1082 lines
36 KiB
Rust
1082 lines
36 KiB
Rust
use crate::DbPool;
|
|
use crate::api::ClientVersion;
|
|
use crate::providers::Provider;
|
|
use crate::status::*;
|
|
use crate::util::parse_abbreviated_number;
|
|
use crate::util::cache::VideoCache;
|
|
use crate::util::discord::{format_error_chain, send_discord_error_report};
|
|
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 htmlentity::entity::{ICodedDataTrait, decode};
|
|
use std::sync::{Arc, RwLock};
|
|
use std::{thread, vec};
|
|
use titlecase::Titlecase;
|
|
use url::Url;
|
|
use wreq::Version;
|
|
|
|
pub const CHANNEL_METADATA: crate::providers::ProviderChannelMetadata =
|
|
crate::providers::ProviderChannelMetadata {
|
|
group_id: "onlyfans",
|
|
tags: &["creator", "onlyfans", "amateur"],
|
|
};
|
|
|
|
error_chain! {
|
|
foreign_links {
|
|
Io(std::io::Error);
|
|
HttpRequest(wreq::Error);
|
|
Json(serde_json::Error);
|
|
}
|
|
errors {
|
|
Parse(msg: String) {
|
|
description("parse error")
|
|
display("parse error: {}", msg)
|
|
}
|
|
}
|
|
}
|
|
|
|
#[derive(Debug, Clone)]
|
|
pub struct PimpbunnyProvider {
|
|
url: String,
|
|
stars: Arc<RwLock<Vec<FilterOption>>>,
|
|
categories: Arc<RwLock<Vec<FilterOption>>>,
|
|
}
|
|
|
|
impl PimpbunnyProvider {
|
|
const FIREFOX_USER_AGENT: &'static str =
|
|
"Mozilla/5.0 (X11; Linux x86_64; rv:147.0) Gecko/20100101 Firefox/147.0";
|
|
const HTML_ACCEPT: &'static str =
|
|
"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8";
|
|
pub fn new() -> Self {
|
|
let provider = Self {
|
|
url: "https://pimpbunny.com".to_string(),
|
|
stars: Arc::new(RwLock::new(vec![])),
|
|
categories: Arc::new(RwLock::new(vec![])),
|
|
};
|
|
provider.spawn_initial_load();
|
|
provider
|
|
}
|
|
|
|
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()
|
|
.map(|categories| categories.iter().map(|c| c.title.clone()).collect())
|
|
.unwrap_or_else(|e| {
|
|
crate::providers::report_provider_error_background(
|
|
"pimpbunny",
|
|
"build_channel.categories_read",
|
|
&e.to_string(),
|
|
);
|
|
vec![]
|
|
}),
|
|
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,
|
|
}
|
|
}
|
|
|
|
fn spawn_initial_load(&self) {
|
|
let url = self.url.clone();
|
|
let stars = Arc::clone(&self.stars);
|
|
let categories = Arc::clone(&self.categories);
|
|
|
|
thread::spawn(async move || {
|
|
let rt = match tokio::runtime::Builder::new_current_thread()
|
|
.enable_all()
|
|
.build()
|
|
{
|
|
Ok(rt) => rt,
|
|
Err(e) => {
|
|
eprintln!("tokio runtime failed: {e}");
|
|
send_discord_error_report(
|
|
e.to_string(),
|
|
Some(format_error_chain(&e)),
|
|
Some("Pimpbunny Provider"),
|
|
Some("Failed to create tokio runtime"),
|
|
file!(),
|
|
line!(),
|
|
module_path!(),
|
|
)
|
|
.await;
|
|
return;
|
|
}
|
|
};
|
|
|
|
rt.block_on(async {
|
|
if let Err(e) = Self::load_stars(&url, Arc::clone(&stars)).await {
|
|
eprintln!("load_stars failed: {e}");
|
|
send_discord_error_report(
|
|
e.to_string(),
|
|
Some(format_error_chain(&e)),
|
|
Some("Pimpbunny Provider"),
|
|
Some("Failed to load stars during initial load"),
|
|
file!(),
|
|
line!(),
|
|
module_path!(),
|
|
)
|
|
.await;
|
|
}
|
|
if let Err(e) = Self::load_categories(&url, Arc::clone(&categories)).await {
