hottub/src/providers/javtiful.rs

use crate::DbPool;
use crate::api::ClientVersion;
use crate::providers::Provider;
use crate::status::*;
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 futures::future::join_all;
use htmlentity::entity::{ICodedDataTrait, decode};
use std::sync::{Arc, RwLock};
use std::vec;
use titlecase::Titlecase;
use wreq::Version;

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 JavtifulProvider {
    url: String,
    categories: Arc<RwLock<Vec<FilterOption>>>,
}

impl JavtifulProvider {
    pub fn new() -> Self {
        let provider = Self {
            url: "https://javtiful.com".to_string(),
            categories: Arc::new(RwLock::new(vec![])),
        };
        provider
    }

    fn build_channel(&self, clientversion: ClientVersion) -> Channel {
        let _ = clientversion;
        Channel {
            id: "javtiful".to_string(),
            name: "Javtiful".to_string(),
            description: "Watch Porn!".to_string(),
            premium: false,
            favicon: "https://www.google.com/s2/favicons?sz=64&domain=javtiful.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(
                        "javtiful",
                        "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: "newest".into(),
                        title: "Newest".into(),
                    },
                    FilterOption {
                        id: "top rated".into(),
                        title: "Top Rated".into(),
                    },
                    FilterOption {
                        id: "most viewed".into(),
                        title: "Most Viewed".into(),
                    },
                    FilterOption {
                        id: "top favorites".into(),
                        title: "Top Favorites".into(),
                    },
                ],
                multiSelect: false,
            }],
            nsfw: true,
            cacheDuration: Some(1800),
        }
    }

    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);
            }
        }
    }

    async fn get(
        &self,
        cache: VideoCache,
        page: u8,
        sort: &str,
        options: ServerOptions,
    ) -> Result<Vec<VideoItem>> {
        let sort_string = match sort {
            "top rated" => "/sort=top_rated",
            "most viewed" => "/sort=most_viewed",
            _ => "",
        };
        let video_url = format!("{}/videos{}?page={}", self.url, sort_string, 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());
                } else {
                    items.clone()
                }
            }
            None => {
                vec![]
            }
        };

        let mut requester =
            crate::providers::requester_or_default(&options, module_path!(), "missing_requester");
        let text = match requester.get(&video_url, Some(Version::HTTP_2)).await {
            Ok(text) => text,
            Err(e) => {
                crate::providers::report_provider_error(
                    "javtiful",
                    "get.request",
                    &format!("url={video_url}; error={e}"),
                )
                .await;
                return Ok(old_items);
            }
        };
        if page > 1
            && !text.contains(&format!(
                "<li class=\"page-item active\"><span class=\"page-link\">{}</span>",
                page
            ))
        {
            return Ok(vec![]);
        }
        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 sort_string = match options.sort.as_deref().unwrap_or("") {
            "top rated" => "/sort=top_rated",
            "most viewed" => "/sort=most_viewed",
            _ => "",
        };
        let video_url = format!(
            "{}/search/videos{}?search_query={}&page={}",
            self.url,
            sort_string,
            query.replace(" ", "+"),
            page
        );
        // 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");
        let text = match requester.get(&video_url, Some(Version::HTTP_2)).await {
            Ok(text) => text,
            Err(e) => {
                crate::providers::report_provider_error(
                    "javtiful",
                    "query.request",
                    &format!("url={video_url}; error={e}"),
                )
                .await;
                return Ok(old_items);
            }
        };
        if page > 1
            && !text.contains(&format!(
                "<li class=\"page-item active\"><span class=\"page-link\">{}</span>",
                page
            ))
        {
            return Ok(vec![]);
        }
        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 block = match html.split("pagination ").next().and_then(|s| {
            s.split("row row-cols-1 row-cols-sm-2 row-cols-lg-3 row-cols-xl-4")
                .nth(1)
        }) {
            Some(b) => b,
            None => {
                eprint!("Javtiful Provider: Failed to get block from html");
                let e = Error::from(ErrorKind::Parse("html".into()));
                send_discord_error_report(
                    e.to_string(),
                    Some(format_error_chain(&e)),
                    Some("Javtiful Provider"),
                    Some(&format!("Failed to get block from html:\n```{html}\n```")),
                    file!(),
                    line!(),
                    module_path!(),
                )
                .await;
                return vec![];
            }
        };

        let futures = block
            .split("card ")
            .skip(1)
            .filter(|seg| !seg.contains("SPONSOR"))
            .map(|el| self.get_video_item(el.to_string(), requester.clone()));

        join_all(futures)
            .await
            .into_iter()
            .inspect(|r| {
                if let Err(e) = r {
                    eprint!("Javtiful Provider: Failed to get video item:{}\n", e);
                    // Prepare data to move into the background task
                    let msg = e.to_string();
                    let chain = format_error_chain(&e);

