植生凡例scraping.R

library("RSelenium")
library("rvest")
library("tidyverse")
library("stringr")

browser = remoteDriver(remoteServerAddr = "localhost", port = 4444, browserName = "chrome")
browser$open()

for(page in 1:58){
   url <- paste0("http://gis.biodic.go.jp/webgis/sc-017.html?1st=",str_pad(page, 2, pad = "0"))
   browser$navigate(url)
   Sys.sleep(3)
   pagesource <- browser$getPageSource()
   page_html <- paste0("get_snap_page",page,".html")
   write(unlist(pagesource), page_html)
}

####page 10の伐採跡地群落は空のページなので注意!
  
alldata<-NULL
for(page in 1:58){
   data<-read_html(paste0("get_snap_page",page,".html"),encoding = "sjis") %>% 
     html_nodes("#legend") %>% html_table() %>% .[[1]]
   alldata<-rbind(alldata,data)
}

tidydata<-alldata %>% 
  mutate(中区分=replace(中区分,大区分==中区分,NA)) %>% fill(中区分) %>% 
  replace(is.na(.), "00") %>% replace(.=="", "00") %>% 
  separate(大区分,c("DAI_C","DAI_N")," ") %>% 
  separate(中区分,c("CHU_C","CHU_N")," ") %>% 
  separate(細区分,c("SAI_C","SAI_N")," ") %>% 
  replace(is.na(.), "") %>% 
  unite(HANREI_C,DAI_C,CHU_C,SAI_C,sep="")

write_csv(tidydata,"HP植生凡例一覧.csv")