forkonlp · mrchypark · Sep 4, 2022
diff --git a/R/getCategory.R b/R/getCategory.R
@@ -3,8 +3,12 @@
 #' @param fresh get data from online. Default is FALSE using cached built-in data.
 #' @export
 getCategory <- function(fresh = FALSE) {
+  news_category(fresh)
+}
+
+news_category <- function(fresh = FALSE) {
   if (!fresh) {
-    return(news_category)
+    return(news_category_data)
   }
   mcate <- getMainCategory()
   cate <- list()

diff --git a/R/getComment.R b/R/getComment.R
@@ -17,7 +17,7 @@
 getComment <- function(turl,
                        count = 10,
                        type = c("df", "list")) {
-  get_comment(turl, count, type)
+  news_comment(turl, count, type)
 }
 
 #' Get All Comment
@@ -37,13 +37,13 @@ getComment <- function(turl,
 #'   getAllComment("https://n.news.naver.com/mnews/article/214/0001195110")
 #'   }
 getAllComment <- function(turl) {
-  get_comment(turl, "all", "df")
+  news_comment(turl, "all", "df")
 }
 
 #' @importFrom purrr when
 #' @importFrom httr2 req_perform resp_body_string
 #' @importFrom jsonlite fromJSON
-get_comment <- function(turl,
+news_comment <- function(turl,
                         count = 10,
                         type = c("df", "list")) {
   . <- NULL

diff --git a/R/getCommentHistory.R b/R/getCommentHistory.R
@@ -20,7 +20,7 @@ getCommentHistory <- function(turl,
                               commentNo,
                               count = 10,
                               type = c("df", "list")) {
-  get_comment_history(turl, commentNo, count, type)
+  news_comment_history(turl, commentNo, count, type)
 }
 
 #' Get All Comment History
@@ -39,12 +39,12 @@ getCommentHistory <- function(turl,
 
 getAllCommentHistory <- function(turl,
                                  commentNo) {
-  get_comment_history(turl, commentNo, "all", "df")
+  news_comment_history(turl, commentNo, "all", "df")
 }
 
 #' @importFrom purrr when
 #' @importFrom httr2 req_perform
-get_comment_history <- function(turl,
+news_comment_history <- function(turl,
                                 commentNo,
                                 count = 10,
                                 type = c("df", "list")) {

diff --git a/R/getContent.R b/R/getContent.R
@@ -10,10 +10,22 @@
 #' @importFrom rvest html_nodes html_text html_attr
 #' @examples
 #' \dontrun{
-#'   getContent("https://n.news.naver.com/mnews/article/214/0001195110?sid=103")
+#'   news_content_("https://n.news.naver.com/mnews/article/214/0001195110?sid=103")
 #'   }
+getContent <-   function(turl,
+                         col = c("url",
+                                 "original_url",
+                                 "section",
+                                 "datetime",
+                                 "edittime",
+                                 "press",
+                                 "title",
+                                 "body",
+                                 "value")) {
+  news_content(turl, col)
+}
 
-getContent <-
+news_content <-
   function(turl,
            col = c("url",
                    "original_url",
@@ -65,13 +77,13 @@ getContent <-
       }
     }
     if (value) {
-      original_url <- getOriginalUrl(html_obj)
-      title <- getContentTitle(html_obj)
-      datetime <- getContentDatetime(html_obj)
-      edittime <- getContentEditDatetime(html_obj)
-      press <- getContentPress(html_obj)
-      body <- getContentBody(html_obj)
-      section <- getSection(turl)
+      original_url <- news_content_original_url(html_obj)
+      title <- news_content_title(html_obj)
+      datetime <- news_content_datetime(html_obj)
+      edittime <- news_content_edit_datetime(html_obj)
+      press <- news_content_press(html_obj)
+      body <- news_content_body(html_obj)
+      section <- news_content_section(turl)
     }
 
     if (length(edittime) == 0) {
@@ -91,7 +103,7 @@ getContent <-
     return(newsInfo[, col])
   }
 