                    // Spawn the report into the background - NO .await here
                    tokio::spawn(async move {
                        let _ = send_discord_error_report(
                            msg,
                            Some(chain),
                            Some("Javtiful Provider"),
                            Some("Failed to get video item"),
                            file!(), // Note: these might report the utility line
                            line!(), // better to hardcode or pass from outside
                            module_path!(),
                        )
                        .await;
                    });
                }
            })
            .filter_map(Result::ok)
            .collect()
    }

    async fn get_video_item(&self, seg: String, mut requester: Requester) -> Result<VideoItem> {
        let video_url = seg
            .split(" href=\"")
            .nth(1)
            .and_then(|s| s.split('"').next())
            .ok_or_else(|| ErrorKind::Parse("video url\n\n{seg}".into()))?
            .to_string();

        let mut title = seg
            .split(" alt=\"")
            .nth(1)
            .and_then(|s| s.split('"').next())
            .ok_or_else(|| ErrorKind::Parse(format!("video title\n\n{seg}").into()))?
            .trim()
            .to_string();

        title = decode(title.as_bytes())
            .to_string()
            .unwrap_or(title)
            .titlecase();
        let id = video_url
            .split('/')
            .nth(5)
            .and_then(|s| s.split('.').next())
            .ok_or_else(|| ErrorKind::Parse("video id\n\n{seg}".into()))?
            .to_string();
        let thumb_block = seg
            .split("<img ")
            .nth(1)
            .ok_or_else(|| ErrorKind::Parse("thumb block\n\n{seg}".into()))?;

        let thumb = thumb_block
            .split("data-src=\"")
            .nth(1)
            .and_then(|s| s.split('"').next())
            .unwrap_or("")
            .to_string();
        let mut preview = seg
            .split("data-trailer=\"")
            .nth(1)
            .and_then(|s| s.split('"').next())
            .unwrap_or("")
            .to_string();
        let raw_duration = seg
            .split("label-duration\">")
            .nth(1)
            .and_then(|s| s.split('<').next())
            .unwrap_or("")
            .to_string();
        let duration = parse_time_to_seconds(&raw_duration).unwrap_or(0) as u32;
        let (tags, formats, views) = self.extract_media(&video_url, &mut requester).await?;

        if preview.len() == 0 {
            preview = format!("https://trailers.jav.si/preview/{id}.mp4");
        }
        let video_item = VideoItem::new(id, title, video_url, "javtiful".into(), thumb, duration)
            .formats(formats)
            .tags(tags)
            .preview(preview)
            .views(views);
        Ok(video_item)
    }

    async fn extract_media(
        &self,
        url: &str,
        requester: &mut Requester,
    ) -> Result<(Vec<String>, Vec<VideoFormat>, u32)> {
        let text = requester
            .get(url, Some(Version::HTTP_2))
            .await
            .map_err(|e| Error::from(format!("{}", e)))?;
        let tags = text
            .split("related-actress")
            .next()
            .and_then(|s| s.split("video-comments").next())
            .and_then(|s| s.split(">Tags<").nth(1))
            .map(|tag_block| {
                tag_block
                    .split("<a ")
                    .skip(1)
                    .filter_map(|tag_el| {
                        tag_el
                            .split('>')
                            .nth(1)
                            .and_then(|s| s.split('<').next())
                            .map(|s| {
                                decode(s.as_bytes())
                                    .to_string()
                                    .unwrap_or(s.to_string())
                                    .titlecase()
                            })
                    })
                    .collect()
            })
            .unwrap_or_else(|| vec![]);
        for tag in &tags {
            Self::push_unique(
                &self.categories,
                FilterOption {
                    id: tag.to_ascii_lowercase().replace(" ", "+"),
                    title: tag.to_string(),
                },
            );
        }
        let views = text
            .split(" Views ")
            .next()
            .and_then(|s| s.split(" ").last())
            .and_then(|s| s.replace(".", "").parse::<u32>().ok())
            .unwrap_or(0);

        let quality = "1080p".to_string();
        let video_url = url.replace("javtiful.com", "hottub.spacemoehre.de/proxy/javtiful");
        Ok((
            tags,
            vec![VideoFormat::new(video_url, quality, "video/mp4".into())],
            views,
        ))
    }
}

#[async_trait]
impl Provider for JavtifulProvider {
    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 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!("javtiful error: {e}");
            vec![]
        })
    }

    fn get_channel(&self, v: ClientVersion) -> Option<Channel> {
        Some(self.build_channel(v))
    }
}