archivebate repaired

src/providers/archivebate.rs

@@ -64,12 +64,10 @@ const PLATFORM_SHORTCUTS: &[(&str, &str)] = &[
     ("tiktok", "dGlrdG9r"),
 ];
 
-const GENDER_SHORTCUTS: &[(&str, &str)] = &[
+// NOTE: archivebate.com also exposes `/gender/<base64>` routes in its nav, but the
-    ("female", "ZmVtYWxl"),
+// Livewire `filter.platform` component always responds with a redirect to the home
-    ("couple", "Y291cGxl"),
+// page for gender values (server-side bug on the site), so gender browsing returns
-    ("male", "bWFsZQ=="),
+// no videos. Gender shortcuts are intentionally not exposed here.
-    ("trans", "dHJhbnM="),
-];
 
 #[derive(Debug, Clone)]
 pub struct ArchivebateProvider {
@@ -85,10 +83,6 @@ enum Target {
         id: String,
         title: String,
     },
-    Gender {
-        id: String,
-        title: String,
-    },
     Profile {
         username: String,
         platform: Option<String>,
@@ -120,12 +114,6 @@ struct LivewireInitialData {
     server_memo_json: String,
 }
 
-#[derive(Debug, Clone)]
-struct ResolvedMixdropMedia {
-    media_url: String,
-    embed_url: String,
-}
-
 impl ArchivebateProvider {
     pub fn new() -> Self {
         let provider = Self {
@@ -191,13 +179,6 @@ impl ArchivebateProvider {
             title: "All".to_string(),
         }];
 
-        for (title, id) in GENDER_SHORTCUTS {
-            filters.push(FilterOption {
-                id: format!("gender:{id}"),
-                title: format!("Gender: {}", Self::title_case(title)),
-            });
-        }
-
         for (title, id) in PLATFORM_SHORTCUTS {
             filters.push(FilterOption {
                 id: format!("platform:{id}"),
@@ -223,7 +204,7 @@ impl ArchivebateProvider {
         Channel {
             id: CHANNEL_ID.to_string(),
             name: "ArchiveBate".to_string(),
-            description: "ArchiveBate cam recording feeds with platform/gender/profile shortcuts and yt-dlp compatible watch URLs.".to_string(),
+            description: "ArchiveBate cam recording feeds with platform and profile shortcuts and yt-dlp compatible watch URLs.".to_string(),
             premium: false,
             favicon: "https://www.google.com/s2/favicons?sz=64&domain=archivebate.com".to_string(),
             status: "work in progress".to_string(),
@@ -244,7 +225,7 @@ impl ArchivebateProvider {
                 ChannelOption {
                     id: "filter".to_string(),
                     title: "Shortcuts".to_string(),
-                    description: "Direct platform and gender archive routes.".to_string(),
+                    description: "Direct platform archive routes.".to_string(),
                     systemImage: "tag.fill".to_string(),
                     colorName: "green".to_string(),
                     options: filters,
@@ -365,13 +346,6 @@ impl ArchivebateProvider {
                     format!("{}/platform/{id}?page={page}", self.url)
                 }
             }
-            Target::Gender { id, .. } => {
-                if page <= 1 {
-                    format!("{}/gender/{id}", self.url)
-                } else {
-                    format!("{}/gender/{id}?page={page}", self.url)
-                }
-            }
             Target::Profile { username, .. } => {
                 if page <= 1 {
                     format!("{}/profile/{username}", self.url)
@@ -435,15 +409,6 @@ impl ArchivebateProvider {
             }
         }
 
-        if let Some(id) = trimmed.strip_prefix("gender:") {
-            if let Some((name, _)) = GENDER_SHORTCUTS.iter().find(|(_, known_id)| *known_id == id) {
-                return Some(Target::Gender {
-                    id: id.to_string(),
-                    title: Self::title_case(name),
-                });
-            }
-        }
-
         let normalized = Self::normalize_title(trimmed);
         if let Some((name, id)) = PLATFORM_SHORTCUTS
             .iter()
@@ -455,16 +420,6 @@ impl ArchivebateProvider {
             });
         }
 
