From 617b694d4c9037c81a93444d0242aa1ec2b3ef8d Mon Sep 17 00:00:00 2001 From: Josiah Campbell <9521010+jocmp@users.noreply.github.com> Date: Sat, 1 Feb 2025 22:06:38 -0600 Subject: [PATCH] fix: Keep nested h3's in tldr.tech --- src/extractors/custom/tldr.tech/index.js | 4 ++-- src/extractors/custom/tldr.tech/index.test.js | 5 +---- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/src/extractors/custom/tldr.tech/index.js b/src/extractors/custom/tldr.tech/index.js index b3598f2..aa0e4f3 100644 --- a/src/extractors/custom/tldr.tech/index.js +++ b/src/extractors/custom/tldr.tech/index.js @@ -2,7 +2,7 @@ export const TldrTechExtractor = { domain: 'tldr.tech', title: { - selectors: [['meta[name="og:title"]', 'value'], 'title'], + selectors: ['h1'], }, lead_image_url: { @@ -14,7 +14,7 @@ export const TldrTechExtractor = { transforms: { h2: $node => $node.attr('class', 'mercury-parser-keep'), - h3: $node => $node.attr('class', 'mercury-parser-keep'), + h3: 'b', }, clean: [], diff --git a/src/extractors/custom/tldr.tech/index.test.js b/src/extractors/custom/tldr.tech/index.test.js index 0307ed5..ca7193c 100644 --- a/src/extractors/custom/tldr.tech/index.test.js +++ b/src/extractors/custom/tldr.tech/index.test.js @@ -27,10 +27,7 @@ describe('TldrTechExtractor', () => { it('returns the title', async () => { const { title } = await result; - assert.equal( - title, - `OpenAI eyes $340B valuation 💰, Gemini 2.0 🤖, Javascript Temporal 👨‍💻` - ); + assert.equal(title, `TLDR 2025-01-31`); }); it('returns the lead_image_url', async () => { const { lead_image_url } = await result;