library(httr)
## Warning: package 'httr' was built under R version 4.4.2
library(jsonlite)
## Warning: package 'jsonlite' was built under R version 4.4.2
library(tidyverse)
## Warning: package 'ggplot2' was built under R version 4.4.2
## Warning: package 'dplyr' was built under R version 4.4.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ purrr::flatten() masks jsonlite::flatten()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(kableExtra)
## Warning: package 'kableExtra' was built under R version 4.4.2
##
## Attaching package: 'kableExtra'
##
## The following object is masked from 'package:dplyr':
##
## group_rows
library(dplyr)
dotenv::load_dot_env(file = '.env')
Sys.getenv('my_key')
## [1] "oJaiGJzQtRpzC4t73LcoxAMAPVOvXG08"
url <- paste0("https://api.nytimes.com/svc/mostpopular/v2/viewed/7.json?api-key=", Sys.getenv('my_key'))
response <- httr::GET(url)
str(response)
## List of 10
## $ url : chr "https://api.nytimes.com/svc/mostpopular/v2/viewed/7.json?api-key=oJaiGJzQtRpzC4t73LcoxAMAPVOvXG08"
## $ status_code: int 200
## $ headers :List of 25
## ..$ date : chr "Mon, 11 Nov 2024 06:33:21 GMT"
## ..$ content-type : chr "application/json; charset=utf-8"
## ..$ transfer-encoding : chr "chunked"
## ..$ connection : chr "keep-alive"
## ..$ cache-control : chr "max-age=60"
## ..$ x-nyt-most-popular-values : chr "VIEWED 7"
## ..$ x-request-id : chr "9eedd427-2157-4941-a2e3-4ea2f3b9b4d1"
## ..$ x-envoy-upstream-service-time: chr "234"
## ..$ server : chr "envoy"
## ..$ content-encoding : chr "gzip"
## ..$ x-envoy-decorator-operation : chr "trending-api.publishing.nyti.nyt.net:443/*"
## ..$ accept-ranges : chr "bytes"
## ..$ via : chr "1.1 varnish"
## ..$ age : chr "37"
## ..$ x-served-by : chr "cache-iad-kjyo7100175-IAD"
## ..$ x-cache : chr "HIT"
## ..$ x-cache-hits : chr "1"
## ..$ x-timer : chr "S1731306802.671933,VS0,VE1"
## ..$ vary : chr "Accept-Encoding"
## ..$ x-nyt-mktg-group : chr "group1"
## ..$ access-control-allow-origin : chr "*"
## ..$ access-control-allow-headers : chr "Accept, Content-Type, X-Forwarded-For, X-Prototype-Version, X-Requested-With"
## ..$ access-control-expose-headers: chr "Content-Length, X-JSON"
## ..$ access-control-allow-methods : chr "GET, OPTIONS"
## ..$ strict-transport-security : chr "max-age=63072000; preload; includeSubdomains"
## ..- attr(*, "class")= chr [1:2] "insensitive" "list"
## $ all_headers:List of 1
## ..$ :List of 3
## .. ..$ status : int 200
## .. ..$ version: chr "HTTP/1.1"
## .. ..$ headers:List of 25
## .. .. ..$ date : chr "Mon, 11 Nov 2024 06:33:21 GMT"
## .. .. ..$ content-type : chr "application/json; charset=utf-8"
## .. .. ..$ transfer-encoding : chr "chunked"
## .. .. ..$ connection : chr "keep-alive"
## .. .. ..$ cache-control : chr "max-age=60"
## .. .. ..$ x-nyt-most-popular-values : chr "VIEWED 7"
## .. .. ..$ x-request-id : chr "9eedd427-2157-4941-a2e3-4ea2f3b9b4d1"
## .. .. ..$ x-envoy-upstream-service-time: chr "234"
## .. .. ..$ server : chr "envoy"
## .. .. ..$ content-encoding : chr "gzip"
## .. .. ..