special handling for youtube videos

src/lib.rs

@@ -1,6 +1,7 @@
 mod article;
 mod config;
 mod error;
+mod youtube;
 pub mod images;
 
 use self::error::{ScraperError, ScraperErrorKind};
@@ -58,6 +59,11 @@ impl ArticleScraper {
         client: &Client,
     ) -> Result<Article, ScraperError> {
         info!("Scraping article: '{}'", url.as_str());
+
+        if let Some(article) = youtube::Youtube::handle(&url) {
+            return Ok(article);
+        }
+
         let response = client
             .head(url.clone())
             .send()
@@ -834,4 +840,21 @@ mod tests {
             ))
         );
     }
+
+    #[tokio::test(basic_scheduler)]
+    async fn youtube() {
+        let config_path = PathBuf::from(r"./resources/tests/");
+        let url = url::Url::parse(
+            "https://www.youtube.com/watch?v=lHRkYLcmFY8",
+        )
+        .unwrap();
+
+        let grabber = ArticleScraper::new(config_path);
+        let article = grabber.parse(url, false, &Client::new()).await.unwrap();
+
+        assert_eq!(
+            article.html,
+            Some("<iframe width=\"650\" height=\"350\" frameborder=\"0\" src=\"https://www.youtube-nocookie.com/embed/lHRkYLcmFY8\" allowfullscreen></iframe>".into())
+        );
+    }
 }

src/youtube.rs

@@ -0,0 +1,26 @@
+use crate::article::Article;
+
+pub struct Youtube;
+
+impl Youtube {
+    pub fn handle(url: &url::Url) -> Option<Article> {
+        if url.host_str() == Some("youtube.com") || url.host_str() == Some("www.youtube.com") {
+            let regex = regex::Regex::new(r#"youtube\.com/watch\?v=(.*)"#).unwrap();
+            if let Some(captures) = regex.captures(url.as_str()) {
+                if let Some(video_id) = captures.get(1) {
+                    let html = format!("<iframe width=\"650\" height=\"350\" frameborder=\"0\" src=\"https://www.youtube-nocookie.com/embed/{}\" allowfullscreen></iframe>", video_id.as_str());
+
+                    return Some(Article {
+                        title: None,
+                        date: None,
+                        author: None,
+                        url: url.clone(),
+                        html: Some(html),
+                    })
+                }
+            }
+        }
+
+        None
+    }
+}