fixes

src/providers/rule34video.rs

@@ -1,203 +1,241 @@
-use crate::util::parse_abbreviated_number;
 use crate::DbPool;
 use crate::providers::Provider;
 use crate::util::cache::VideoCache;
+use crate::util::discord::send_discord_error_report;
+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;
 use std::time::{SystemTime, UNIX_EPOCH};
-use async_trait::async_trait;
+use std::vec;
 
 error_chain! {
     foreign_links {
         Io(std::io::Error);
         HttpRequest(wreq::Error);
     }
+    errors {
+        ParsingError(t: String) {
+            description("html parsing error")
+            display("HTML parsing error: '{}'", t)
+        }
+    }
 }
 
 #[derive(Debug, Clone)]
 pub struct Rule34videoProvider {
     url: String,
 }
+
 impl Rule34videoProvider {
     pub fn new() -> Self {
         Rule34videoProvider {
             url: "https://rule34video.com".to_string(),
         }
     }
+
+    /// Helper to safely extract a string between two delimiters
+    fn extract_between<'a>(content: &'a str, start_pat: &str, end_pat: &str) -> Option<&'a str> {
+        let start_idx = content.find(start_pat)? + start_pat.len();
+        let sub = &content[start_idx..];
+        let end_idx = sub.find(end_pat)?;
+        Some(&sub[..end_idx])
+    }
+
     async fn get(
         &self,
         cache: VideoCache,
         page: u8,
         sort: &str,
-        options: ServerOptions
+        options: ServerOptions,
     ) -> Result<Vec<VideoItem>> {
-        let now = SystemTime::now()
+        let timestamp_millis = SystemTime::now()
             .duration_since(UNIX_EPOCH)
-            .expect("Time went backwards");
+            .map(|d| d.as_millis())
+            .unwrap_or(0);
 
-        let timestamp_millis = now.as_millis(); // u128
-        let expected_sorts = vec!["post_date", "video_viewed", "rating", "duration", "pseudo_random"];
-        let sort = if expected_sorts.contains(&sort) {
+        let expected_sorts = vec![
+            "post_date",
+            "video_viewed",
+            "rating",
+            "duration",
+            "pseudo_random",
+        ];
+        let sort_val = if expected_sorts.contains(&sort) {
             sort
         } else {
             "post_date"
         };
 
-        let index = format!("rule34video:{}:{}", page, sort);
+        let index = format!("rule34video:{}:{}", page, sort_val);
 
-        let url = format!("{}/?mode=async&function=get_block&block_id=custom_list_videos_most_recent_videos&tag_ids=&sort_by={}&from={}&_={}", self.url, sort, page, timestamp_millis);
-        
-        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()
-                    }
+        if sort_val != "pseudo_random" {
+            if let Some((time, items)) = cache.get(&index) {
+                if time.elapsed().unwrap_or_default().as_secs() < 300 {
+                    return Ok(items.clone());
                 }
-                None => {
-                    vec![]
-                }
-            };
+            }
         }
-        let mut requester = options.requester.clone().unwrap();
-        let text = requester.get(&url, None).await.unwrap();
-        let video_items: Vec<VideoItem> = self.get_video_items_from_html(text.clone());
+
+        let mut requester = options.requester.clone().ok_or("Requester missing")?;
+        let url = format!(
+            "{}/?mode=async&function=get_block&block_id=custom_list_videos_most_recent_videos&tag_ids=&sort_by={}&from={}&_={}",
+            self.url, sort_val, page, timestamp_millis
+        );
+
+        let text = requester.get(&url, None).await.unwrap_or_else(|e| {
+            eprintln!("Error fetching rule34video URL {}: {}", url, e);
+            let _ = send_discord_error_report(e.to_string(), None, Some(&url), None, file!(), line!(), module_path!());
+            "".to_string()
+        });
+        let video_items = self.get_video_items_from_html(text);
+
         if !video_items.is_empty() {
-            cache.remove(&url);
-            cache.insert(url.clone(), video_items.clone());
+            cache.insert(index, video_items.clone());
+            Ok(video_items)
         } else {
-            return Ok(old_items);
+            // Return empty or old items if available
+            Ok(cache
+                .get(&index)
+                .map(|(_, items)| items)
+                .unwrap_or_default())
         }
-        Ok(video_items)
     }
+
     async fn query(
         &self,
         cache: VideoCache,
         page: u8,
         query: &str,
         sort: &str,
-        options: ServerOptions
+        options: ServerOptions,
     ) -> Result<Vec<VideoItem>> {
-        let now = SystemTime::now()
+        let timestamp_millis = SystemTime::now()
             .duration_since(UNIX_EPOCH)
-            .expect("Time went backwards");
-        let timestamp_millis = now.as_millis(); // u128
-        let expected_sorts = vec!["post_date", "video_viewed", "rating", "duration", "pseudo_random"];
-        let sort = if expected_sorts.contains(&sort) {
+            .map(|d| d.as_millis())
+            .unwrap_or(0);
+
+        let expected_sorts = vec![
+            "post_date",
+            "video_viewed",
+            "rating",
+            "duration",
+            "pseudo_random",
+        ];
+        let sort_val = if expected_sorts.contains(&sort) {
             sort
         } else {
             "post_date"
         };
 
