How to get headers by file

roblog_headers.R

``` r
roblog <- "C:\\Users\\Maelle\\Documents\\ropensci\\roweb2\\content\\blog"

all_posts <- fs::dir_ls(roblog, regexp = "*.md")
all_posts <- all_posts[all_posts != "_index.md"]

library("magrittr")

# Headers
get_headers <- function(path){
  filename <- fs::path_file(path) %>%
    as.character()

  path %>%
    readLines(encoding = "UTF-8") %>%
    blogdown:::split_yaml_body() %>%
    .$body %>%
    commonmark::markdown_xml(extensions = TRUE) %>%
    xml2::read_xml() %>%
    xml2::xml_find_all(xpath = './/d1:heading', 
                       xml2::xml_ns(.)) %>%
    xml2::xml_attr("level") -> levels
  
  if(length(levels) > 0){
    tibble::tibble(filename = filename,
                   level = levels)
  }else{
      NULL
    }
}

headers <- purrr::map_df(all_posts, get_headers)

headers %>%
  dplyr::group_by(filename) %>%
  dplyr::summarise(no_levels = length(unique(level)),
                   levels = toString(unique(level)))
#> # A tibble: 153 x 3
#>    filename                             no_levels levels
#>    <chr>                                    <int> <chr> 
#>  1 2012-11-26-is-invasive.md                    1 2     
#>  2 2013-03-08-ropensci-collaboration.md         1 3     
#>  3 2013-03-14-ropensci-challenge.md             1 2     
#>  4 2013-03-15-r-metadata.md                     2 3, 4  
#>  5 2013-04-12-rgbif-genus.md                    1 3     
#>  6 2013-04-22-usgs_app.md                       2 3, 4  
#>  7 2013-05-16-pyopensci.md                      1 1     
#>  8 2013-05-20-updates.md                        2 3, 4  
#>  9 2013-05-27-rbison.md                         2 3, 4  
#> 10 2013-06-14-goals-for-year.md                 1 2     
#> # ... with 143 more rows
```

Created on 2018-08-29 by the [reprex package](http://reprex.tidyverse.org) (v0.2.0).