295 lines
8.4 KiB
Rust
295 lines
8.4 KiB
Rust
use crate::util::parse_abbreviated_number;
|
|
use crate::DbPool;
|
|
use crate::providers::Provider;
|
|
use crate::util::cache::VideoCache;
|
|
use crate::util::time::parse_time_to_seconds;
|
|
use crate::videos::{ServerOptions, VideoItem};
|
|
|
|
use error_chain::error_chain;
|
|
use htmlentity::entity::{decode, ICodedDataTrait};
|
|
use async_trait::async_trait;
|
|
use std::vec;
|
|
|
|
error_chain! {
|
|
foreign_links {
|
|
Io(std::io::Error);
|
|
HttpRequest(wreq::Error);
|
|
}
|
|
errors {
|
|
Parse(msg: String) {
|
|
description("parse error")
|
|
display("parse error: {}", msg)
|
|
}
|
|
}
|
|
}
|
|
|
|
#[derive(Debug, Clone)]
|
|
pub struct PornhubProvider {
|
|
url: String,
|
|
}
|
|
|
|
impl PornhubProvider {
|
|
pub fn new() -> Self {
|
|
Self {
|
|
url: "https://www.pornhub.com".to_string(),
|
|
}
|
|
}
|
|
|
|
async fn get(
|
|
&self,
|
|
cache: VideoCache,
|
|
page: u8,
|
|
sort: &str,
|
|
options: ServerOptions,
|
|
) -> Result<Vec<VideoItem>> {
|
|
let video_url = format!("{}/video?o={}&page={}", self.url, sort, page);
|
|
|
|
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());
|
|
}
|
|
Some((_, items)) => items.clone(),
|
|
None => vec![],
|
|
};
|
|
|
|
let mut requester = match options.requester.clone() {
|
|
Some(r) => r,
|
|
None => return Ok(old_items),
|
|
};
|
|
|
|
let text = match requester.get(&video_url, None).await {
|
|
Ok(t) => t,
|
|
Err(_) => return Ok(old_items),
|
|
};
|
|
|
|
let video_items = self.get_video_items_from_html(text, "<ul id=\"video");
|
|
|
|
if video_items.is_empty() {
|
|
Ok(old_items)
|
|
} else {
|
|
cache.remove(&video_url);
|
|
cache.insert(video_url.clone(), video_items.clone());
|
|
Ok(video_items)
|
|
}
|
|
}
|
|
|
|
async fn query(
|
|
&self,
|
|
cache: VideoCache,
|
|
page: u8,
|
|
query: &str,
|
|
sort: &str,
|
|
options: ServerOptions,
|
|
) -> Result<Vec<VideoItem>> {
|
|
let mut split_string = "<ul id=\"video";
|
|
let search_string = query.to_lowercase().trim().replace(' ', "+");
|
|
|
|
let mut video_url =
|
|
format!("{}/video/search?search={}&page={}", self.url, search_string, page);
|
|
|
|
if query.starts_with('@') {
|
|
let mut parts = query[1..].split(':');
|
|
let a = parts.next().unwrap_or("");
|
|
let b = parts.next().unwrap_or("");
|
|
video_url = format!("{}/{}/{}/videos?page={}", self.url, a, b.replace(' ', "-"), page);
|
|
|
|
if query.contains("@model") || query.contains("@pornstar") {
|
|
split_string = "mostRecentVideosSection";
|
|
}
|
|
if query.contains("@channels") {
|
|
split_string = "<ul class=\"videos row-5-thumbs";
|
|
}
|
|
}
|
|
|
|
video_url.push_str(match (query.contains("@channels"), sort) {
|
|
(true, "mv") => "&o=vi",
|
|
(true, "tr") => "&o=ra",
|
|
(false, "mv") => "&o=mv",
|
|
(false, "tr") => "&o=tr",
|
|
(false, "lg") => "&o=lg",
|
|
_ => "",
|
|
});
|
|
|
|
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());
|
|
}
|
|
Some((_, items)) => items.clone(),
|
|
None => vec![],
|
|
};
|
|
|
|
let mut requester = match options.requester.clone() {
|
|
Some(r) => r,
|
|
None => return Ok(old_items),
|
|
};
|
|
|
|
let text = match requester.get(&video_url, None).await {
|
|
Ok(t) => t,
|
|
Err(_) => return Ok(old_items),
|
|
};
|
|
|
|
let video_items = self.get_video_items_from_html(text, split_string);
|
|
|
|
if video_items.is_empty() {
|
|
Ok(old_items)
|
|
} else {
|
|
cache.remove(&video_url);
|
|
cache.insert(video_url.clone(), video_items.clone());