|
|
eprintln!("load_categories failed: {e}");
|
|
send_discord_error_report(
|
|
e.to_string(),
|
|
Some(format_error_chain(&e)),
|
|
Some("Pimpbunny Provider"),
|
|
Some("Failed to load categories during initial load"),
|
|
file!(),
|
|
line!(),
|
|
module_path!(),
|
|
)
|
|
.await;
|
|
}
|
|
});
|
|
});
|
|
}
|
|
|
|
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);
|
|
}
|
|
}
|
|
}
|
|
|
|
fn is_allowed_thumb_url(url: &str) -> bool {
|
|
let Some(url) = Url::parse(url).ok() else {
|
|
return false;
|
|
};
|
|
if url.scheme() != "https" {
|
|
return false;
|
|
}
|
|
let Some(host) = url.host_str() else {
|
|
return false;
|
|
};
|
|
matches!(host, "pimpbunny.com" | "www.pimpbunny.com")
|
|
&& url.path().starts_with("/contents/videos_screenshots/")
|
|
}
|
|
|
|
fn proxied_thumb(&self, options: &ServerOptions, thumb: &str) -> String {
|
|
if thumb.is_empty() || !Self::is_allowed_thumb_url(thumb) {
|
|
return thumb.to_string();
|
|
}
|
|
|
|
crate::providers::build_proxy_url(
|
|
options,
|
|
"pimpbunny-thumb",
|
|
&crate::providers::strip_url_scheme(thumb),
|
|
)
|
|
}
|
|
|
|
fn is_allowed_detail_url(url: &str) -> bool {
|
|
let Some(url) = Url::parse(url).ok() else {
|
|
return false;
|
|
};
|
|
if url.scheme() != "https" {
|
|
return false;
|
|
}
|
|
let Some(host) = url.host_str() else {
|
|
return false;
|
|
};
|
|
matches!(host, "pimpbunny.com" | "www.pimpbunny.com")
|
|
&& !url.path().starts_with("/contents/videos_screenshots/")
|
|
}
|
|
|
|
fn proxied_video(&self, options: &ServerOptions, page_url: &str) -> String {
|
|
if page_url.is_empty() || !Self::is_allowed_detail_url(page_url) {
|
|
return page_url.to_string();
|
|
}
|
|
|
|
crate::providers::build_proxy_url(
|
|
options,
|
|
"pimpbunny",
|
|
&crate::providers::strip_url_scheme(page_url),
|
|
)
|
|
}
|
|
|
|
fn root_referer(&self) -> String {
|
|
format!("{}/", self.url.trim_end_matches('/'))
|
|
}
|
|
|
|
fn sort_by(sort: &str) -> &'static str {
|
|
match sort {
|
|
"best rated" => "rating",
|
|
"most viewed" => "video_viewed",
|
|
_ => "post_date",
|
|
}
|
|
}
|
|
|
|
fn build_search_path_query(query: &str, separator: &str) -> String {
|
|
query.split_whitespace().collect::<Vec<_>>().join(separator)
|
|
}
|
|
|
|
fn append_archive_query(url: String, sort: &str) -> String {
|
|
let separator = if url.contains('?') { '&' } else { '?' };
|
|
format!("{url}{separator}sort_by={}", Self::sort_by(sort))
|
|
}
|
|
|
|
fn page_family_referer(&self, request_url: &str) -> String {
|
|
let Some(url) = Url::parse(request_url).ok() else {
|
|
return self.root_referer();
|
|
};
|
|
|
|
let path = url.path();
|
|
let referer_path = if path.starts_with("/videos/") {
|
|
"/videos/".to_string()
|
|
} else if path.starts_with("/search/") {
|
|
let parts: Vec<_> = path.trim_matches('/').split('/').collect();
|
|
if parts.len() >= 2 {
|
|
format!("/search/{}/", parts[1])
|
|
} else {
|
|
"/search/".to_string()
|
|
}
|
|
} else if path.starts_with("/categories/") {
|
|
let parts: Vec<_> = path.trim_matches('/').split('/').collect();
|
|
if parts.len() >= 2 {
|
|
format!("/categories/{}/", parts[1])
|
|
} else {
|
|
"/categories/".to_string()
|
|
}
|
|
