library(tidyverse)
library(rvest)
nbs_url <- "http://nbsurvey.kr/files"
nbs_bbs <- read_html(nbs_url)
nbs_bbs_raw <- nbs_bbs |>
html_nodes('.pagination-large') |>
html_nodes('.btn-page') |>
html_nodes('a') |>
html_attr('href')
nbs_bbs_lists <- c('http://nbsurvey.kr/files?mode=list', nbs_bbs_raw[2:length(nbs_bbs_raw)], 'http://nbsurvey.kr/files?mode=list&board_page=11')
nbs_bbs_lists
page_html <- read_html(nbs_bbs_list[2])
page_links <- page_html |>
html_nodes("a") |>
html_attr('href')
page_report_links_raw <- page_links[str_detect(page_links, "vid=")]
page_report_links <- page_report_links_raw[!is.na(page_report_links_raw)]
page_report_linkslibrary(httr)
report_html <- read_html(page_report_links[1])
report_filename <- report_html |>
html_nodes('a.file-download') |>
html_text() |>
str_extract(pattern = "\\((NBS)\\)_\\d+차_결과\\.zip")
report_download_url <- glue::glue("http://nbsurvey.kr/wp-content/plugins/mangboard/includes/mb-file.php",
"?path=MjAyMy8wMy8zMC9GMjc1XyhOQlMpXzkz7LCoX%2BqysOqzvC56aXA%3D",
"&type=download",
"&file_name={I(report_filename)}")
# fs::dir_create("data/NBS")
download.file(report_download_url, mode='wb', destfile = glue::glue("data/NBS/{report_filename}"))
# for(i in 1:length(page_report_links)) {
# cat("\n", i, "----------", page_report_links[i], "\n")
# download_zip_report(page_report_links[i])
# }
download_zip_report <- function(page_report_link) {
report_html <- read_html(page_report_link)
report_filename <- report_html |>
html_nodes('a.file-download') |>
html_text() |>
str_extract(pattern = "\\((NBS)\\)_\\d+차_결과\\.zip")
report_download_url <- glue::glue("http://nbsurvey.kr/wp-content/plugins/mangboard/includes/mb-file.php",
"?path=MjAyMy8wMy8zMC9GMjc1XyhOQlMpXzkz7LCoX%2BqysOqzvC56aXA%3D",
"&type=download",
"&file_name={I(report_filename)}")
download.file(report_download_url, mode='wb', destfile = glue::glue("data/NBS/{report_filename}"))
}
walk(page_report_links, download_zip_report)
nbs_bbs_lists
get_page_links <- function(nbs_bbs_list) {
page_html <- read_html(nbs_bbs_list)
page_links <- page_html |>
html_nodes("a") |>
html_attr('href')
page_report_links_raw <- page_links[str_detect(page_links, "vid=")]
page_report_links <- page_report_links_raw[!is.na(page_report_links_raw)]
page_report_links
}
nbs_bbs_tbl <- nbs_bbs_lists |>
enframe(value = "page_url") |>
mutate(data = map(page_url, get_page_links))
nbs_bbs_tbl |>
unnest(data)
download_zip_report <- function(page_report_link) {
report_html <- read_html(page_report_link)
report_filename <- report_html |>
html_nodes('a.file-download') |>
html_text() |>
str_extract(pattern = "\\((NBS)\\)_\\d+차_결과\\.zip")
report_download_url <- glue::glue("http://nbsurvey.kr/wp-content/plugins/mangboard/includes/mb-file.php",
"?path=MjAyMy8wMy8zMC9GMjc1XyhOQlMpXzkz7LCoX%2BqysOqzvC56aXA%3D",
"&type=download",
"&file_name={I(report_filename)}")
download.file(report_download_url, mode='wb', destfile = glue::glue("data/NBS/{report_filename}"))
}
walk(page_report_links, download_zip_report)---
title: "지도제작 대회"
subtitle: "한국갤럽 PDF"
description: |
전국지표조사(NBS) 수도권 역대 지지율을 살펴보자.
