories_el.split("\">").collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.titlecase();
tags.push(category_name.clone());
Self::push_unique(
&self.categories,
FilterOption {
id: category_id,
title: category_name.clone(),
},
);
}
}
let json_str = text
.split(";</script><script type=\"application/ld+json\">")
.collect::<Vec<&str>>()[1]
.split("</script>")
.collect::<Vec<&str>>()[0];
let json = serde_json::from_str::<serde_json::Value>(json_str).unwrap_or_default();
let video_url = json["contentUrl"].as_str().unwrap_or("").to_string();
let quality = video_url
.split("_")
.collect::<Vec<&str>>()
.last()
.map_or("", |v| v)
.split(".")
.collect::<Vec<&str>>()[0]
.to_string();
let views = json["interactionStatistic"].as_array().unwrap()[0]["userInteractionCount"]
.as_str().unwrap().parse::<u32>().unwrap_or(0);
let raw_duration = json["duration"].as_str().unwrap_or("00:00").replace("PT", "").replace("H", ":").replace("M", ":").replace("S", "");
let duration = parse_time_to_seconds(raw_duration.as_str()).unwrap_or(0) as u32;
formats.push(VideoFormat::new(
video_url,
quality.clone(),
"video/mp4".to_string(),
));
Ok((tags, formats, views, duration))
}
}
#[async_trait]
impl Provider for PimpbunnyProvider {
async fn get_videos(
&self,
cache: VideoCache,
pool: DbPool,
sort: String,
query: Option<String>,
page: String,
per_page: String,
options: ServerOptions,
) -> Vec<VideoItem> {
let _ = per_page;
let _ = pool;
let videos: std::result::Result<Vec<VideoItem>, Error> = match query {
Some(q) => {
self.query(cache, page.parse::<u8>().unwrap_or(1), &q, options)
.await
}
None => {
self.get(cache, page.parse::<u8>().unwrap_or(1), &sort, options)
.await
}
};
match videos {
Ok(v) => v,
Err(e) => {
println!("Error fetching videos: {}", e);
vec![]
}
}
}
fn get_channel(&self, clientversion: ClientVersion) -> crate::status::Channel {
self.build_channel(clientversion)
}
}