-getContentTitle <-
+news_content_title <-
   function(html_obj,
            title_node_info = "h2.media_end_head_headline",
            title_attr = "") {
@@ -104,7 +116,7 @@ getContentTitle <-
   }
 
 
-getContentDatetime <-
+news_content_datetime <-
   function(html_obj,
            datetime_node_info = "span._ARTICLE_DATE_TIME",
            datetime_attr = "data-date-time") {
@@ -116,7 +128,7 @@ getContentDatetime <-
     as.POSIXct(datetime, tz = "Asia/Seoul")
   }
 
-getContentEditDatetime <-
+news_content_edit_datetime <-
   function(html_obj,
            datetime_node_info = "span._ARTICLE_MODIFY_DATE_TIME",
            datetime_attr = "data-modify-date-time") {
@@ -128,7 +140,7 @@ getContentEditDatetime <-
     as.POSIXct(datetime, tz = "Asia/Seoul")
   }
 
-getContentPress <-
+news_content_press <-
   function(html_obj,
            press_node_info = "div.media_end_head_top a img",
            press_attr = "title") {
@@ -140,7 +152,7 @@ getContentPress <-
     return(press[1])
   }
 
-getContentBody <-
+news_content_body <-
   function(html_obj,
            body_node_info = "div#dic_area",
            body_attr = "") {
@@ -153,7 +165,7 @@ getContentBody <-
     return(body)
   }
 
-getOriginalUrl <-   function(html_obj,
+news_content_original_url <-   function(html_obj,
                              origin_url_node_info = "a.media_end_head_origin_link",
                              origin_url_attr = "href") {
   node <- rvest::html_nodes(html_obj, origin_url_node_info)
@@ -166,7 +178,7 @@ getOriginalUrl <-   function(html_obj,
 }
 
 #' @importFrom httr2 url_parse
-getSection <- function(turl) {
+news_content_section <- function(turl) {
   if (is.null(httr2::url_parse(turl)$query$sid)) {
     return(NA)
   }

diff --git a/R/getMaxPageNum.R b/R/getMaxPageNum.R
@@ -11,8 +11,10 @@
 #' \dontrun{
 #'   getMaxPageNum("https://news.naver.com/main/list.naver?mode=LS2D&mid=shm&sid1=103&sid2=376")
 #'   }
-
 getMaxPageNum <- function(turl, max = 100) {
+  news_max_page_num(turl, max)
+}
+news_max_page_num <- function(turl, max = 100) {
   httr2::request(turl) %>%
     httr2::req_url_query(page = max) %>%
     httr2::req_method("GET") %>%

diff --git a/R/getUrlList.R b/R/getUrlList.R
@@ -13,7 +13,12 @@
 #'   getUrlList("https://news.naver.com/main/list.naver?mode=LS2D&mid=shm&sid1=103&sid2=376")
 #'   }
 
-getUrlList <-
+getUrlList <- function(turl,
+                       col = c("titles", "links")) {
+  news_urls_from_list(turl, col)
+}
+
+news_urls_from_list <-
   function(turl,
            col = c("titles", "links")) {
 

diff --git a/R/sysdata.rda b/R/sysdata.rda
diff --git a/data-raw/news_category.R b/data-raw/news_category.R
diff --git a/data-raw/news_category_data.R b/data-raw/news_category_data.R
@@ -0,0 +1,6 @@
+## code to prepare `news_category` dataset goes here
+library(N2H4)
+
+news_category_data <- getCategory(fresh = TRUE)
+
+usethis::use_data(news_category_data, overwrite = TRUE, internal = TRUE)
diff --git a/man/getContent.Rd b/man/getContent.Rd
diff --git a/tests/testthat/test-func.R b/tests/testthat/test-func.R
@@ -75,7 +75,7 @@ test_that("passSportsnews", {
 
 test_that("getCategory", {
   test <- getCategory()
-  expect_equal(test, news_category)
+  expect_equal(test, news_category_data)
 })
 
 test_that("getCategoryFresh", {