author:
- name: 이광춘
url: https://www.linkedin.com/in/kwangchunlee/
affiliation: 한국 R 사용자회
affiliation-url: https://github.com/bit2r
title-block-banner: true
format:
html:
theme: flatly
code-fold: true
code-overflow: wrap
toc: true
toc-depth: 3
toc-title: 목차
number-sections: true
highlight-style: github
self-contained: false
default-image-extension: jpg
filters:
- lightbox
lightbox: auto
link-citations: true
knitr:
opts_chunk:
eval: false
message: false
warning: false
collapse: true
comment: "#>"
R.options:
knitr.graphics.auto_pdf: true
editor_options:
chunk_output_type: console
---
# 데이터
## 자료실 목록
```{r}
library(tidyverse)
library(rvest)
nbs_url <- "http://nbsurvey.kr/files"
nbs_bbs <- read_html(nbs_url)
nbs_bbs_raw <- nbs_bbs |>
html_nodes('.pagination-large') |>
html_nodes('.btn-page') |>
html_nodes('a') |>
html_attr('href')
nbs_bbs_lists <- c('http://nbsurvey.kr/files?mode=list', nbs_bbs_raw[2:length(nbs_bbs_raw)], 'http://nbsurvey.kr/files?mode=list&board_page=11')
nbs_bbs_lists
```
## 페이지별 보고서 링크
```{r}
page_html <- read_html(nbs_bbs_list[2])
page_links <- page_html |>
html_nodes("a") |>
html_attr('href')
page_report_links_raw <- page_links[str_detect(page_links, "vid=")]
page_report_links <- page_report_links_raw[!is.na(page_report_links_raw)]
page_report_links
```
## 보고서 파일
```{r}
library(httr)
report_html <- read_html(page_report_links[1])
report_filename <- report_html |>
html_nodes('a.file-download') |>
html_text() |>
str_extract(pattern = "\\((NBS)\\)_\\d+차_결과\\.zip")
report_download_url <- glue::glue("http://nbsurvey.kr/wp-content/plugins/mangboard/includes/mb-file.php",
"?path=MjAyMy8wMy8zMC9GMjc1XyhOQlMpXzkz7LCoX%2BqysOqzvC56aXA%3D",
"&type=download",
"&file_name={I(report_filename)}")
# fs::dir_create("data/NBS")
download.file(report_download_url, mode='wb', destfile = glue::glue("data/NBS/{report_filename}"))
```
# 전체 파일 다운로드
## 한 페이지
```{r}
# for(i in 1:length(page_report_links)) {
# cat("\n", i, "----------", page_report_links[i], "\n")
# download_zip_report(page_report_links[i])
# }
download_zip_report <- function(page_report_link) {
report_html <- read_html(page_report_link)
report_filename <- report_html |>
html_nodes('a.file-download') |>
html_text() |>
str_extract(pattern = "\\((NBS)\\)_\\d+차_결과\\.zip")
report_download_url <- glue::glue("http://nbsurvey.kr/wp-content/plugins/mangboard/includes/mb-file.php",
"?path=MjAyMy8wMy8zMC9GMjc1XyhOQlMpXzkz7LCoX%2BqysOqzvC56aXA%3D",
"&type=download",
"&file_name={I(report_filename)}")
download.file(report_download_url, mode='wb', destfile = glue::glue("data/NBS/{report_filename}"))
}
walk(page_report_links, download_zip_report)
```
## 젠체 페이지
```{r}
nbs_bbs_lists
get_page_links <- function(nbs_bbs_list) {
page_html <- read_html(nbs_bbs_list)
page_links <- page_html |>
html_nodes("a") |>
html_attr('href')
page_report_links_raw <- page_links[str_detect(page_links, "vid=")]
page_report_links <- page_report_links_raw[!is.na(page_report_links_raw)]
page_report_links
}
nbs_bbs_tbl <- nbs_bbs_lists |>
enframe(value = "page_url") |>
mutate(data = map(page_url, get_page_links))
nbs_bbs_tbl |>
unnest(data)
download_zip_report <- function(page_report_link) {
report_html <- read_html(page_report_link)
report_filename <- report_html |>
html_nodes('a.file-download') |>
html_text() |>
str_extract(pattern = "\\((NBS)\\)_\\d+차_결과\\.zip")
report_download_url <- glue::glue("http://nbsurvey.kr/wp-content/plugins/mangboard/includes/mb-file.php",
"?path=MjAyMy8wMy8zMC9GMjc1XyhOQlMpXzkz7LCoX%2BqysOqzvC56aXA%3D",
"&type=download",
"&file_name={I(report_filename)}")
download.file(report_download_url, mode='wb', destfile = glue::glue("data/NBS/{report_filename}"))
}
walk(page_report_links, download_zip_report)
```