From 8b24f381a0c6289d5c399affba9a7aedf902abda Mon Sep 17 00:00:00 2001
From: Jose <greenleaves@disroot.org>
Date: Thu, 27 Oct 2022 12:27:40 -0300
Subject: [PATCH] A web scraping example

---
 README.org         |  4 ++++
 script/scraping2.R | 49 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100755 script/scraping2.R

diff --git a/README.org b/README.org
index 8363d39..c680466 100755
--- a/README.org
+++ b/README.org
@@ -21,6 +21,10 @@ data using the R programming environment
 
  * [[./script/iteration.R][Lapply, apply and for loop: brief introduction]]
 
+** Web scraping
+
+ * [[./script/scraping2.R][Web scraping example]]
+
 ** Interesting packages
 
  * [[./script/roadoi_package.R]['roadoi']]
diff --git a/script/scraping2.R b/script/scraping2.R
new file mode 100755
index 0000000..380ac49
--- /dev/null
+++ b/script/scraping2.R
@@ -0,0 +1,49 @@
+#' ---
+#' title: ""
+#' date: "2022-06-24"
+#' author: "Jose"
+#' output:
+#'   html_document:
+#'    code_folding: show
+#'    toc: yes
+#'    toc_float:
+#'      smooth_scroll: true
+#'    df_print: paged
+#'    highlight: zenburn
+#' ---
+
+#' remove objects
+
+rm(list = ls())
+
+#' Libraries
+
+library(rvest)
+library(crul)
+
+url <- 'https://www.mdpi.com/search?q=pasture&journal=remotesensing'
+
+url_parse = url
+
+a = read_html(url)
+
+html_children(a)[1] |> html_text()
+
+str(a)
+
+html_elements(a, "h1")
+
+html_elements(a, "h2")
+
+html_elements(a, "h3")
+
+html_elements(a, "h4")
+
+html_elements(a, "h2") |> html_text2()
+
+html_elements(a, "p1")
+
+html_elements(a, "p2")
+
+html_elements(a, "p3")
+