One way to extract text from a page is to tell the browser to run JavaScript code that does it.
library(chromote)
b <- ChromoteSession$new()
p <- b$Page$loadEventFired(wait_ = FALSE)
b$Page$navigate("https://www.whatismybrowser.com/", wait_ = FALSE)
p$then(function(value) {
b$Runtime$evaluate(
'document.querySelector(".corset .string-major a").innerText'
)
})$
then(function(value) {
print(value$result$value)
})
Another way is to use CDP commands to extract content from the DOM. This does not require executing JavaScript in the browser’s context, but it is also not as flexible as JavaScript.
library(chromote)
b <- ChromoteSession$new()
b$Page$navigate("https://www.whatismybrowser.com/")
x <- b$DOM$getDocument()
x <- b$DOM$querySelector(x$root$nodeId, ".corset .string-major a")
b$DOM$getOuterHTML(x$nodeId)
#> $outerHTML
#> [1] "<a href=\"/detect/what-version-of-chrome-do-i-have\">Chrome 75 on macOS (Mojave)</a>"
library(chromote)
b <- ChromoteSession$new()
p <- b$Page$loadEventFired(wait_ = FALSE)
b$Page$navigate("https://www.whatismybrowser.com/", wait_ = FALSE)
p$then(function(value) {
b$DOM$getDocument()
})$
then(function(value) {
b$DOM$querySelector(value$root$nodeId, ".corset .string-major a")
})$
then(function(value) {
b$DOM$getOuterHTML(value$nodeId)
})$
then(function(value) {
print(value)
})