Merge pull request #1 from hrbrmstr/master

Updating fork to master changes

DESCRIPTION

@@ -5,10 +5,12 @@ Version: 0.6.0
 Date: 2017-10-01
 Author: Bob Rudis (bob@rud.is)
 Authors@R: c(
-      person("Bob", "Rudis", email = "bob@rud.is", role = c("aut", "cre")),
+      person("Bob", "Rudis", email = "bob@rud.is", role = c("aut", "cre"), 
+           comment = c(ORCID = "0000-0001-5670-2640")),
       person("Abe", "Neuwirth", role = c("ctb")),
       person("Mike", "Gruszczynski", role = c("ctb"))
     )
+Encoding: UTF-8
 Maintainer: Bob Rudis <bob@rud.is>
 Description: The 'GDELT' Television Explorer (<http://television.gdeltproject.org/cgi-bin/iatv_ftxtsearch/iatv_ftxtsearch>) 
     provides a simple and straighforward interface for searching through current and historical
@@ -38,4 +40,4 @@ Imports:
     txtplot,
     readr,
     utils
-RoxygenNote: 6.0.1
+RoxygenNote: 6.0.1.9000

NAMESPACE

@@ -1,14 +1,12 @@
 # Generated by roxygen2: do not edit by hand
 
-S3method(print,newsflash)
+export(gd_top_trending)
+export(iatv_top_trending)
 export(list_chyrons)
 export(list_networks)
 export(query_tv)
 export(read_chyrons)
-export(top_text)
-export(top_trending)
-export(top_trending_range)
-export(view_clip)
+export(word_cloud)
 import(httr)
 importFrom(DT,datatable)
 importFrom(curl,curl_fetch_memory)

R/gd-top-trending.R

@@ -0,0 +1,8 @@
+#' Top Trending (GDELT)
+#'
+#' Retrieve current (last 15 minute) "top topics" being discussed on stations
+#' @export
+gd_top_trending <- function() {
+  query_tv("", mode = "TrendingTopics")
+}
+

R/networks.r

@@ -10,22 +10,25 @@
 #' the console by passing in \code{widget=FALSE}
 #'
 #' @export
+#' @param widget if `TRUE` then an HTML widget will be displayed to make it easier to
+#'        sift through stations/networks
+#' @return data frame
 #' @examples
 #' list_networks() # widget
-#' list_networks(FALSE) # console
-list_networks <- function(widget=interactive()) {
+#' print(list_networks(FALSE)) # no widget
+list_networks <- function(widget = interactive()) {
 
-  xml2::read_html("http://television.gdeltproject.org/cgi-bin/iatv_ftxtsearch/iatv_ftxtsearch") %>%
-    rvest::html_nodes("select[name='filter_network'] > option") -> networks
+  xdf <- jsonlite::fromJSON("https://api.gdeltproject.org/api/v2/tv/tv?mode=stationdetails&format=json")
 
-  detail_text <- rvest::html_text(networks) %>% gsub("=*> (.*)", "All \\1 (See individual networks for dates)", .)
+  xdf$station_details %>%
+  mutate(StartDate = as.Date(anytime::anytime(StartDate))) %>%
+    mutate(EndDate = as.Date(anytime::anytime(StartDate))) -> xdf
 
-  stri_match_all_regex(detail_text, "(.*) (\\(.*\\))") %>%
-    map_df(~tbl_df(setNames(as.list(.[,2:3]), c("network", "date_range")))) %>%
-    mutate(keyword=rvest::html_attr(networks, "value")) %>%
-    select(keyword, network, date_range) -> df
+  if (widget) DT::datatable(xdf)
 
-  if (widget) DT::datatable(df) else print(df, n=nrow(df))
+  class(xdf) <- c("tbl_df", "tbl", "data.frame")
+
+  xdf
 
 }
 

R/top-tending-range.r

@@ -1,4 +1,4 @@
-#' Top Trending Tables (Ranged)
+#' Top Trending Topics (Internet Archive TV Archive)
 #'
 #' Provide start & end times in current time zone and this function will generate
 #' the proper "every 15-second" values, convert them to GMT values and issue the queries,
@@ -20,16 +20,16 @@
 #' processed hours later).
 #'
 #' @md
-#' @param from,to start and end `POSIXct` values in **current** time zone.
+#' @param from,to start and end date/time ranges (will auto-convert if properly formatted strings)
 #' @param .progress show a progress bar? Defaukts to `TRUE` if in an interactive session.
+#' @note The times are auto-converted to GMT
 #' @export
 #' @examples
-#' # This gets the from/to times in current time zone
-#' from <- as.POSIXct("2017-09-08 18:00:00")
-#' to <- as.POSIXct("2017-09-09 06:00:00")
-#'
-#' top_trending_range(from, to)
-top_trending_range <-  function(from, to, .progress=interactive()) {
+#' top_trending("2017-09-08 18:00", "2017-09-09 06:00")
+iatv_top_trending <-  function(from, to, .progress=interactive()) {
+
+  from <- anytime::anytime(from)
+  to <- anytime::anytime(to)
 
   base_url <- "http://data.gdeltproject.org/gdeltv3/iatv_trending/%s.tvtrending.v3.15min.json"
 

R/word-cloud.R

@@ -0,0 +1,27 @@
+#' Retrieve top words that appear most frequently in clips matching your search
+#'
+#' The API takes the 200 most relevant clips that match your search and returns the
+#' terms for a "word cloud" of up to the top 200 most frequent words that appeared in
+#' those clips (common stop words are automatically removed). This is a powerful way
+#' of understanding the topics and words dominating the relevant coverage and
+#' suggesting additional contextual search terms to narrow or evolve your search.
+#' Note that if there are too few matching clips for your query, the word cloud may
+#' be blank.
+#'
+#' @md
+#' @param query query string in GDELT format. See `QUERY` in https://blog.gdeltproject.org/gdelt-2-0-television-api-debuts/
+#'     for details; use [list_networks()] to obtain valid station/network identifiers
+#' @param start_date,end_date start/end dates. Leaving both `NULL` searches all archive history.
+#'     Leaving just `start_date` `NULL` sets the start date to July 2009. Leaving just `end_date`
+#'     `NULL` sets the end date to today.
+#' @export
+word_cloud <- function(query, start_date = NULL, end_date = NULL) {
+
+  query_tv(
+    query = query,
+    mode = "WordCloud",
+    start_date = start_date,
+    end_date = end_date
+  )
+
+}

R/zzz.R

@@ -0,0 +1,5 @@
+.onLoad <- function(libname, pkgname) {
+
+  packageStartupMessage("NOTE: There are breaking changes to the package API due to GDELT's v2 API")
+
+}