v1.3.0 - More Robust Feed Parsing & Description Limiter

Qolors · Jan 20, 2024 · b92153f · b92153f
1 parent b7593ed
commit b92153f
Show file tree

Hide file tree

Showing 8 changed files with 55 additions and 29 deletions.
diff --git a/FeedCord/FeedCord.csproj b/FeedCord/FeedCord.csproj
@@ -9,6 +9,7 @@
   </PropertyGroup>
 
   <ItemGroup>
+    <PackageReference Include="CodeHollow.FeedReader" Version="1.2.6" />
     <PackageReference Include="HtmlAgilityPack" Version="1.11.54" />
     <PackageReference Include="Microsoft.Extensions.Hosting" Version="8.0.0-rc.2.23479.6" />
     <PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0-rc.2.23479.6" />

diff --git a/FeedCord/docs/reference.md b/FeedCord/docs/reference.md
@@ -16,6 +16,7 @@
 - **AuthorUrl**: The external link it will send users to when they click on the Author's Name.
 - **FallbackImage**: FeedCord always attemps to grab the webpage's image from metadata. If for some reason this fails, it will display this image instead.
 - **Color**: Color of the Post's embedded message.
+- **DescriptionLimit**: Limits the length of the description of the post to this number.
 
 ---
 
diff --git a/FeedCord/src/Common/Config.cs b/FeedCord/src/Common/Config.cs
@@ -15,6 +15,7 @@ internal class Config
         public int Color { get; }
         public int RssCheckIntervalMinutes { get; }
         public bool EnableAutoRemove { get; }
+        public int DescriptionLimit { get; }
 
         public Config(
             string[] urls,
@@ -29,7 +30,8 @@ public Config(
             string footerImage,
             int color,
             int rssCheckIntervalMinutes,
-            bool enableAutoRemove)
+            bool enableAutoRemove,
+            int descriptionLimit)
         {
             Urls = urls ?? throw new ArgumentNullException(nameof(urls));
             YoutubeUrls = youtubeurls ?? new string[] { };
@@ -44,6 +46,7 @@ public Config(
             Color = color;
             RssCheckIntervalMinutes = rssCheckIntervalMinutes;
             EnableAutoRemove = enableAutoRemove;
+            DescriptionLimit = descriptionLimit;
         }
     }
 }
diff --git a/FeedCord/src/Common/Interfaces/IRssProcessorService.cs b/FeedCord/src/Common/Interfaces/IRssProcessorService.cs
@@ -3,7 +3,7 @@ namespace FeedCord.src.Common.Interfaces
 {
     internal interface IRssProcessorService
     {
-        Task<Post?> ParseRssFeedAsync(string xmlContent);
+        Task<Post?> ParseRssFeedAsync(string xmlContent, int trim);
         Task<Post?> ParseYoutubeFeedAsync(string channelUrl);
     }
 }
diff --git a/FeedCord/src/RssReader/FeedProcessor.cs b/FeedCord/src/RssReader/FeedProcessor.cs
@@ -46,8 +46,8 @@ public async Task<List<Post>> CheckForNewPostsAsync()
         {
             ConcurrentBag<Post> newPosts = new();
 
-            var rsstasks = rssFeedData.Select(rssFeed => CheckAndAddNewPostAsync(rssFeed, newPosts, false)).ToList();
-            var youtubetasks = youtubeFeedData.Select(youtubeFeed => CheckAndAddNewPostAsync(youtubeFeed, newPosts, true)).ToList();
+            var rsstasks = rssFeedData.Select(rssFeed => CheckAndAddNewPostAsync(rssFeed, newPosts, false, config.DescriptionLimit)).ToList();
+            var youtubetasks = youtubeFeedData.Select(youtubeFeed => CheckAndAddNewPostAsync(youtubeFeed, newPosts, true, config.DescriptionLimit)).ToList();
 
             var tasks = rsstasks.Concat(youtubetasks).ToList();
 
@@ -133,11 +133,11 @@ private async Task<bool> TestUrlAsync(string url)
             }
         }
 
-        private async Task CheckAndAddNewPostAsync(KeyValuePair<string, DateTime> rssFeed, ConcurrentBag<Post> newPosts, bool isYoutube)
+        private async Task CheckAndAddNewPostAsync(KeyValuePair<string, DateTime> rssFeed, ConcurrentBag<Post> newPosts, bool isYoutube, int trim)
         {
             logger.LogInformation("Checking if any new posts for {RssFeedKey}...", rssFeed.Key);
 
-            var post = await CheckFeedForUpdatesAsync(rssFeed.Key, isYoutube);
+            var post = await CheckFeedForUpdatesAsync(rssFeed.Key, isYoutube, trim);
 
             if (post is null)
             {
@@ -192,17 +192,19 @@ private async Task CheckAndAddNewPostAsync(KeyValuePair<string, DateTime> rssFee
 
 
 
-        private async Task<Post?> CheckFeedForUpdatesAsync(string url, bool isYoutube)
+        private async Task<Post?> CheckFeedForUpdatesAsync(string url, bool isYoutube, int trim)
         {
             try
             {
                 var response = await httpClient.GetAsync(url);
                 response.EnsureSuccessStatusCode();
 