-        let index = format!("rule34video:{}:{}:{}", page, sort, query);
+        let index = format!("rule34video:{}:{}:{}", page, sort_val, query);
 
-        let url = format!("{}/search/{}/?mode=async&function=get_block&block_id=custom_list_videos_videos_list_search&tag_ids=&sort_by={}&from_videos={}&from_albums={}&_={}", self.url, query.replace(" ","-"), sort, page, page, timestamp_millis);
+        if let Some((time, items)) = cache.get(&index) {
+            if time.elapsed().unwrap_or_default().as_secs() < 300 {
+                return Ok(items.clone());
+            }
+        }
 
-        // 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 = options.requester.clone().unwrap();
-        let text = requester.get(&url, None).await.unwrap();
-            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);
-            }
+        let mut requester = options.requester.clone().ok_or("Requester missing")?;
+        let url = format!(
+            "{}/search/{}/?mode=async&function=get_block&block_id=custom_list_videos_videos_list_search&tag_ids=&sort_by={}&from_videos={}&from_albums={}&_={}",
+            self.url,
+            query.replace(" ", "-"),
+            sort_val,
+            page,
+            page,
+            timestamp_millis
+        );
+
+        let text = requester.get(&url, None).await.unwrap_or_else(|e| {
+            eprintln!("Error fetching rule34video URL {}: {}", url, e);
+            let _ = send_discord_error_report(e.to_string(), None, Some(&url), None, file!(), line!(), module_path!());
+            "".to_string()
+        });
+        let video_items = self.get_video_items_from_html(text);
+
+        if !video_items.is_empty() {
+            cache.insert(index, video_items.clone());
             Ok(video_items)
+        } else {
+            Ok(cache
+                .get(&index)
+                .map(|(_, items)| items)
+                .unwrap_or_default())
+        }
     }
 
     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();
-        let video_listing_content = html.split("<div class=\"thumbs clearfix\" id=\"custom_list_videos").collect::<Vec<&str>>()[1].split("<div class=\"pagination\"").collect::<Vec<&str>>()[0].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>>()[1]
-            // for (index, line) in vid.iter().enumerate() {
-            //     println!("Line {}: {}", index, line);
-            // }
 
-            if video_segment.contains("https://rule34video.com/images/advertisements"){
+        // Safely isolate the video listing section
+        let video_listing = match Self::extract_between(
+            &html,
+            "id=\"custom_list_videos",
+            "<div class=\"pagination\"",
+        ) {
+            Some(content) => content,
+            None => return vec![],
+        };
+
+        let mut items = Vec::new();
+        // Skip the first split result as it's the preamble
+        let raw_videos = video_listing
+            .split("<div class=\"item thumb video_")
+            .skip(1);
+
+        for video_segment in raw_videos {
+            if video_segment.contains("title=\"Advertisement\"") {
                 continue;
             }
 