$ x-envoy-decorator-operation : chr "trending-api.publishing.nyti.nyt.net:443/*"
## .. .. ..$ accept-ranges : chr "bytes"
## .. .. ..$ via : chr "1.1 varnish"
## .. .. ..$ age : chr "37"
## .. .. ..$ x-served-by : chr "cache-iad-kjyo7100175-IAD"
## .. .. ..$ x-cache : chr "HIT"
## .. .. ..$ x-cache-hits : chr "1"
## .. .. ..$ x-timer : chr "S1731306802.671933,VS0,VE1"
## .. .. ..$ vary : chr "Accept-Encoding"
## .. .. ..$ x-nyt-mktg-group : chr "group1"
## .. .. ..$ access-control-allow-origin : chr "*"
## .. .. ..$ access-control-allow-headers : chr "Accept, Content-Type, X-Forwarded-For, X-Prototype-Version, X-Requested-With"
## .. .. ..$ access-control-expose-headers: chr "Content-Length, X-JSON"
## .. .. ..$ access-control-allow-methods : chr "GET, OPTIONS"
## .. .. ..$ strict-transport-security : chr "max-age=63072000; preload; includeSubdomains"
## .. .. ..- attr(*, "class")= chr [1:2] "insensitive" "list"
## $ cookies :'data.frame': 0 obs. of 7 variables:
## ..$ domain : logi(0)
## ..$ flag : logi(0)
## ..$ path : logi(0)
## ..$ secure : logi(0)
## ..$ expiration: 'POSIXct' num(0)
## ..$ name : logi(0)
## ..$ value : logi(0)
## $ content : raw [1:39921] 7b 22 73 74 ...
## $ date : POSIXct[1:1], format: "2024-11-11 06:33:21"
## $ times : Named num [1:6] 0 0.0402 0.0752 0.2391 0.5283 ...
## ..- attr(*, "names")= chr [1:6] "redirect" "namelookup" "connect" "pretransfer" ...
## $ request :List of 7
## ..$ method : chr "GET"
## ..$ url : chr "https://api.nytimes.com/svc/mostpopular/v2/viewed/7.json?api-key=oJaiGJzQtRpzC4t73LcoxAMAPVOvXG08"
## ..$ headers : Named chr "application/json, text/xml, application/xml, */*"
## .. ..- attr(*, "names")= chr "Accept"
## ..$ fields : NULL
## ..$ options :List of 2
## .. ..$ useragent: chr "libcurl/8.3.0 r-curl/5.2.1 httr/1.4.7"
## .. ..$ httpget : logi TRUE
## ..$ auth_token: NULL
## ..$ output : list()
## .. ..- attr(*, "class")= chr [1:2] "write_memory" "write_function"
## ..- attr(*, "class")= chr "request"
## $ handle :Class 'curl_handle' <externalptr>
## - attr(*, "class")= chr "response"
summary(response)
## Length Class Mode
## url 1 -none- character
## status_code 1 -none- numeric
## headers 25 insensitive list
## all_headers 1 -none- list
## cookies 7 data.frame list
## content 39921 -none- raw
## date 1 POSIXct numeric
## times 6 -none- numeric
## request 7 request list
## handle 1 curl_handle externalptr
mostpolular <- httr::content(response, as = "text", encoding = "UTF-8")
df <- fromJSON(mostpolular, flatten = TRUE)
df <- data.frame(df$results, stringsAsFactors = FALSE)
#Get column names
colnames(df)
## [1] "uri" "url" "id" "asset_id"
## [5] "source" "published_date" "updated" "section"
## [9] "subsection" "nytdsection" "adx_keywords" "column"
## [13] "byline" "type" "title" "abstract"
## [17] "des_facet" "org_facet" "per_facet" "geo_facet"
## [21] "media" "eta_id"
selected_columns <- df %>%
select(
uri,
url,
id,
asset_id,
source,
published_date,
updated,
section,
subsection,
nytdsection,
title,
abstract,
byline,
published_date,
section
)
# Preview the cleaned DataFrame
head(selected_columns)