-                string xmlContent = await response.Content.ReadAsStringAsync();
+                string xmlContent = isYoutube ?
+                    await response.Content.ReadAsStringAsync() :
+                    url;
                 return isYoutube ? 
                     await rssProcessorService.ParseYoutubeFeedAsync(xmlContent) :
-                    await rssProcessorService.ParseRssFeedAsync(xmlContent);
+                    await rssProcessorService.ParseRssFeedAsync(xmlContent, trim);
 
             }
             catch (HttpRequestException ex)

diff --git a/FeedCord/src/Services/RssProcessorService.cs b/FeedCord/src/Services/RssProcessorService.cs
@@ -1,8 +1,8 @@
-using FeedCord.src.Common;
+using CodeHollow.FeedReader;
+using FeedCord.src.Common;
 using FeedCord.src.Common.Interfaces;
 using FeedCord.src.Helpers;
 using Microsoft.Extensions.Logging;
-using System.Xml.Linq;
 
 namespace FeedCord.src.Services
 {
@@ -22,32 +22,33 @@ public RssProcessorService(
             this.youtubeParsingService = youtubeParsingService;
         }
 
-        public async Task<Post?> ParseRssFeedAsync(string xmlContent)
+        public async Task<Post?> ParseRssFeedAsync(string xmlContent, int trim)
         {
             try
             {
-                var xDoc = XDocument.Parse(xmlContent);
-                var subtitle = xDoc.Descendants("title").FirstOrDefault()?.Value ?? string.Empty;
-                var latestPost = xDoc.Descendants("item").FirstOrDefault();
+                var feed = await FeedReader.ReadAsync(xmlContent);
+
+                var latestPost = feed.Items.FirstOrDefault();
 
                 if (latestPost == null)
-                {
-                    logger.LogError("No items found in the RSS feed. FeedCord only supports Traditional RSS Feeds");
                     return null;
-                }
 
-                string rawDescription = latestPost.Element("description")?.Value ?? string.Empty;
-                string description = StringHelper.StripTags(rawDescription);
-                if (description.Length > 200)
+                string title = latestPost.Title;
+                string imageLink = await openGraphService.ExtractImageUrl(latestPost.Link) ?? feed.ImageUrl ?? string.Empty;
+                string description = StringHelper.StripTags(latestPost.Description ?? string.Empty);
+                string link = latestPost.Link ?? string.Empty;
+                string subtitle = feed.Title;
+                DateTime pubDate = DateTime.TryParse(latestPost.PublishingDate.ToString(), out var tempDate) ? tempDate : default;
+
+                if (trim != 0)
                 {
-                    description = string.Concat(description.AsSpan(0, 197), "...");
+                    if (description.Length > trim)
+                    {
+                        description = description.Substring(0, trim) + "...";
+                    }
                 }
 
-                string title = StringHelper.StripTags(latestPost.Element("title")?.Value ?? string.Empty);
-                string imageLink = await openGraphService.ExtractImageUrl(latestPost.Element("link")?.Value ?? string.Empty);
-                DateTime pubDate = DateTime.TryParse(latestPost.Element("pubDate")?.Value, out var tempDate) ? tempDate : default;
-
-                return new Post(title, imageLink, description, latestPost.Element("link")?.Value ?? string.Empty, subtitle, pubDate);
+                return new Post(title, imageLink, description, link, subtitle, pubDate);
             }
             catch (Exception ex)
             {

diff --git a/FeedCord/src/Startup.cs b/FeedCord/src/Startup.cs
@@ -47,6 +47,7 @@ private static IHostBuilder CreateHostBuilder(string[] args) =>
                     var color = config.GetValue<int>("Color");
                     var rssCheckIntervalMinutes = config.GetValue<int>("RssCheckIntervalMinutes");
                     var enableAutoRemove = config.GetValue<bool>("EnableAutoRemove");
+                    var descriptionTrimLength = config.GetValue<int>("DescriptionLimit");
 
                     var appConfig = new Config(
                         rssUrls,
@@ -61,7 +62,8 @@ private static IHostBuilder CreateHostBuilder(string[] args) =>
                         footerImage,
                         color,
                         rssCheckIntervalMinutes,
-                        enableAutoRemove);
+                        enableAutoRemove,
+                        descriptionTrimLength);
 
                     services.AddHttpClient("Default", httpClient => 
                         {

diff --git a/README.md b/README.md
@@ -53,7 +53,8 @@ FeedCord is a dead-simple RSS Reader designed to integrate seamlessly with Disco
   "AuthorUrl": "https://github.com/Qolors/FeedCord",
   "FallbackImage": "https://i.imgur.com/f8M2Y5s.png",
   "FooterImage": "https://i.imgur.com/f8M2Y5s.png",
-  "Color": 8411391
+  "Color": 8411391,
+  "DescriptionLimit": 200
 }
 ```
 
@@ -119,6 +120,21 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+<details>
+  <summary>[1.3.0] - 2024-01-20</summary>
+
+  ### Added
+  - Added Description Length Configuration
+
+  ### Changed
+  - Improved RSS & ATOM Parsing with implementing [FeedReader](https://github.com/arminreiter/FeedReader) library
+
+  ### Fixed
+  - RSS/ATOM Feeds returning errors because of parsing issues
+
+</details>
+
+
 <details>
   <summary>[1.2.1] - 2024-01-17</summary>
   ### Changed