Using R to extract data out of some HTML code for a leaflet map (needed for a blogdown to Quarto blog conversion for rostrum.blog)

extract-html-data-leaflet.R

x <- readLines("~/Desktop/leaflet-map.txt")

popup_html <- stringr::str_split_1(x, "\",\"")

lmb_simple <- tibble::tibble(
  status_id = stringr::str_extract(popup_html, "\\d{19}"),
  lat = stringr::str_extract(popup_html, "(?<=📍 )5\\d{1}\\.\\d{0,4}(?=, )"),
  lon = stringr::str_extract(popup_html, "(?<=\\d, )(-)?\\d\\.\\d{0,4}(?=<br>📮)"),
  osm_url = glue::glue("https://www.openstreetmap.org/#map=17/{lat}/{lon}/"),
  media_url = stringr::str_extract(popup_html, "(?<=img src=\\')http://pbs\\.twimg\\.com/media/.*\\.jpg(?=\\' width)")
)

lmb_simple <- lmb_simple[complete.cases(lmb_simple), ]
lmb_simple$lat <- as.numeric(lmb_simple$lat)
lmb_simple$lon <- as.numeric(lmb_simple$lon)

saveRDS(lmb_simple, "~/Desktop/lmb_simple.rds")