-        if let Some((name, id)) = GENDER_SHORTCUTS
-            .iter()
-            .find(|(name, _)| Self::normalize_title(name) == normalized)
-        {
-            return Some(Target::Gender {
-                id: (*id).to_string(),
-                title: Self::title_case(name),
-            });
-        }
-
         if let Some(option) = self.find_uploader_option(trimmed) {
             if let Some(username) = option.id.strip_prefix("profile:") {
                 return Some(Target::Profile {
@@ -605,7 +560,6 @@ impl ArchivebateProvider {
     fn extra_tags_for_target(target: &Target) -> Vec<String> {
         match target {
             Target::Platform { title, .. } => vec![title.clone()],
-            Target::Gender { title, .. } => vec![title.clone()],
             Target::Profile { platform, gender, .. } => {
                 let mut tags = Vec::new();
                 if let Some(platform) = platform.as_ref().filter(|value| !value.trim().is_empty()) {
@@ -746,104 +700,6 @@ impl ArchivebateProvider {
         Ok(items)
     }
 
-    fn parse_mixin_packed_eval(html: &str) -> Option<String> {
-        let eval_regex = Regex::new(
-            r#"(?s)eval\(function\(p,a,c,k,e,d\)\{.*?\}\('(?P<payload>.*?)',\s*(?P<radix>[0-9]+),\s*(?P<count>[0-9]+),\s*'(?P<tokens>.*?)'\.split\('\|'\)"#,
-        )
-        .ok()?;
-        let captures = eval_regex.captures(html)?;
-        let payload_raw = captures.name("payload")?.as_str();
-        let radix = captures.name("radix")?.as_str().parse::<u32>().ok()?;
-        let count = captures.name("count")?.as_str().parse::<usize>().ok()?;
-        if !(2..=36).contains(&radix) {
-            return None;
-        }
-
-        let payload = Self::unescape_js_single_quoted(payload_raw);
-        let tokens_raw = captures.name("tokens")?.as_str();
-        let tokens = tokens_raw.split('|').collect::<Vec<_>>();
-        let mut unpacked = payload;
-
-        for index in (0..count).rev() {
-            let Some(token) = tokens.get(index) else {
-                continue;
-            };
-            if token.is_empty() {
-                continue;
-            }
-            let key = Self::to_radix(index, radix);
-            let pattern = format!(r"\b{}\b", regex::escape(&key));
-            let re = Regex::new(&pattern).ok()?;
-            unpacked = re.replace_all(&unpacked, *token).into_owned();
-        }
-
-        Some(unpacked)
-    }
-
-    fn unescape_js_single_quoted(value: &str) -> String {
-        let mut output = String::with_capacity(value.len());
-        let mut chars = value.chars();
-        while let Some(character) = chars.next() {
-            if character != '\\' {
-                output.push(character);
-                continue;
-            }
-            let Some(next) = chars.next() else {
-                break;
-            };
-            match next {
-                '\\' => output.push('\\'),
-                '\'' => output.push('\''),
-                '"' => output.push('"'),
-                'n' => output.push('\n'),
-                'r' => output.push('\r'),
-                't' => output.push('\t'),
-                _ => output.push(next),
-            }
-        }
-        output
-    }
-
-    fn to_radix(mut value: usize, radix: u32) -> String {
-        if value == 0 {
-            return "0".to_string();
-        }
-        let alphabet = b"0123456789abcdefghijklmnopqrstuvwxyz";
-        let mut out = Vec::new();
-        while value > 0 {
-            let digit = value % radix as usize;
-            out.push(alphabet[digit] as char);
-            value /= radix as usize;
-        }
-        out.iter().rev().collect()
-    }
-
-    fn extract_mixdrop_media_url(html: &str) -> Option<String> {
-        let direct_regex = Regex::new(r#"MDCore\.wurl\s*=\s*"([^"]+)""#).ok()?;
-        if let Some(url) = direct_regex
-            .captures(html)
-            .and_then(|captures| captures.get(1).map(|value| value.as_str().to_string()))
-        {
-            return Some(Self::normalize_possible_protocol_relative(&url));
-        }
-
-        let unpacked = Self::parse_mixin_packed_eval(html)?;
-        let unpacked_regex = Regex::new(r#"MDCore\.wurl\s*=\s*"([^"]+)""#).ok()?;
-        unpacked_regex
-            .captures(&unpacked)
-            .and_then(|captures| captures.get(1).map(|value| value.as_str().to_string()))
-            .map(|value| Self::normalize_possible_protocol_relative(&value))
-    }
-
-    fn normalize_possible_protocol_relative(value: &str) -> String {
-        let trimmed = value.trim();
-        if trimmed.starts_with("//") {
-            format!("https:{trimmed}")
-        } else {
-            trimmed.to_string()
-        }
-    }
-
     fn host_from_url(url: &str) -> Option<String> {
         let parsed = url::Url::parse(url).ok()?;
         parsed.host_str().map(|value| value.to_ascii_lowercase())
@@ -931,25 +787,6 @@ impl ArchivebateProvider {
         format
     }
 