} else if path.starts_with("/onlyfans-models/") {
|
|
let parts: Vec<_> = path.trim_matches('/').split('/').collect();
|
|
if parts.len() >= 2 {
|
|
format!("/onlyfans-models/{}/", parts[1])
|
|
} else {
|
|
"/onlyfans-models/".to_string()
|
|
}
|
|
} else {
|
|
"/".to_string()
|
|
};
|
|
|
|
format!("{}{}", self.url.trim_end_matches('/'), referer_path)
|
|
}
|
|
|
|
fn build_browse_url(&self, page: u8, sort: &str) -> String {
|
|
let base = if page <= 1 {
|
|
format!("{}/videos/", self.url)
|
|
} else {
|
|
format!("{}/videos/{page}/", self.url)
|
|
};
|
|
Self::append_archive_query(base, sort)
|
|
}
|
|
|
|
fn build_search_url(&self, query: &str, page: u8, sort: &str) -> String {
|
|
let path_query = Self::build_search_path_query(query, "-");
|
|
let base = if page <= 1 {
|
|
format!("{}/search/{path_query}/", self.url)
|
|
} else {
|
|
format!("{}/search/{path_query}/{page}/", self.url)
|
|
};
|
|
Self::append_archive_query(base, sort)
|
|
}
|
|
|
|
fn build_common_archive_url(&self, archive_path: &str, page: u8, sort: &str) -> String {
|
|
let canonical = format!(
|
|
"{}/{}",
|
|
self.url.trim_end_matches('/'),
|
|
archive_path.trim_start_matches('/')
|
|
);
|
|
let base = if page <= 1 {
|
|
canonical
|
|
} else {
|
|
format!("{}/{}", canonical.trim_end_matches('/'), page)
|
|
};
|
|
let base = if base.ends_with('/') {
|
|
base
|
|
} else {
|
|
format!("{base}/")
|
|
};
|
|
Self::append_archive_query(base, sort)
|
|
}
|
|
|
|
fn navigation_headers(
|
|
referer: Option<&str>,
|
|
sec_fetch_site: &'static str,
|
|
) -> Vec<(String, String)> {
|
|
let mut headers = vec![
|
|
(
|
|
"User-Agent".to_string(),
|
|
Self::FIREFOX_USER_AGENT.to_string(),
|
|
),
|
|
("Accept".to_string(), Self::HTML_ACCEPT.to_string()),
|
|
("Accept-Language".to_string(), "en-US,en;q=0.9".to_string()),
|
|
("Cache-Control".to_string(), "no-cache".to_string()),
|
|
("Pragma".to_string(), "no-cache".to_string()),
|
|
("Priority".to_string(), "u=0, i".to_string()),
|
|
("Connection".to_string(), "keep-alive".to_string()),
|
|
("TE".to_string(), "trailers".to_string()),
|
|
("Sec-Fetch-Dest".to_string(), "document".to_string()),
|
|
("Sec-Fetch-Mode".to_string(), "navigate".to_string()),
|
|
("Sec-Fetch-Site".to_string(), sec_fetch_site.to_string()),
|
|
("Sec-Fetch-User".to_string(), "?1".to_string()),
|
|
("Upgrade-Insecure-Requests".to_string(), "1".to_string()),
|
|
];
|
|
if let Some(referer) = referer {
|
|
headers.push(("Referer".to_string(), referer.to_string()));
|
|
}
|
|
headers
|
|
}
|
|
|
|
fn headers_with_cookies(
|
|
&self,
|
|
requester: &Requester,
|
|
request_url: &str,
|
|
referer: Option<&str>,
|
|
sec_fetch_site: &'static str,
|
|
) -> Vec<(String, String)> {
|
|
let mut headers = Self::navigation_headers(referer, sec_fetch_site);
|
|
if let Some(cookie) = requester.cookie_header_for_url(request_url) {
|
|
headers.push(("Cookie".to_string(), cookie));
|
|
}
|
|
headers
|
|
}
|
|
|
|
fn is_cloudflare_challenge(html: &str) -> bool {
|
|
html.contains("cf-turnstile-response")
|
|
|| html.contains("Performing security verification")
|
|
|| html.contains("__cf_chl_rt_tk")
|
|
|| html.contains("cUPMDTk:\"")
|
|
|| html.contains("Just a moment...")
