-
-
Save kguidonimartins/e6e54293d90f590f562c91c80a33d87e to your computer and use it in GitHub Desktop.
Extract link texts and urls from a web page into an R data frame
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
if (!require("tidyverse")) install.packages("tidyverse") | |
if (!require("rvest")) install.packages("rvest") | |
#' Extract link texts and urls from a web page | |
#' @param url character an url | |
#' @return a data frame of link text and urls | |
#' @examples | |
#' \dontrun{ | |
#' scraplinks("http://localhost/") | |
#' glinks <- scraplinks("http://google.com/") | |
#' } | |
#' @export | |
scraplinks <- function(url){ | |
# Create an html document from the url | |
webpage <- xml2::read_html(url) | |
# Extract the URLs | |
url_ <- webpage %>% | |
rvest::html_nodes("a") %>% | |
rvest::html_attr("href") | |
# Extract the link text | |
link_ <- webpage %>% | |
rvest::html_nodes("a") %>% | |
rvest::html_text() | |
return(tibble(link = link_, url = url_)) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
How to use: