prehistoric-systems/omnivore
1
0
Fork 0
mirror of https://github.com/omnivore-app/omnivore.git synced 2026-03-11 08:54:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #1417 from omnivore-app/feat/github-title-and-author

Browse source 
Better content extraction of title and description for GitHub URLs
This commit is contained in:
Jackson Harper 2022-11-15 19:32:48 +08:00 committed by GitHub
commit f7c6b0834b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 20 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
packages/content-handler/src/websites/github-handler.ts
View file

@ -12,10 +12,29 @@ export class GitHubHandler extends ContentHandler {
async preParse(url: string, dom: Document): Promise<Document> {
const body = dom.querySelector('body')
const head = dom.querySelector('head')
const article = dom.querySelector('article')
const twitterTitle = dom.querySelector(`meta[name='twitter:title']`)
const linkAuthor = dom.querySelector(`span[itemprop='author']`)
if (body && article) {
body?.replaceChildren(article)
body.replaceChildren(article)
// Attempt to set the author also. This is available on repo homepages
// but not on things like PRs. Ideally we want PRs and issues to have
// author set to the author of the PR/issue.
if (linkAuthor && linkAuthor.textContent) {
const author = dom.createElement('span')
author.setAttribute('rel', 'author')
author.innerHTML = linkAuthor.textContent
article.appendChild(author)
}
}
// Remove the GitHub - and repo org from the title
const twitterTitleContent = twitterTitle?.getAttribute('content')
if (twitterTitle && twitterTitleContent) {
twitterTitle.setAttribute('content', twitterTitleContent.replace(/GitHub - .*\//, ''))
}
return Promise.resolve(dom)