|
|
}
|
|
|
|
fn extract_challenge_path(html: &str) -> Option<String> {
|
|
html.split("cUPMDTk:\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.map(str::to_string)
|
|
.or_else(|| {
|
|
html.split("__cf_chl_rt_tk=")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.map(|token| format!("/?__cf_chl_rt_tk={token}"))
|
|
})
|
|
}
|
|
|
|
fn absolute_site_url(&self, path_or_url: &str) -> String {
|
|
if path_or_url.starts_with("http://") || path_or_url.starts_with("https://") {
|
|
path_or_url.to_string()
|
|
} else {
|
|
format!(
|
|
"{}/{}",
|
|
self.url.trim_end_matches('/'),
|
|
path_or_url.trim_start_matches('/')
|
|
)
|
|
}
|
|
}
|
|
|
|
async fn fetch_html(
|
|
&self,
|
|
requester: &mut Requester,
|
|
request_url: &str,
|
|
referer: Option<&str>,
|
|
sec_fetch_site: &'static str,
|
|
) -> Result<String> {
|
|
let headers = self.headers_with_cookies(requester, request_url, referer, sec_fetch_site);
|
|
let response = requester
|
|
.get_raw_with_headers(request_url, headers.clone())
|
|
.await
|
|
.map_err(Error::from)?;
|
|
let status = response.status();
|
|
let body = response.text().await.map_err(Error::from)?;
|
|
|
|
if status.is_success() || status.as_u16() == 404 {
|
|
return Ok(body);
|
|
}
|
|
|
|
if status.as_u16() == 403 && Self::is_cloudflare_challenge(&body) {
|
|
if let Some(challenge_path) = Self::extract_challenge_path(&body) {
|
|
let challenge_url = self.absolute_site_url(&challenge_path);
|
|
let challenge_headers = self.headers_with_cookies(
|
|
requester,
|
|
&challenge_url,
|
|
Some(request_url),
|
|
"same-origin",
|
|
);
|
|
let _ = requester
|
|
.get_raw_with_headers(&challenge_url, challenge_headers)
|
|
.await;
|
|
}
|
|
}
|
|
|
|
let retry_headers =
|
|
self.headers_with_cookies(requester, request_url, referer, sec_fetch_site);
|
|
requester
|
|
.get_with_headers(request_url, retry_headers, Some(Version::HTTP_11))
|
|
.await
|
|
.map_err(|e| Error::from(format!("{e}")))
|
|
}
|
|
|
|
async fn warm_root_session(&self, requester: &mut Requester) {
|
|
let root_url = self.root_referer();
|
|
let _ = self
|
|
.fetch_html(requester, &root_url, None, "none")
|
|
.await;
|
|
}
|
|
|
|
async fn warm_root_session_for_base(base: &str, requester: &mut Requester) {
|
|
let root_url = format!("{}/", base.trim_end_matches('/'));
|
|
let _ = requester
|
|
.get_with_headers(
|
|
&root_url,
|
|
Self::navigation_headers(None, "none"),
|
|
Some(Version::HTTP_11),
|
|
)
|
|
.await;
|
|
}
|
|
|
|
async fn load_stars(base: &str, stars: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
|
|
let mut requester = Requester::new();
|
|
Self::warm_root_session_for_base(base, &mut requester).await;
|
|
let request_url = format!("{base}/onlyfans-models/?models_per_page=20");
|
|
let headers = {
|
|
let root_url = format!("{}/", base.trim_end_matches('/'));
|
|
let mut headers = Self::navigation_headers(Some(&root_url), "same-origin");
|
|
if let Some(cookie) = requester.cookie_header_for_url(&request_url) {
|
|
headers.push(("Cookie".to_string(), cookie));
|
|
}
|
|
headers
|
|
};
|
|
let text = requester
|
|
.get_with_headers(
|
|
&request_url,
|
|
headers,
|
|
Some(Version::HTTP_2),
|
|
)
|
|
.await
|
|
.map_err(|e| Error::from(format!("{}", e)))?;
|
|
|
|
let block = text
|
|
.split("vt_list_models_with_advertising_custom_models_list_items")
|
|
.last()
|
|
.ok_or_else(|| ErrorKind::Parse("missing stars block".into()))?
|
|
.split("pb-page-description")
|
|
.next()
|
|
.unwrap_or("");
|
|
|
|
for el in block.split("<div class=\"col\">").skip(1) {
|
|
if el.contains("pb-promoted-link")
|
|
|| !el.contains("href=\"https://pimpbunny.com/onlyfans-models/")
|
|
{
|
|
continue;
|
|
}
|
|
|
|
let id = el
|
|
.split("href=\"https://pimpbunny.com/onlyfans-models/")
|
|
.nth(1)
|
|
.and_then(|s| s.split("/\"").next())
|
|
.ok_or_else(|| ErrorKind::Parse(format!("star id: {el}").into()))?
|
|
.to_string();
|
|
|
|
let title = el
|
|
.split("ui-card-title")
|
|
.nth(1)
|
|
.and_then(|s| s.split('<').next())
|
|
.ok_or_else(|| ErrorKind::Parse(format!("star title: {el}").into()))?
