rvest_extract_between_nodes.r

# R rvest workflow to extract nodes between given headings

require(rvest)
require(tidyverse)

u = '<url>'

h0 = xml2::read_html(u)

# e.g. h2 elements
from_heading = 'Section 2' 
to_heading = 'Section 4'

xpath <- sprintf(
  "//h2[normalize-space(.)='%s']
     /following-sibling::*
     [not(preceding-sibling::h2[normalize-space(.)='%s'])]",
  from_heading, to_heading
)

nodes <- html_nodes(h0, xpath = xpath)