477 lines
16 KiB
Rust
477 lines
16 KiB
Rust
use crate::DbPool;
|
|
use crate::api::*;
|
|
use crate::providers::{Provider, report_provider_error};
|
|
use crate::status::*;
|
|
use crate::util::cache::VideoCache;
|
|
use crate::util::parse_abbreviated_number;
|
|
use crate::util::time::parse_time_to_seconds;
|
|
use crate::videos::{ServerOptions, VideoItem};
|
|
use async_trait::async_trait;
|
|
use error_chain::error_chain;
|
|
use htmlentity::entity::{ICodedDataTrait, decode};
|
|
use std::vec;
|
|
|
|
error_chain! {
|
|
foreign_links {
|
|
Io(std::io::Error);
|
|
HttpRequest(wreq::Error);
|
|
}
|
|
}
|
|
|
|
#[derive(Debug, Clone)]
|
|
pub struct Rule34genProvider {
|
|
url: String,
|
|
}
|
|
impl Rule34genProvider {
|
|
pub fn new() -> Self {
|
|
Rule34genProvider {
|
|
url: "https://rule34gen.com".to_string(),
|
|
}
|
|
}
|
|
|
|
fn build_channel(&self, clientversion: ClientVersion) -> Channel {
|
|
let _ = clientversion;
|
|
Channel {
|
|
id: "rule34gen".to_string(),
|
|
name: "Rule34Gen".to_string(),
|
|
description: "If it exists, here might be an AI generated video of it".to_string(),
|
|
premium: false,
|
|
favicon: "https://www.google.com/s2/favicons?sz=64&domain=rule34gen.com".to_string(),
|
|
status: "active".to_string(),
|
|
categories: vec![],
|
|
options: vec![ChannelOption {
|
|
id: "sort".to_string(),
|
|
title: "Sort".to_string(),
|
|
description: "Sort the Videos".to_string(), //"Sort the videos by Date or Name.".to_string(),
|
|
systemImage: "list.number".to_string(),
|
|
colorName: "blue".to_string(),
|
|
options: vec![
|
|
FilterOption {
|
|
id: "post_date".to_string(),
|
|
title: "Newest".to_string(),
|
|
},
|
|
FilterOption {
|
|
id: "video_viewed".to_string(),
|
|
title: "Most Viewed".to_string(),
|
|
},
|
|
FilterOption {
|
|
id: "rating".to_string(),
|
|
title: "Top Rated".to_string(),
|
|
},
|
|
FilterOption {
|
|
id: "duration".to_string(),
|
|
title: "Longest".to_string(),
|
|
},
|
|
FilterOption {
|
|
id: "pseudo_random".to_string(),
|
|
title: "Random".to_string(),
|
|
},
|
|
],
|
|
multiSelect: false,
|
|
}],
|
|
nsfw: true,
|
|
cacheDuration: Some(1800),
|
|
}
|
|
}
|
|
|
|
async fn get(
|
|
&self,
|
|
cache: VideoCache,
|
|
page: u8,
|
|
sort: &str,
|
|
options: ServerOptions,
|
|
) -> Result<Vec<VideoItem>> {
|
|
let expected_sorts = vec![
|
|
"post_date",
|
|
"video_viewed",
|
|
"rating",
|
|
"duration",
|
|
"pseudo_random",
|
|
];
|
|
let sort = if expected_sorts.contains(&sort) {
|
|
sort
|
|
} else {
|
|
"post_date"
|
|
};
|
|
|
|
let index = format!("rule34gen:{}:{}", page, sort);
|
|
let url = if page <= 1 {
|
|
format!("{}/?sort_by={}", self.url, sort)
|
|
} else {
|
|
format!("{}/{}/?sort_by={}", self.url, page, sort)
|
|
};
|
|
|
|
let mut old_items: Vec<VideoItem> = vec![];
|
|
if !(sort == "pseudo_random") {
|
|
old_items = match cache.get(&index) {
|
|
Some((time, items)) => {
|
|
if time.elapsed().unwrap_or_default().as_secs() < 60 * 5 {
|
|
// println!("Cache hit for URL: {}", url);
|
|
return Ok(items.clone());
|
|
} else {
|
|
items.clone()
|
|
}
|
|
}
|
|
None => {
|
|
vec![]
|
|
}
|
|
};
|
|
}
|
|
let mut requester =
|
|
crate::providers::requester_or_default(&options, module_path!(), "missing_requester");
|
|
let text = match requester.get(&url, None).await {
|
|
Ok(text) => text,
|
|
Err(e) => {
|
|
report_provider_error("rule34gen", "get.request", &format!("url={url}; error={e}"))
|
|
.await;
|
|
return Ok(old_items);
|
|
}
|
|
};
|
|
let video_items: Vec<VideoItem> = self.get_video_items_from_html(text.clone());
|
|
if !video_items.is_empty() {
|
|
cache.remove(&url);
|
|
cache.insert(url.clone(), video_items.clone());
|
|
} else {
|
|
return Ok(old_items);
|
|
}
|
|
Ok(video_items)
|
|
}
|
|
async fn query(
|
|
&self,
|
|
cache: VideoCache,
|
|
page: u8,
|
|
query: &str,
|
|
sort: &str,