|
|
.to_string();
|
|
|
|
Self::push_unique(&stars, FilterOption { id, title });
|
|
}
|
|
Ok(())
|
|
}
|
|
|
|
async fn load_categories(base: &str, cats: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
|
|
let mut requester = Requester::new();
|
|
Self::warm_root_session_for_base(base, &mut requester).await;
|
|
let request_url = format!("{base}/categories/?items_per_page=120");
|
|
let headers = {
|
|
let root_url = format!("{}/", base.trim_end_matches('/'));
|
|
let mut headers = Self::navigation_headers(Some(&root_url), "same-origin");
|
|
if let Some(cookie) = requester.cookie_header_for_url(&request_url) {
|
|
headers.push(("Cookie".to_string(), cookie));
|
|
}
|
|
headers
|
|
};
|
|
let text = requester
|
|
.get_with_headers(
|
|
&request_url,
|
|
headers,
|
|
Some(Version::HTTP_2),
|
|
)
|
|
.await
|
|
.map_err(|e| Error::from(format!("{}", e)))?;
|
|
|
|
let block = text
|
|
.split("list_categories_categories_list_items")
|
|
.last()
|
|
.ok_or_else(|| ErrorKind::Parse("categories block".into()))?
|
|
.split("pb-pagination-wrapper")
|
|
.next()
|
|
.unwrap_or("");
|
|
|
|
for el in block.split("<div class=\"col\">").skip(1) {
|
|
let id = el
|
|
.split("href=\"https://pimpbunny.com/categories/")
|
|
.nth(1)
|
|
.and_then(|s| s.split("/\"").next())
|
|
.ok_or_else(|| ErrorKind::Parse(format!("category id: {el}").into()))?
|
|
.to_string();
|
|
|
|
let title = el
|
|
.split("ui-heading-h3")
|
|
.nth(1)
|
|
.and_then(|s| s.split('<').next())
|
|
.ok_or_else(|| ErrorKind::Parse(format!("category title: {el}").into()))?
|
|
.titlecase();
|
|
|
|
Self::push_unique(&cats, FilterOption { id, title });
|
|
}
|
|
Ok(())
|
|
}
|
|
|
|
async fn get(
|
|
&self,
|
|
cache: VideoCache,
|
|
page: u8,
|
|
sort: &str,
|
|
options: ServerOptions,
|
|
) -> Result<Vec<VideoItem>> {
|
|
let video_url = self.build_browse_url(page, sort);
|
|
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 {
|
|
items.clone()
|
|
}
|
|
}
|
|
None => {
|
|
vec![]
|
|
}
|
|
};
|
|
let mut requester =
|
|
crate::providers::requester_or_default(&options, module_path!(), "missing_requester");
|
|
self.warm_root_session(&mut requester).await;
|
|
let referer = self.page_family_referer(&video_url);
|
|
let text = match self
|
|
.fetch_html(
|
|
&mut requester,
|
|
&video_url,
|
|
Some(&referer),
|
|
"same-origin",
|
|
)
|
|
.await
|
|
{
|
|
Ok(text) => text,
|
|
Err(e) => {
|
|
crate::providers::report_provider_error(
|
|
"pimpbunny",
|
|
"get.request",
|
|
&format!("url={video_url}; error={e}"),
|
|
)
|
|
.await;
|
|
return Ok(old_items);
|
|
}
|
|
};
|
|
let video_items = self.get_video_items_from_html(text.clone(), &options);
|
|
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 sort = options.sort.as_deref().unwrap_or("");
|
|
let mut video_url = self.build_search_url(&search_string, page, sort);
|
|
if let Ok(stars) = self.stars.read() {
|
|
if let Some(star) = stars
|
|
.iter()
|
|
.find(|s| s.title.to_ascii_lowercase() == search_string.to_ascii_lowercase())
|
|
{
|
|
video_url = self.build_common_archive_url(
|
|
&format!("/onlyfans-models/{}/", star.id),
|
|
page,
|
|
sort,
|
|
);
|
|
}
|
|
} else {
|
|
crate::providers::report_provider_error_background(
|
|
"pimpbunny",
|
|
"query.stars_read",
|
|
"failed to lock stars",
|
|
);
|
|
}
|
|
if let Ok(categories) = self.categories.read() {
