xvideos: resolve channel/pornstar names without prefix; channel archives via the JSON video list

src/providers/xvideos.rs

@@ -1,6 +1,8 @@
 use crate::DbPool;
 use crate::api::ClientVersion;
-use crate::providers::{Provider, report_provider_error, requester_or_default};
+use crate::providers::{
+    Provider, probe_first_archive, report_provider_error, requester_or_default, slug_dashed,
+};
 use crate::status::*;
 use crate::util::cache::VideoCache;
 use crate::util::parse_abbreviated_number;
@@ -86,6 +88,8 @@ enum Target {
     Best,
     Search(String),
     Archive(String),
+    /// Channel / pornstar profile, served as JSON by `/channels/{slug}/videos/new/{n}`.
+    Channel(String),
 }
 
 #[derive(Debug, Clone)]
@@ -238,6 +242,9 @@ impl XvideosProvider {
                     format!("{BASE_URL}/?k={encoded}&p={}", page - 1)
                 }
             }
+            Target::Channel(slug) => {
+                format!("{BASE_URL}/channels/{slug}/videos/new/{}", page.saturating_sub(1))
+            }
             Target::Archive(base_url) => {
                 let base = base_url.trim_end_matches('/');
                 if page <= 1 {
@@ -528,9 +535,8 @@ impl XvideosProvider {
                         let slug = value.replace(' ', "_");
                         return Target::Archive(format!("{BASE_URL}/c/{slug}"));
                     }
-                    "uploader" | "channel" | "profile" => {
-                        let slug = value.replace(' ', "_").to_ascii_lowercase();
-                        return Target::Archive(format!("{BASE_URL}/{slug}"));
+                    "uploader" | "channel" | "profile" | "pornstar" | "star" | "model" => {
+                        return Target::Channel(slug_dashed(value));
                     }
                     _ => {}
                 }
@@ -545,6 +551,83 @@ impl XvideosProvider {
         Target::Search(trimmed.to_string())
     }
 
+    /// A free-form query that names a channel / pornstar profile goes to its
+    /// archive (probed on the site; unknown names land on an empty profile),
+    /// else keyword search.
+    async fn resolve_keyword(query: &str, options: &ServerOptions) -> Option<Target> {
+        let slug = slug_dashed(query);
+        if slug.is_empty() {
+            return None;
+        }
+        let target = Target::Channel(slug);
+        let mut requester = requester_or_default(options, CHANNEL_ID, "resolve_keyword");
+        probe_first_archive(
+            &mut requester,
+            &[Self::target_url(&target, 1)],
+            &format!("{BASE_URL}/"),
+            |body| body.contains("\"videos\":[{"),
+        )
+        .await
+        .map(|_| target)
+    }
+
+    /// Parses the JSON served for a channel / profile video list.
+    fn parse_channel_json(json: &str, limit: usize) -> Result<Vec<VideoItem>> {
+        let root: serde_json::Value = serde_json::from_str(json)
+            .map_err(|e| Error::from(format!("channel json: {e}")))?;
+        let Some(videos) = root.get("videos").and_then(|v| v.as_array()) else {
+            return Ok(vec![]);
+        };
+        let text = |v: &serde_json::Value, key: &str| -> String {
+            v.get(key).and_then(|x| x.as_str()).unwrap_or_default().trim().to_string()
+        };
+        let mut items = Vec::new();
+        for video in videos {
+            let eid = text(video, "eid");
+            let thumb = text(video, "i");
+            let title = {
+                let full = text(video, "tf");
+                if full.is_empty() { text(video, "t") } else { full }
+            };
+            if eid.is_empty() || thumb.is_empty() || title.is_empty() {
+                continue;
+            }
+            let id = video
+                .get("id")
+                .map(|x| x.to_string().trim_matches('"').to_string())
+                .unwrap_or_else(|| eid.clone());
+            let mut item = VideoItem::new(
+                id,
+                Self::decode_html(&title),
+                format!("{BASE_URL}/video.{eid}/x"),
+                CHANNEL_ID.to_string(),
+                thumb,
+                Self::parse_duration(&text(video, "d")),
+            );
+            item.views = Self::parse_views(&text(video, "n"));
+            item.rating = text(video, "r").trim_end_matches('%').parse::<f32>().ok();
+            let preview = text(video, "ipu");
+            if !preview.is_empty() {
+                item.preview = Some(preview);
+            }
+            let name = text(video, "pn");
+            let slug = text(video, "pu");
+            if !name.is_empty() {
+                item.uploader = Some(name);
+                let slug = slug.trim_matches('/').to_string();
+                if !slug.is_empty() {
+                    item.uploaderUrl = Some(format!("{BASE_URL}/{slug}"));
+                    item.uploaderId = Some(format!("{CHANNEL_ID}:{slug}"));
+                }
+            }
+            items.push(item);
+            if items.len() >= limit {
+                break;
+            }
+        }
+        Ok(items)
+    }
+
     fn resolve_option_target(options: &ServerOptions, sort: &str) -> Target {
         if let Some(cat) = options.categories.as_deref() {
             if cat != "all" && !cat.is_empty() {
@@ -602,7 +685,11 @@ impl XvideosProvider {
             return Ok(vec![]);
         }
 
-        let items = Self::parse_listing(&html, per_page)?;
+        let items = if matches!(target, Target::Channel(_)) {
+            Self::parse_channel_json(&html, per_page)?
+        } else {
+            Self::parse_listing(&html, per_page)?
+        };
         if !items.is_empty() {
             cache.insert(cache_key, items.clone());
         }
@@ -625,10 +712,15 @@ impl Provider for XvideosProvider {
         let page = page.parse::<u16>().unwrap_or(1).max(1);
         let per_page = per_page.parse::<usize>().unwrap_or(10).clamp(1, 60);
 
-        let target = match query {
+        let mut target = match query {
             Some(q) if !q.trim().is_empty() => Self::resolve_query_target(q.trim()),
             _ => Self::resolve_option_target(&options, &sort),
         };
+        if let Target::Search(query) = &target {
+            if let Some(found) = Self::resolve_keyword(query, &options).await {
+                target = found;
+            }
+        }
 
         match self
             .fetch_target(cache, target, page, per_page, options)