|
|
options: ServerOptions,
|
|
) -> Result<Vec<VideoItem>> {
|
|
let expected_sorts = vec![
|
|
"post_date",
|
|
"video_viewed",
|
|
"rating",
|
|
"duration",
|
|
"pseudo_random",
|
|
];
|
|
let sort = if expected_sorts.contains(&sort) {
|
|
sort
|
|
} else {
|
|
"post_date"
|
|
};
|
|
|
|
let index = format!("rule34gen:{}:{}:{}", page, sort, query);
|
|
let search_slug = query.replace(" ", "-");
|
|
let url = if page <= 1 {
|
|
format!("{}/search/{}/?sort_by={}", self.url, search_slug, sort)
|
|
} else {
|
|
format!(
|
|
"{}/search/{}/{}/?sort_by={}",
|
|
self.url, search_slug, page, sort
|
|
)
|
|
};
|
|
|
|
// Check our Video Cache. If the result is younger than 1 hour, we return it.
|
|
let old_items = match cache.get(&index) {
|
|
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");
|
|
let text = match requester.get(&url, None).await {
|
|
Ok(text) => text,
|
|
Err(e) => {
|
|
report_provider_error(
|
|
"rule34gen",
|
|
"query.request",
|
|
&format!("url={url}; error={e}"),
|
|
)
|
|
.await;
|
|
return Ok(old_items);
|
|
}
|
|
};
|
|
let video_items: Vec<VideoItem> = self.get_video_items_from_html(text.clone());
|
|
if !video_items.is_empty() {
|
|
cache.remove(&url);
|
|
cache.insert(url.clone(), video_items.clone());
|
|
} else {
|
|
return Ok(old_items);
|
|
}
|
|
Ok(video_items)
|
|
}
|
|
|
|
fn get_video_items_from_html(&self, html: String) -> Vec<VideoItem> {
|
|
if html.is_empty() {
|
|
println!("HTML is empty");
|
|
return vec![];
|
|
}
|
|
let mut items: Vec<VideoItem> = Vec::new();
|
|
if html.contains("cards__item") {
|
|
for video_segment in html.split("<div class=\"cards__item\"").skip(1) {
|
|
let video_url = video_segment
|
|
.split("href=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
if !video_url.contains("/video/") {
|
|
continue;
|
|
}
|
|
|
|
let id = video_url
|
|
.split("/video/")
|
|
.nth(1)
|
|
.and_then(|s| s.split('/').next())
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
if id.is_empty() {
|
|
continue;
|
|
}
|
|
|
|
let mut title = video_segment
|
|
.split("title=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
if title.is_empty() {
|
|
title = video_segment
|
|
.split("<span class=\"card__title\">")
|
|
.nth(1)
|
|
.and_then(|s| s.split('<').next())
|
|
.unwrap_or_default()
|
|
.trim()
|
|
.to_string();
|
|
}
|
|
title = decode(title.as_bytes()).to_string().unwrap_or(title);
|
|
|
|
let thumb = video_segment
|
|
.split("data-original=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
let preview = video_segment
|
|
.split("data-preview=\"")
|
|
.nth(1)
|
|
.and_then(|s| s.split('"').next())
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
let raw_duration = video_segment
|
|
.split("card__label card__label--primary\">")
|
|
.nth(1)
|
|
.and_then(|s| s.split('<').next())
|
|
.unwrap_or_default()
|
|
.trim()
|
|
.to_string();
|
|
let duration = parse_time_to_seconds(&raw_duration).unwrap_or(0) as u32;
|
|
|
|
let views_text = video_segment
|
|
.split("<small class=\"card__text\">")
|
|
.nth(2)
|
|
.and_then(|s| s.split("</small>").next())
|
|
.unwrap_or_default()
|
|
.replace("views", "")
|
|
.replace(' ', "")
|
|
.trim()
|
|
.to_string();
|
|
let views = parse_abbreviated_number(views_text.as_str()).unwrap_or(0) as u32;
|
|
|
|
items.push(
|
|
VideoItem::new(
|
|
id,
|
|
title,
|
|
video_url,
|
|
"rule34gen".to_string(),
|
|
thumb,
|
|
duration,
|
|
)
|
|
.views(views)
|
|
.preview(preview),
|
|
);
|
|
}
|
|
return items;
|
|
}
|
|
let video_listing_content = html
|
|
.split("<div class=\"thumbs clearfix\" id=\"custom_list_videos")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("<div class=\"pagination\"")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
let raw_videos = video_listing_content
|
|
.split("<div class=\"item thumb video_")
|
|
.collect::<Vec<&str>>()[1..]
