in response to @daattali's request to extract html tables with links included: https://twitter.com/daattali/status/717582654476914688

parse_extract_html_table_w_content_preserved.R

#compare with https://gist.github.com/expersso/bb03efcab2a6c125da5ac22e1c33d070

url <- "https://github.com/daattali/addinslist/blob/master/README.md#list-of-addins"

get_html_table <- function(url){
  xx <- xml2::read_html(url)
  rvest::xml_node(rvest::xml_node(xx,"body"),"table")
}

tr_to_nms <- function(tbl){
  tbl_tr <- rvest::xml_nodes(rvest::xml_nodes(tbl,"thead"),'tr')
  tbl_tr <- sapply(tbl_tr, function(x) gsub("(<th/>)", "<th>''</th>", x))
 sapply(tbl_tr, function(x) {
   strsplit(gsub("(<tr>\n<th>)|(</th>\n</tr>)","",x),"(</th>\n<th>)")[[1]]
   } , USE.NAMES=FALSE)
}

tr_to_df <- function(tbl){
  tbl_df <- rvest::xml_nodes(rvest::xml_nodes(tbl,"tbody"),'tr')
  tbl_df <-sapply(tbl_df, function(x) gsub("(<td/>)", "<td>''</td>", x))
  as.data.frame(
    t(sapply(tbl_df, function(x) {
      strsplit(gsub("(<tr>\n<td>)|(</td>\n</tr>)","",x),"(</td>\n<td>)")[[1]]
      }, USE.NAMES = F))
    ,stringsAsFactors=FALSE)
}

get_table <- function(url){
  xml_table <- get_html_table(url)
  stats::setNames(tr_to_df(xml_table),tr_to_nms(xml_table))
}

df <- get_table(url)
dplyr::glimpse(df)
# Observations: 28
# Variables: 7
# $ Name        (chr) "Browse RStudio addins", "Colour picker", "ggplot2 Marginal Plots", "ggplot Theme Assist", "S...
# $ Description (chr) "Browse and install RStudio addins", "Lets you easily select colours", "Add marginal plots to...
# $ Package     (chr) "<a href=\"https://github.com/daattali/addinslist\">addinslist</a>", "<a href=\"https://githu...
# $ On CRAN?    (chr) "<g-emoji alias=\"white_check_mark\" fallback-src=\"https://assets-cdn.github.com/images/icon...
# $ Author      (chr) "<a href=\"http://deanattali.com/\">Dean Attali</a>", "<a href=\"http://deanattali.com/\">Dea...
# $ More links  (chr) "<a href=\"https://raw.githubusercontent.com/daattali/addinslist/master/inst/media/addin.png\...
# $ Notes       (chr) "''", "''", "''", "''", "''", "''", "''", "''", "''", "Doesn't work on Windows", "''", "''", ...