Using a New York Times API in R: Approach

Overview

For this assignment, I plan to use the New York Times Most Popular API to explore which newspaper sections appear most often among its most-viewed articles over the past seven days. I am interested in seeing which topics are most represented in that list.

I will request the data in R, convert the JSON response into a clean data frame, and count the articles in each section. These counts will describe the articles returned by the API, rather than the total number of views each section received.

Selected API and Request

I plan to use the Most Popular API’s most-viewed endpoint:

https://api.nytimes.com/svc/mostpopular/v2/viewed/7.json

The 7 specifies a seven-day period. I will create an account through the New York Times Developer Portal, enable the Most Popular API for my application, and obtain an API key.

I will store the key in an environment variable named NYT_API_KEY and access it in R using Sys.getenv("NYT_API_KEY"). The key will not appear in my Quarto document, GitHub repository, or published output.

Planned Approach

I will use httr2 to send the request and check whether it was successful. Then I will parse the JSON response and extract the article records into a data frame.

I plan to keep the article title, section, publication date, author byline, and URL. I will use dplyr to count the articles in each section and arrange the results from highest to lowest. A summary table and bar chart will show which sections appear most often in the returned list.

Data-Cleaning Decisions

I will convert publication dates into R’s date format and check for missing or blank section names. Articles without a section will be labeled “Unknown” so they remain included in the counts.

The response may contain nested information, such as multimedia details. I will leave out fields that are not needed for my question and keep one row per article.

Anticipated Challenges

The main challenges may be setting up the API key, handling request errors, and finding the article records within the JSON response. I will check the response before transforming it and avoid displaying my key in any output.

The most-viewed list changes over time, so running the same request on another day may produce different results. I will record when I retrieved the data to give the findings context.

Expected Outcome

The final result will include a tidy article data frame, a table of article counts by section, and a bar chart. I will use these outputs to answer which sections are most represented in the seven-day most-viewed list. I will also explain that this is a snapshot of the returned articles and does not measure total readership.