-            let mut title = video_segment.split("<div class=\"thumb_title\">").collect::<Vec<&str>>()[1]
-                .split("<")
-                .collect::<Vec<&str>>()[0]
+            // Title extraction
+            let title_raw =
+                Self::extract_between(video_segment, "<div class=\"thumb_title\">", "<")
+                    .unwrap_or("Unknown");
+            let title = decode(title_raw.as_bytes())
+                .to_string()
+                .unwrap_or_else(|_| title_raw.to_string());
+
+            // ID extraction
+            let id = Self::extract_between(video_segment, "https://rule34video.com/video/", "/")
+                .unwrap_or("0")
                 .to_string();
-            // html decode
-            title = decode(title.as_bytes()).to_string().unwrap_or(title);
-            let id = video_segment.split("https://rule34video.com/video/").collect::<Vec<&str>>()[1].split("/").collect::<Vec<&str>>()[0].to_string();
-            let raw_duration = video_segment.split("<div class=\"time\">").collect::<Vec<&str>>()[1]
-                    .split("<")
-                    .collect::<Vec<&str>>()[0]
+
+            // Duration extraction
+            let raw_duration =
+                Self::extract_between(video_segment, "<div class=\"time\">", "<").unwrap_or("0:00");
+            let duration = parse_time_to_seconds(raw_duration).unwrap_or(0) as u32;
+
+            // Views extraction
+            let views_segment = Self::extract_between(video_segment, "<div class=\"views\">", "<");
+            let views_count_str = views_segment
+                .and_then(|s| s.split("</svg>").nth(1))
+                .unwrap_or("0");
+            let views = parse_abbreviated_number(views_count_str.trim()).unwrap_or(0);
+
+            // Thumbnail extraction
+            let thumb = Self::extract_between(video_segment, "data-original=\"", "\"")
+                .unwrap_or("")
+                .to_string();
+
+            // URL extraction
+            let url =
+                Self::extract_between(video_segment, "<a class=\"th js-open-popup\" href=\"", "\"")
+                    .unwrap_or("")
                     .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>>()[1].split("</svg>").collect::<Vec<&str>>()[1]
-                .split("<")
-                .collect::<Vec<&str>>()[0]).unwrap_or(0);
-//https://rule34video.com/get_file/47/5e71602b7642f9b997f90c979a368c99b8aad90d89/3942000/3942353/3942353_preview.mp4/
-//https://rule34video.com/get_file/47/5e71602b7642f9b997f90c979a368c99b8aad90d89/3942000/3942353/3942353_preview.mp4/
-            let thumb = video_segment.split("<img class=\"thumb lazy-load\" src=\"").collect::<Vec<&str>>()[1].split("data-original=\"").collect::<Vec<&str>>()[1]
-                .split("\"")
-                .collect::<Vec<&str>>()[0]
-                .to_string();
-            let url = video_segment.split("<a class=\"th js-open-popup\" href=\"").collect::<Vec<&str>>()[1]
-                .split("\"")
-                .collect::<Vec<&str>>()[0]
-                .to_string();
-            // let preview = video_segment.split("<div class=\"img wrap_image\" data-preview=\"").collect::<Vec<&str>>()[1]
-            //     .split("\"")
-            //     .collect::<Vec<&str>>()[0]
-            //     .to_string();
 
-
-            let video_item = VideoItem::new(
-                id,
-                title,
-                url.to_string(),
-                "Rule34video".to_string(),
-                thumb,
-                duration,
-            )
-            .views(views)
-            // .preview(preview)
-            ;
-
-
-            items.push(video_item);
+            items.push(
+                VideoItem::new(id, title, url, "Rule34video".to_string(), thumb, duration)
+                    .views(views),
+            );
         }
-        return items;
+        items
     }
-
-
 }
 
 #[async_trait]
@@ -205,30 +243,24 @@ impl Provider for Rule34videoProvider {
     async fn get_videos(
         &self,
         cache: VideoCache,
-        pool: DbPool,
+        _pool: DbPool,
         sort: String,
         query: Option<String>,
         page: String,
-        per_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
-            }
+        let page_num = page.parse::<u8>().unwrap_or(1);
+
+        let result = match query {
+            Some(q) => self.query(cache, page_num, &q, &sort, options).await,
+            None => self.get(cache, page_num, &sort, options).await,
         };
-        match videos {
+
+        match result {
             Ok(v) => v,
             Err(e) => {
-                println!("Error fetching videos: {}", e);
+                eprintln!("Error fetching videos: {}", e);
                 vec![]
             }
         }