|
|
if let Some(cat) = categories
|
|
.iter()
|
|
.find(|c| c.title.to_ascii_lowercase() == search_string.to_ascii_lowercase())
|
|
{
|
|
video_url =
|
|
self.build_common_archive_url(&format!("/categories/{}/", cat.id), page, sort);
|
|
}
|
|
} else {
|
|
crate::providers::report_provider_error_background(
|
|
"pimpbunny",
|
|
"query.categories_read",
|
|
"failed to lock categories",
|
|
);
|
|
}
|
|
// 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 =
|
|
crate::providers::requester_or_default(&options, module_path!(), "missing_requester");
|
|
self.warm_root_session(&mut requester).await;
|
|
let referer = self.page_family_referer(&video_url);
|
|
let text = match self
|
|
.fetch_html(
|
|
&mut requester,
|
|
&video_url,
|
|
Some(&referer),
|
|
"same-origin",
|
|
)
|
|
.await
|
|
{
|
|
Ok(text) => text,
|
|
Err(e) => {
|
|
crate::providers::report_provider_error(
|
|
"pimpbunny",
|
|
"query.request",
|
|
&format!("url={video_url}; error={e}"),
|
|
)
|
|
.await;
|
|
return Ok(old_items);
|
|
}
|
|
};
|
|
let video_items = self.get_video_items_from_html(text.clone(), &options);
|
|
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)
|
|
}
|
|
|
|
fn get_video_items_from_html(&self, html: String, options: &ServerOptions) -> Vec<VideoItem> {
|
|
if html.is_empty() || html.contains("404 Not Found") {
|
|
return vec![];
|
|
}
|
|
|
|
let block = match html
|
|
.split("-pagination-wrapper")
|
|
.next()
|
|
.and_then(|s| s.split("videos_videos_list").nth(2))
|
|
{
|
|
Some(b) => b,
|
|
None => return vec![],
|
|
};
|
|
|
|
block
|
|
.split("<div class=\"col\">")
|
|
.skip(1)
|
|
.filter_map(|el| self.get_video_item(el.to_string(), options).ok())
|
|
.into_iter()
|
|
.collect()
|
|
}
|
|
|
|
fn extract_duration_from_segment(&self, seg: &str) -> u32 {
|
|
for token in seg.split(|ch: char| ch == '<' || ch == '>' || ch.is_whitespace()) {
|
|
let candidate = token.trim();
|
|
if candidate.is_empty() || !candidate.contains(':') {
|
|
continue;
|
|
}
|
|
if let Some(parsed) = parse_time_to_seconds(candidate) {
|
|
return parsed as u32;
|
|
}
|
|
}
|
|
0
|
|
}
|
|
|
|
fn extract_views_from_segment(&self, seg: &str) -> u32 {
|
|
let Some(before_views) = seg.split("Views").next() else {
|
|
return 0;
|
|
};
|
|
let candidate = before_views
|
|
.split(|ch: char| ch == '<' || ch == '>' || ch.is_whitespace())
|
|
.filter(|value| !value.trim().is_empty())
|
|
.next_back()
|
|
.unwrap_or("")
|
|
.trim_matches(|ch: char| ch == '(' || ch == ')' || ch == ',');
|
|
|
|
parse_abbreviated_number(candidate).unwrap_or(0)
|
|
}
|
|
|
|
fn get_video_item(&self, seg: String, options: &ServerOptions) -> Result<VideoItem> {
|
|
let video_url = seg
|
|
.split(" href=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.ok_or_else(|| ErrorKind::Parse("video url".into()))?
|
|
.to_string();
|
|
|
|
let mut title = seg
|
|
.split("card-title")
|
|
.nth(1)
|
|
.and_then(|s| s.split('>').nth(1))
|
|
.and_then(|s| s.split('<').next())
|
|
.ok_or_else(|| ErrorKind::Parse("video title".into()))?
|
|
.trim()
|
|
.to_string();
|
|
title = decode(title.as_bytes())
|
|
.to_string()
|
|
.unwrap_or(title)
|
|
.titlecase();
|
|
|
|
let id = video_url
|
|
.split('/')
|
|
.nth(4)
|
|
.and_then(|s| s.split('.').next())
|
|
.ok_or_else(|| ErrorKind::Parse("video id".into()))?