|
|
.to_vec();
|
|
for video_segment in &raw_videos {
|
|
// let vid = video_segment.split("\n").collect::<Vec<&str>>().get(1).copied().unwrap_or_default()
|
|
// for (index, line) in vid.iter().enumerate() {
|
|
// println!("Line {}: {}", index, line);
|
|
// }
|
|
|
|
if video_segment.contains("https://rule34gen.com/images/advertisements") {
|
|
continue;
|
|
}
|
|
|
|
let mut title = video_segment
|
|
.split("<div class=\"thumb_title\">")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("<")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
// html decode
|
|
title = decode(title.as_bytes()).to_string().unwrap_or(title);
|
|
let id = video_segment
|
|
.split("https://rule34gen.com/video/")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("/")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
let raw_duration = video_segment
|
|
.split("<div class=\"time\">")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("<")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
let duration = parse_time_to_seconds(&raw_duration).unwrap_or(0) as u32;
|
|
let views = parse_abbreviated_number(
|
|
&video_segment
|
|
.split("<div class=\"views\">")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("</svg>")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("<")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default(),
|
|
)
|
|
.unwrap_or(0);
|
|
//https://rule34gen.com/get_file/47/5e71602b7642f9b997f90c979a368c99b8aad90d89/3942000/3942353/3942353_preview.mp4/
|
|
//https://rule34gen.com/get_file/47/5e71602b7642f9b997f90c979a368c99b8aad90d89/3942000/3942353/3942353_preview.mp4/
|
|
let thumb = video_segment
|
|
.split("<img class=\"thumb lazy-load\" src=\"")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("data-original=\"")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("\"")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
let url = video_segment
|
|
.split("<a class=\"th js-open-popup\" href=\"")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.split("\"")
|
|
.collect::<Vec<&str>>()
|
|
.get(0)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
// let preview = video_segment.split("<div class=\"img wrap_image\" data-preview=\"").collect::<Vec<&str>>().get(1).copied().unwrap_or_default()
|
|
// .split("\"")
|
|
// .collect::<Vec<&str>>().get(0).copied().unwrap_or_default()
|
|
// .to_string();
|
|
|
|
let video_item = VideoItem::new(
|
|
id,
|
|
title,
|
|
url.to_string(),
|
|
"rule34gen".to_string(),
|
|
thumb,
|
|
duration,
|
|
)
|
|
.views(views)
|
|
// .preview(preview)
|
|
;
|
|
|
|
items.push(video_item);
|
|
}
|
|
return items;
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Provider for Rule34genProvider {
|
|
async fn get_videos(
|
|
&self,
|
|
cache: VideoCache,
|
|
pool: DbPool,
|
|
sort: String,
|
|
query: Option<String>,
|
|
page: String,
|
|
per_page: String,
|
|
options: ServerOptions,
|
|
) -> Vec<VideoItem> {
|
|
let _ = options;
|
|
let _ = per_page;
|
|
let _ = pool; // Ignored in this implementation
|
|
let videos: std::result::Result<Vec<VideoItem>, Error> = match query {
|
|
Some(q) => {
|
|
self.query(cache, page.parse::<u8>().unwrap_or(1), &q, &sort, 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) -> Option<crate::status::Channel> {
|
|
Some(self.build_channel(clientversion))
|
|
}
|
|
}
|