1
0
mirror of https://github.com/MontFerret/ferret.git synced 2024-12-16 11:37:36 +02:00
ferret/examples/crawler.fql
2019-04-10 13:20:20 +03:00

15 lines
536 B
Plaintext

LET doc = DOCUMENT('https://www.theverge.com/tech', {
driver: "cdp"
})
WAIT_ELEMENT(doc, '.c-compact-river__entry', 5000)
LET articles = ELEMENTS(doc, '.c-entry-box--compact__image-wrapper')
LET links = (
FOR article IN articles
RETURN article.attributes.href
)
FOR link IN links
// The Verge has pretty heavy pages, so let's increase the navigation wait time
NAVIGATE(doc, link, 20000)
WAIT_ELEMENT(doc, '.c-entry-content', 5000)
LET texter = ELEMENT(doc, '.c-entry-content')
RETURN texter.innerText