|
|
.to_string();
|
|
|
|
let thumb_block = seg
|
|
.split("card-thumbnail")
|
|
.nth(1)
|
|
.ok_or_else(|| ErrorKind::Parse("thumb block".into()))?;
|
|
|
|
let mut thumb = thumb_block
|
|
.split("src=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or("")
|
|
.to_string();
|
|
|
|
if thumb.contains("data:image/jpg;base64") {
|
|
thumb = thumb_block
|
|
.split("data-original=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or("")
|
|
.to_string();
|
|
}
|
|
|
|
let preview = thumb_block
|
|
.split("data-preview=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or("")
|
|
.to_string();
|
|
let proxy_url = self.proxied_video(options, &video_url);
|
|
let views = self.extract_views_from_segment(&seg);
|
|
let duration = self.extract_duration_from_segment(&seg);
|
|
let formats = vec![
|
|
VideoFormat::new(proxy_url.clone(), "auto".into(), "video/mp4".into())
|
|
.format_id("auto".into())
|
|
.format_note("proxied".into()),
|
|
];
|
|
|
|
Ok(
|
|
VideoItem::new(id, title, proxy_url, "pimpbunny".into(), thumb, duration)
|
|
.formats(formats)
|
|
.preview(preview)
|
|
.views(views),
|
|
)
|
|
}
|
|
}
|
|
|
|
#[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 page = page.parse::<u8>().unwrap_or(1);
|
|
let thumb_options = options.clone();
|
|
|
|
let res = match query {
|
|
Some(q) => self.to_owned().query(cache, page, &q, options).await,
|
|
None => self.get(cache, page, &sort, options).await,
|
|
};
|
|
|
|
res.unwrap_or_else(|e| {
|
|
eprintln!("pimpbunny error: {e}");
|
|
vec![]
|
|
})
|
|
.into_iter()
|
|
.map(|mut item| {
|
|
if !item.thumb.is_empty() {
|
|
item.thumb = self.proxied_thumb(&thumb_options, &item.thumb);
|
|
}
|
|
item
|
|
})
|
|
.collect()
|
|
}
|
|
|
|
fn get_channel(&self, v: ClientVersion) -> Option<Channel> {
|
|
Some(self.build_channel(v))
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::PimpbunnyProvider;
|
|
use crate::videos::ServerOptions;
|
|
use std::sync::{Arc, RwLock};
|
|
|
|
fn test_provider() -> PimpbunnyProvider {
|
|
PimpbunnyProvider {
|
|
url: "https://pimpbunny.com".to_string(),
|
|
stars: Arc::new(RwLock::new(vec![])),
|
|
categories: Arc::new(RwLock::new(vec![])),
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn rewrites_allowed_thumbs_to_proxy_urls() {
|
|
let provider = test_provider();
|
|
let options = ServerOptions {
|
|
featured: None,
|
|
category: None,
|
|
sites: None,
|
|
filter: None,
|
|
language: None,
|
|
public_url_base: Some("https://example.com".to_string()),
|
|
requester: None,
|
|
network: None,
|
|
stars: None,
|
|
categories: None,
|
|
duration: None,
|
|
sort: None,
|
|
sexuality: None,
|
|
};
|
|
|
|
let proxied = provider.proxied_thumb(
|
|
&options,
|
|
"https://pimpbunny.com/contents/videos_screenshots/517000/517329/800x450/1.jpg",
|
|
);
|
|
|
|
assert_eq!(
|
|
proxied,
|
|
"https://example.com/proxy/pimpbunny-thumb/pimpbunny.com/contents/videos_screenshots/517000/517329/800x450/1.jpg"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn rewrites_video_pages_to_redirect_proxy() {
|
|
let provider = test_provider();
|
|
let options = ServerOptions {
|
|
featured: None,
|
|
category: None,
|
|
sites: None,
|
|
filter: None,
|
|
language: None,
|
|
public_url_base: Some("https://example.com".to_string()),
|
|
requester: None,
|
|
network: None,
|
|
stars: None,
|
|
categories: None,
|
|
duration: None,
|
|
sort: None,
|
|
sexuality: None,
|
|
};
|
|
|
|
let proxied = provider.proxied_video(
|
|
&options,
|
|
"https://pimpbunny.com/videos/example-video/",
|
|
);
|
|
|
|
assert_eq!(
|
|
proxied,
|
|
"https://example.com/proxy/pimpbunny/pimpbunny.com/videos/example-video/"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn parses_listing_without_detail_requests() {
|
|
let provider = test_provider();
|
|
let options = ServerOptions {
|
|
featured: None,
|
|
category: None,
|
|
sites: None,
|
|
filter: None,
|
|
language: None,
|
|