## uri
## 1 nyt://interactive/82df359c-4a5d-5f5a-8e6f-84e3711a7485
## 2 nyt://article/657f574b-2765-5a32-a542-75c924ad9ac3
## 3 nyt://interactive/addf9b67-dc9d-5a4e-8f27-2207dae3f4e4
## 4 nyt://interactive/a5e2cc45-d3d9-5e19-bc3e-dc43088f5f1a
## 5 nyt://article/590c765c-dccf-5b10-87da-20da55afa5f8
## 6 nyt://interactive/2d44e623-26b0-521b-95fc-3069ebb0a81a
## url
## 1 https://www.nytimes.com/interactive/2024/11/05/us/elections/results-arizona-us-senate.html
## 2 https://www.nytimes.com/2024/11/08/us/politics/trump-musk-zelensky.html
## 3 https://www.nytimes.com/interactive/2024/us/elections/results-timing-presidential-race-calls.html
## 4 https://www.nytimes.com/interactive/2024/11/05/us/elections/results-arizona-president.html
## 5 https://www.nytimes.com/2024/11/06/us/politics/trump-america-election-victory.html
## 6 https://www.nytimes.com/interactive/2024/11/06/us/elections/results-house-races-tracker.html
## id asset_id source published_date updated section
## 1 0e+00 0e+00 New York Times 2024-11-05 2024-11-11 01:31:43 U.S.
## 2 1e+14 1e+14 New York Times 2024-11-08 2024-11-09 11:45:23 U.S.
## 3 1e+14 1e+14 New York Times 2024-11-01 2024-11-05 09:19:05 U.S.
## 4 0e+00 0e+00 New York Times 2024-11-05 2024-11-11 01:31:43 U.S.
## 5 1e+14 1e+14 New York Times 2024-11-06 2024-11-07 03:03:04 U.S.
## 6 1e+14 1e+14 New York Times 2024-11-06 2024-11-11 01:31:44 U.S.
## subsection nytdsection
## 1 2024 Elections u.s.
## 2 Politics u.s.
## 3 2024 Elections u.s.
## 4 2024 Elections u.s.
## 5 Politics u.s.
## 6 2024 Elections u.s.
## title
## 1 Arizona U.S. Senate Election Results
## 2 Trump Put Musk on Phone With Zelensky During Call
## 3 When to Expect Results in Each State on Election Night, and Beyond
## 4 Arizona Presidential Election Results
## 5 ‘Trump’s America’: Comeback Victory Signals a Different Kind of Country
## 6 Path to 218: Tracking the Remaining House Races
## abstract
## 1 Get live results and maps from the 2024 Arizona general election.
## 2 Elon Musk was with Donald Trump at Mar-a-Lago when the president-elect spoke with Ukraine’s leader. It is not clear if they discussed any change in U.S. policy toward Ukraine.
## 3 The Times surveyed election officials in all 50 states to learn how they will count the votes, and when we might know the outcome in the battleground states.
## 4 Get live results and maps from the 2024 Arizona general election.
## 5 In the end, Donald J. Trump is not the historical aberration some thought he was, but instead a transformational force reshaping the modern United States in his own image.
## 6 Follow the results in the undecided congressional districts in the race for House control.
## byline
## 1
## 2 By Maggie Haberman
## 3 By Alicia Parlapiano and Lazaro Gamio
## 4
## 5 By Peter Baker
## 6
NYTsection <- selected_columns%>%
group_by(section)%>%
summarise(num=n())%>%
arrange(desc(num))
print(NYTsection)
## # A tibble: 2 × 2
## section num
## <chr> <int>
## 1 U.S. 19
## 2 The Upshot 1
NYT <- selected_columns %>%
group_by(section) %>%
summarise(Count = n()) %>%
arrange(desc(Count))
ggplot(data = NYT, aes(x = reorder(section, Count), y = Count)) +
geom_bar(stat = "identity", fill = "orange") +
coord_flip() +
labs(
title = "Distribution of NYT Most Viewed Articles by Section",
x = "Section",
y = "Number of Articles"
) +
theme_minimal()
NYT_Publihsed_Date <- selected_columns %>%
group_by(published_date) %>%
summarise(num = n()) %>%
arrange(desc(num))
ggplot(data = NYT_Publihsed_Date, aes(x = published_date, y = num, fill = published_date))+ geom_bar(stat="identity", position="dodge") + ggtitle("Number of Polular Articles Recently Published on Facebook") + ylab("Frequency")+ geom_text(aes(label = num))+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
