1
0
mirror of https://github.com/MontFerret/ferret.git synced 2024-12-12 11:15:14 +02:00
ferret/examples/crawler.fql

15 lines
536 B
Plaintext
Raw Normal View History

LET doc = DOCUMENT('https://www.theverge.com/tech', {
driver: "cdp"
})
2018-10-06 05:36:23 +02:00
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
2018-10-08 02:15:41 +02:00
// The Verge has pretty heavy pages, so let's increase the navigation wait time
NAVIGATE(doc, link, 20000)
2018-10-06 05:36:23 +02:00
WAIT_ELEMENT(doc, '.c-entry-content', 5000)
LET texter = ELEMENT(doc, '.c-entry-content')
RETURN texter.innerText