public_url_base: Some("https://example.com".to_string()),
|
|
requester: None,
|
|
network: None,
|
|
stars: None,
|
|
categories: None,
|
|
duration: None,
|
|
sort: None,
|
|
sexuality: None,
|
|
};
|
|
|
|
let html = r#"
|
|
<div class="videos_videos_list"></div>
|
|
<div class="videos_videos_list">
|
|
<div class="col">
|
|
<a href="https://pimpbunny.com/videos/example-video/">
|
|
<div class="card-thumbnail">
|
|
<img src="https://pimpbunny.com/contents/videos_screenshots/517000/517329/800x450/1.jpg" data-preview="https://pimpbunny.com/preview.mp4" />
|
|
</div>
|
|
<div class="card-title">sample & title</div>
|
|
<div>12:34</div>
|
|
<div>1.2K Views</div>
|
|
</a>
|
|
</div>
|
|
-pagination-wrapper
|
|
"#;
|
|
|
|
let items = provider.get_video_items_from_html(html.to_string(), &options);
|
|
|
|
assert_eq!(items.len(), 1);
|
|
assert_eq!(
|
|
items[0].url,
|
|
"https://example.com/proxy/pimpbunny/pimpbunny.com/videos/example-video/"
|
|
);
|
|
assert_eq!(items[0].duration, 754);
|
|
assert_eq!(items[0].views, Some(1200));
|
|
assert_eq!(items[0].formats.as_ref().map(|f| f.len()), Some(1));
|
|
}
|
|
|
|
#[test]
|
|
fn extracts_cloudflare_challenge_path() {
|
|
let html = r#"
|
|
<script type="text/javascript">
|
|
(function(){
|
|
window._cf_chl_opt = {
|
|
cUPMDTk:"/?mode=async&function=get_block&block_id=videos_videos_list&videos_per_page=8&sort_by=post_date&from=1&__cf_chl_tk=test-token"
|
|
};
|
|
}());
|
|
</script>
|
|
"#;
|
|
|
|
assert!(PimpbunnyProvider::is_cloudflare_challenge(html));
|
|
assert_eq!(
|
|
PimpbunnyProvider::extract_challenge_path(html).as_deref(),
|
|
Some(
|
|
"/?mode=async&function=get_block&block_id=videos_videos_list&videos_per_page=8&sort_by=post_date&from=1&__cf_chl_tk=test-token"
|
|
)
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn builds_async_browse_url_instead_of_numbered_videos_path() {
|
|
let provider = test_provider();
|
|
assert_eq!(
|
|
provider.build_browse_url(1, "most recent"),
|
|
"https://pimpbunny.com/videos/?sort_by=post_date"
|
|
);
|
|
assert_eq!(
|
|
provider.build_browse_url(2, "most recent"),
|
|
"https://pimpbunny.com/videos/2/?sort_by=post_date"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn builds_search_url_with_query_and_pagination() {
|
|
let provider = test_provider();
|
|
assert_eq!(
|
|
provider.build_search_url("adriana chechik", 1, "most viewed"),
|
|
"https://pimpbunny.com/search/adriana-chechik/?sort_by=video_viewed"
|
|
);
|
|
assert_eq!(
|
|
provider.build_search_url("adriana chechik", 3, "most viewed"),
|
|
"https://pimpbunny.com/search/adriana-chechik/3/?sort_by=video_viewed"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn builds_common_archive_url_with_async_block() {
|
|
let provider = test_provider();
|
|
assert_eq!(
|
|
provider.build_common_archive_url("/categories/amateur/", 1, "best rated"),
|
|
"https://pimpbunny.com/categories/amateur/?sort_by=rating"
|
|
);
|
|
assert_eq!(
|
|
provider.build_common_archive_url("/categories/amateur/", 4, "best rated"),
|
|
"https://pimpbunny.com/categories/amateur/4/?sort_by=rating"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn derives_page_family_referer() {
|
|
let provider = test_provider();
|
|
assert_eq!(
|
|
provider.page_family_referer("https://pimpbunny.com/videos/2/?sort_by=post_date"),
|
|
"https://pimpbunny.com/videos/"
|
|
);
|
|
assert_eq!(
|
|
provider.page_family_referer(
|
|
"https://pimpbunny.com/categories/blowjob/2/?sort_by=post_date"
|
|
),
|
|
"https://pimpbunny.com/categories/blowjob/"
|
|
);
|
|
assert_eq!(
|
|
provider.page_family_referer(
|
|
"https://pimpbunny.com/search/adriana-chechik/3/?sort_by=video_viewed"
|
|
),
|
|
"https://pimpbunny.com/search/adriana-chechik/"
|
|
);
|
|
assert_eq!(
|
|
provider.page_family_referer(
|
|
"https://pimpbunny.com/onlyfans-models/momoitenshi/3/?sort_by=post_date"
|
|
),
|
|
"https://pimpbunny.com/onlyfans-models/momoitenshi/"
|
|
);
|
|
}
|
|
}
|