|
|
Ok(video_items)
|
|
}
|
|
}
|
|
|
|
fn get_video_items_from_html(&self, html: String, split_string: &str) -> Vec<VideoItem> {
|
|
let content = match html.split(split_string).nth(1) {
|
|
Some(c) => c,
|
|
None => return vec![],
|
|
};
|
|
|
|
let content = content.split("Porn in German").next().unwrap_or("");
|
|
|
|
let mut items = Vec::new();
|
|
|
|
for seg in content
|
|
.split("class=\"pcVideoListItem ")
|
|
.skip(1)
|
|
.filter(|s| !s.contains("wrapVideoBlock"))
|
|
{
|
|
let url_part = seg
|
|
.split("<a href=\"")
|
|
.nth(1)
|
|
.or_else(|| seg.split("data-video-vkey=\"").nth(1))
|
|
.and_then(|s| s.split('"').next());
|
|
|
|
let video_url = match url_part {
|
|
Some(u) if !u.is_empty() && u != "javascript:void(0)" => format!("{}{}", self.url, u),
|
|
_ => continue,
|
|
};
|
|
|
|
let mut title = seg
|
|
.split("\" title=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or("")
|
|
.to_string();
|
|
|
|
title = decode(title.as_bytes()).to_string().unwrap_or(title);
|
|
|
|
let id = match seg
|
|
.split("data-video-id=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
{
|
|
Some(id) => id.to_string(),
|
|
None => continue,
|
|
};
|
|
|
|
let raw_duration = seg
|
|
.split("duration")
|
|
.nth(1)
|
|
.and_then(|s| s.split('>').nth(1))
|
|
.and_then(|s| s.split('<').next())
|
|
.unwrap_or("0:00");
|
|
|
|
let duration = parse_time_to_seconds(raw_duration).unwrap_or(0) as u32;
|
|
|
|
let views = seg
|
|
.split("iews\">")
|
|
.filter_map(|p| p.split("<var>").nth(1))
|
|
.next()
|
|
.and_then(|v| v.split('<').next())
|
|
.and_then(|v| parse_abbreviated_number(v))
|
|
.unwrap_or(0);
|
|
|
|
let thumb = seg
|
|
.split("src=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or("")
|
|
.to_string();
|
|
|
|
let (tag, uploader) = if seg.contains("videoUploaderBlock") {
|
|
let href = seg
|
|
.split("videoUploaderBlock")
|
|
.nth(1)
|
|
.and_then(|s| s.split("href=\"").nth(1))
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or("");
|
|
|
|
let parts: Vec<&str> = href.split('/').collect();
|
|
if parts.len() >= 3 {
|
|
(
|
|
Some(format!("@{}:{}", parts[1], parts[2].replace('-', " "))),
|
|
Some(parts[2].to_string()),
|
|
)
|
|
} else {
|
|
(None, None)
|
|
}
|
|
} else {
|
|
(None, None)
|
|
};
|
|
|
|
let mut item = VideoItem::new(
|
|
id,
|
|
title,
|
|
video_url,
|
|
"pornhub".into(),
|
|
thumb,
|
|
duration,
|
|
);
|
|
|
|
if views > 0 {
|
|
item = item.views(views);
|
|
}
|
|
if let Some(t) = tag {
|
|
item = item.tags(vec![t]);
|
|
}
|
|
if let Some(u) = uploader {
|
|
item = item.uploader(u);
|
|
}
|
|
|
|
items.push(item);
|
|
}
|
|
|
|
items
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Provider for PornhubProvider {
|
|
async fn get_videos(
|
|
&self,
|
|
cache: VideoCache,
|
|
pool: DbPool,
|
|
sort: String,
|
|
query: Option<String>,
|
|
page: String,
|
|
per_page: String,
|
|
options: ServerOptions,
|
|
) -> Vec<VideoItem> {
|
|
let _ = pool;
|
|
let _ = per_page;
|
|
|
|
let page = page.parse::<u8>().unwrap_or(1);
|
|
let mut sort = match sort.as_str() {
|
|
"mv" => "mv",
|
|
"tr" => "tr",
|
|
"cm" => "cm",
|
|
"lg" => "lg",
|
|
_ => "mr",
|
|
};
|
|
if sort.contains("date") {
|
|
sort = "mr".into();
|
|
}
|
|
|
|
let res = match query {
|
|
Some(q) => self.query(cache, page, &q, &sort, options).await,
|
|
None => self.get(cache, page, &sort, options).await,
|
|
};
|
|
|
|
res.unwrap_or_else(|e| {
|
|
eprintln!("PornhubProvider error: {e}");
|
|
vec![]
|
|
})
|
|
}
|
|
}
|