Fix not correctly identify milkroad newsletters due to the HTML format changes again by the author

This commit is contained in:
Hongbo Wu
2022-10-13 10:52:03 +08:00
parent 460a013554
commit 5dcde8dac3
3 changed files with 169 additions and 1 deletions

View File

@ -8,7 +8,7 @@ export class BeehiivHandler extends ContentHandler {
}
findNewsletterHeaderHref(dom: Document): string | undefined {
const readOnline = dom.querySelectorAll('table tr td div a')
const readOnline = dom.querySelectorAll('table tr td a')
let res: string | undefined = undefined
readOnline.forEach((e) => {
if (e.textContent === 'Read Online') {

File diff suppressed because one or more lines are too long

View File

@ -136,6 +136,17 @@ describe('Newsletter email test', () => {
})
).to.eventually.be.true
})
it('returns true for milkroad newsletter', async () => {
const html = load('./test/data/milkroad-newsletter.html')
await expect(
new BeehiivHandler().isNewsletter({
html,
postHeader: '',
from: '',
unSubHeader: '',
})
).to.eventually.be.true
})
})
describe('findNewsletterUrl', async () => {