Saving reading position

frontend/src/lib/scraper/strategies/textExtractor.ts

@@ -1,3 +1,4 @@
+import * as cheerio from 'cheerio';
 import 'server-only';
 
 // Dynamic cheerio import used to avoid client-side bundling issues
@@ -36,7 +37,7 @@ export function extractByTextPattern(
 }
 
 export function extractTextBlocks(
-  $: any,
+  $: cheerio.CheerioAPI,
   config: TextBlockStrategy
 ): string {
   const blocks: Array<{element: any, text: string}> = [];
@@ -48,7 +49,7 @@ export function extractTextBlocks(
     });
   }
   
-  $('*').each((_: any, elem: any) => {
+  $('*').each((_, elem) => {
     const $elem = $(elem);
     const text = $elem.clone().children().remove().end().text().trim();
     
@@ -101,10 +102,16 @@ export function extractHtmlBetween(
 }
 
 export function extractLinkText(
-  $: any,
+  $: cheerio.CheerioAPI,
   config: LinkTextStrategy
 ): string {
-  let searchScope = config.searchWithin ? $(config.searchWithin) : $('body');
+  let searchScope: cheerio.Cheerio<cheerio.AnyNode>;
+  
+  if (config.searchWithin) {
+    searchScope = $(config.searchWithin);
+  } else {
+    searchScope = $('body').length ? $('body') : $('*');
+  }
   
   // Look for links near the specified text patterns
   let foundText = '';
@@ -112,7 +119,7 @@ export function extractLinkText(
   config.nearText.forEach(text => {
     if (foundText) return; // Already found
     
-    searchScope.find('*').each((_: any, elem: any) => {
+    searchScope.find('*').each((_, elem) => {
       const $elem = $(elem);
       const elemText = $elem.text().toLowerCase();
       
@@ -132,7 +139,7 @@ export function extractLinkText(
         
         // Look for links in the next few siblings
         const $siblings = $elem.nextAll().slice(0, 3);
-        $siblings.find('a').first().each((_: any, link: any) => {
+        $siblings.find('a').first().each((_, link) => {
           foundText = $(link).text().trim();
           return false;
         });