Created
March 9, 2022 12:58
-
-
Save maurolepore/5d9244aeb652aa6e648deb61826568f5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(dplyr) | |
library(rvest) | |
library(chromote) # remotes::install_github("rstudio/chromote") | |
library(countrycode) | |
library(readr) | |
# ------------------------------------------------------------------------------ | |
em_url <- "https://www.europages.co.uk/DAZUN-GMBH/00000005340662-639906001.html" | |
# start the headless browser and capture the DOM as HTML after JavaScript runs - | |
b <- chromote::ChromoteSession$new() | |
b$Page$navigate(em_url) | |
b$Page$loadEventFired() # wait until the page is loaded to continue\ | |
html <- b$Runtime$evaluate('document.documentElement.outerHTML')$result$value | |
b$close() | |
readr::write_file(html, "temp.html") | |
# ------------------------------------------------------------------------- | |
html <- readr::read_file("temp.html") | |
keywords <- | |
html %>% | |
read_html() %>% | |
html_elements(".pl-0 li") %>% | |
html_text2() | |
products <- | |
html %>% | |
read_html() %>% | |
html_element(".pa-0") %>% | |
html_elements("figcaption") %>% | |
html_text2() | |
headcount <- | |
html %>% | |
read_html() %>% | |
html_element(".ep-epages-business-details-headcount .text-body-1") %>% | |
html_text2() | |
# ------------------------------------------------------------------------- | |
Encoding(headcount) | |
charToRaw(headcount) | |
charToRaw(enc2utf8(headcount)) | |
stringi::stri_enc_toascii(headcount) | |
stringi::stri_trans_general(headcount, "latin-ascii") | |
fixed <- stringi::stri_trans_general(headcount, "latin-ascii") | |
charToRaw(fixed) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment