validate and return rss feed if the url is an rss feed url

packages/api/src/generated/graphql.ts

@@ -2301,7 +2301,6 @@ export enum ScanFeedsErrorCode {
 
 export type ScanFeedsInput = {
   opml?: InputMaybe<Scalars['String']>;
-  type: ScanFeedsType;
   url?: InputMaybe<Scalars['String']>;
 };
 
@@ -2312,11 +2311,6 @@ export type ScanFeedsSuccess = {
   feeds: Array<Feed>;
 };
 
-export enum ScanFeedsType {
-  Html = 'HTML',
-  Opml = 'OPML'
-}
-
 export type SearchError = {
   __typename?: 'SearchError';
   errorCodes: Array<SearchErrorCode>;
@@ -3790,7 +3784,6 @@ export type ResolversTypes = {
   ScanFeedsInput: ScanFeedsInput;
   ScanFeedsResult: ResolversTypes['ScanFeedsError'] | ResolversTypes['ScanFeedsSuccess'];
   ScanFeedsSuccess: ResolverTypeWrapper<ScanFeedsSuccess>;
-  ScanFeedsType: ScanFeedsType;
   SearchError: ResolverTypeWrapper<SearchError>;
   SearchErrorCode: SearchErrorCode;
   SearchItem: ResolverTypeWrapper<SearchItem>;

packages/api/src/generated/schema.graphql

@@ -1751,7 +1751,6 @@ enum ScanFeedsErrorCode {
 
 input ScanFeedsInput {
   opml: String
-  type: ScanFeedsType!
   url: String
 }
 
@@ -1761,11 +1760,6 @@ type ScanFeedsSuccess {
   feeds: [Feed!]!
 }
 
-enum ScanFeedsType {
-  HTML
-  OPML
-}
-
 type SearchError {
   errorCodes: [SearchErrorCode!]!
 }

packages/api/src/resolvers/subscriptions/index.ts

@@ -17,7 +17,6 @@ import {
   ScanFeedsError,
   ScanFeedsErrorCode,
   ScanFeedsSuccess,
-  ScanFeedsType,
   SortBy,
   SortOrder,
   SubscribeError,
@@ -42,7 +41,7 @@ import { Merge } from '../../util'
 import { analytics } from '../../utils/analytics'
 import { enqueueRssFeedFetch } from '../../utils/createTask'
 import { authorized } from '../../utils/helpers'
-import { parseFeed, parseOpml } from '../../utils/parser'
+import { parseFeed, parseOpml, RSS_PARSER_CONFIG } from '../../utils/parser'
 
 type PartialSubscription = Omit<Subscription, 'newsletterEmail'>
 
@@ -399,22 +398,17 @@ export const scanFeedsResolver = authorized<
   ScanFeedsSuccess,
   ScanFeedsError,
   QueryScanFeedsArgs
->(async (_, { input: { type, opml, url } }, { log, uid }) => {
+>(async (_, { input: { opml, url } }, { log, uid }) => {
   analytics.track({
     userId: uid,
     event: 'scan_feeds',
     properties: {
-      type,
+      opml,
+      url,
     },
   })
 
-  if (type === ScanFeedsType.Opml) {
-    if (!opml) {
-      return {
-        errorCodes: [ScanFeedsErrorCode.BadRequest],
-      }
-    }
-
+  if (opml) {
     // parse opml
     const feeds = parseOpml(opml)
     if (!feeds) {
@@ -434,37 +428,52 @@ export const scanFeedsResolver = authorized<
   }
 
   if (!url) {
+    log.error('Missing opml and url')
+
     return {
       errorCodes: [ScanFeedsErrorCode.BadRequest],
     }
   }
 
   try {
-    // fetch HTML and parse feeds
-    const response = await axios.get(url, {
-      timeout: 5000,
-      headers: {
-        'User-Agent': 'Mozilla/5.0',
-        Accept: 'text/html',
-      },
-    })
-    const html = response.data as string
-    const dom = parseHTML(html).document
-    const links = dom.querySelectorAll('link[type="application/rss+xml"]')
-    const feeds = Array.from(links)
-      .map((link) => ({
-        url: link.getAttribute('href') || '',
-        title: link.getAttribute('title') || '',
-        type: 'rss',
-      }))
-      .filter((feed) => feed.url)
+    // fetch page content and parse feeds
+    const response = await axios.get(url, RSS_PARSER_CONFIG)
+    const content = response.data as string
+    // check if the content is html or xml
+    const contentType = response.headers['content-type']
+    const isHtml = contentType?.includes('text/html')
+    if (isHtml) {
+      // this is an html page, parse rss feed links
+      const dom = parseHTML(content).document
+      const links = dom.querySelectorAll('link[type="application/rss+xml"]')
+      const feeds = Array.from(links)
+        .map((link) => ({
+          url: link.getAttribute('href') || '',
+          title: link.getAttribute('title') || '',
+          type: 'rss',
+        }))
+        .filter((feed) => feed.url)
+
+      return {
+        __typename: 'ScanFeedsSuccess',
+        feeds,
+      }
+    }
+
+    // this is the url to an RSS feed
+    const feed = await parseFeed(url)
+    if (!feed) {
+      return {
+        errorCodes: [ScanFeedsErrorCode.BadRequest],
+      }
+    }
 
     return {
       __typename: 'ScanFeedsSuccess',
-      feeds,
+      feeds: [feed],
     }
   } catch (error) {
-    log.error('Error scanning HTML', error)
+    log.error('Error scanning URL', error)
 
     return {
       errorCodes: [ScanFeedsErrorCode.BadRequest],

packages/api/src/schema.ts

@@ -2686,16 +2686,10 @@ const schema = gql`
   }
 
   input ScanFeedsInput {
-    type: ScanFeedsType!
     url: String
     opml: String
   }
 
-  enum ScanFeedsType {
-    OPML
-    HTML
-  }
-
   union ScanFeedsResult = ScanFeedsSuccess | ScanFeedsError
 
   type ScanFeedsSuccess {

packages/api/src/utils/parser.ts

@@ -75,6 +75,16 @@ const DOM_PURIFY_CONFIG = {
 const ARTICLE_PREFIX = 'omnivore:'
 
 export const FAKE_URL_PREFIX = 'https://omnivore.app/no_url?q='
+export const RSS_PARSER_CONFIG = {
+  timeout: 5000, // 5 seconds
+  headers: {
+    // some rss feeds require user agent
+    'User-Agent':
+      'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
+    Accept:
+      'application/rss+xml, application/rdf+xml;q=0.8, application/atom+xml;q=0.6, application/xml;q=0.4, text/xml;q=0.4, text/html;q=0.2',
+  },
+}
 
 /** Hook that prevents DOMPurify from removing youtube iframes */
 const domPurifySanitizeHook = (
@@ -812,16 +822,7 @@ export const parseFeed = async (url: string): Promise<Feed | null> => {
       }
     }
 
-    const parser = new Parser({
-      timeout: 5000, // 5 seconds
-      headers: {
-        // some rss feeds require user agent
-        'User-Agent':
-          'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
-        Accept:
-          'application/rss+xml, application/rdf+xml;q=0.8, application/atom+xml;q=0.6, application/xml;q=0.4, text/xml;q=0.4',
-      },
-    })
+    const parser = new Parser(RSS_PARSER_CONFIG)
 
     const feed = await parser.parseURL(url)
     const feedUrl = feed.feedUrl || url