download_links {clidatajp}

Download links for areas, countries and stations

Description

For polite scraping, 5 sec interval is set in download_links(), it takes about 15 minutes to get all station links. Please use existing links by "data(station_links)", if you do not need to renew links. You can see web page as below. https://www.data.jma.go.jp/gmd/cpd/monitor/nrmlist/

Usage

download_area_links(
  url = "https://www.data.jma.go.jp/gmd/cpd/monitor/nrmlist/"
)

download_links(url)

Arguments

url

A String to specify target html.

Value

A string vector of url links, or NULL when failed.

Examples

# If you want links for all countries and all sations, remove head().
# The codes take over 5 sec because of poliste scraping.

library(magrittr)
library(stringi)
library(dplyr)
library(tibble)
area_links <- download_area_links()
station_links <- NULL
continent     <- NULL
continents <- 
  c("\\u30a2\\u30d5\\u30ea\\u30ab",
    "\\u30a2\\u30b8\\u30a2",
    "\\u5357\\u30a2\\u30e1\\u30ea\\u30ab", 
    "\\u5317\\u4e2d\\u30a2\\u30e1\\u30ea\\u30ab",
    "\\u30aa\\u30bb\\u30a2\\u30cb\\u30a2",
    "\\u30e8\\u30fc\\u30ed\\u30c3\\u30d1")
area_links <- head(area_links, 1)  # for test
for(i in seq_along(area_links)){
    print(stringr::str_c("area: ", i, " / ", length(area_links)))
    country_links <- download_links(area_links[i])
    country_links <- head(country_links, 1)  # for test
    for(j in seq_along(country_links)){
        print(stringr::str_c("    country: ", j, " / ", length(country_links)))
        links <- download_links(country_links[j])
        station_links <- c(station_links, links)
        continent     <- c(continent,     rep(continents[i], length(links)))
    }
}
station_links <- tibble::tibble(url = station_links, continent = continent)
station_links