-    fn first_video_source_from_html(html: &str) -> Option<String> {
-        let document = Html::parse_document(html);
-        let source_selector = Selector::parse("video source[src]").ok()?;
-        let video_src_selector = Selector::parse("video[src]").ok()?;
-
-        if let Some(value) = document
-            .select(&source_selector)
-            .next()
-            .and_then(|node| node.value().attr("src"))
-        {
-            return Some(value.to_string());
-        }
-        document
-            .select(&video_src_selector)
-            .next()
-            .and_then(|node| node.value().attr("src"))
-            .map(|value| value.to_string())
-    }
-
     fn first_iframe_source_from_html(html: &str) -> Option<String> {
         let document = Html::parse_document(html);
         let iframe_selector = Selector::parse("iframe[src]").ok()?;
@@ -960,32 +797,6 @@ impl ArchivebateProvider {
             .map(|value| value.to_string())
     }
 
-    async fn resolve_mixdrop_media_from_iframe(
-        &self,
-        iframe_url: &str,
-        referer: &str,
-        options: &ServerOptions,
-    ) -> Option<ResolvedMixdropMedia> {
-        let mut requester = requester_or_default(options, CHANNEL_ID, "resolve_mixdrop_media");
-        let response = requester
-            .get_raw_with_headers_timeout(
-                iframe_url,
-                self.html_headers(referer),
-                Some(StdDuration::from_secs(6)),
-            )
-            .await
-            .ok()?;
-        if !response.status().is_success() {
-            return None;
-        }
-        let iframe_html = response.text().await.ok()?;
-        let media_url = Self::extract_mixdrop_media_url(&iframe_html)?;
-        Some(ResolvedMixdropMedia {
-            media_url,
-            embed_url: iframe_url.to_string(),
-        })
-    }
-
     async fn enrich_video(&self, item: VideoItem, options: &ServerOptions) -> VideoItem {
         let page_url = item.url.clone();
         let format_url = Self::proxied_video(options, &page_url);
@@ -1405,23 +1216,3 @@ impl Provider for ArchivebateProvider {
         Some(self.build_channel(clientversion))
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use super::ArchivebateProvider;
-
-    #[test]
-    fn extracts_mixdrop_wurl_from_packed_eval() {
-        let html = r#"
-<script>
-eval(function(p,a,c,k,e,d){e=function(c){return c};if(!''.replace(/^/,String)){while(c--){d[c]=k[c]||c}k=[function(e){return d[e]}];e=function(){return'\\w+'};c=1};while(c--){if(k[c]){p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c])}}return p}('1.2="//3.4.5/6/7.8?9=a&b=c";',13,13,'|MDCore|wurl|o230m5y6z|mxcontent|net|v2|r6pkwozjber741|mp4|s|TvNTJe3_z_6nKveumEHk8Q|e|1776460168'.split('|'),0,{}))
-</script>
-"#;
-        let actual = ArchivebateProvider::extract_mixdrop_media_url(html)
-            .expect("expected mixdrop media url");
-        assert_eq!(
-            actual,
-            "https://o230m5y6z.mxcontent.net/v2/r6pkwozjber741.mp4?s=TvNTJe3_z_6nKveumEHk8Q&e=1776460168"
-        );
-    }
-}