DATA 607 Assignment 9

Slection of the libraries:

library(httr)
library(jsonlite)
library(knitr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyverse)

## ── Attaching packages ───────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.2.1     ✔ readr   1.3.1
## ✔ tibble  2.1.3     ✔ purrr   0.3.2
## ✔ tidyr   1.0.0     ✔ stringr 1.4.0
## ✔ ggplot2 3.2.1     ✔ forcats 0.4.0

## ── Conflicts ──────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter()  masks stats::filter()
## ✖ purrr::flatten() masks jsonlite::flatten()
## ✖ dplyr::lag()     masks stats::lag()

The code to extract the articles based on the mention of HIV in them from the dates of Jan 01, 2016 to Oct 31, 2019.

apikey <- '1pHIViwXgD31sA9yA5uvfIkyi8wv7Zn0'

path <- "http://api.nytimes.com/svc/search/v2/articlesearch.json"
# install.packages("httr")
library(httr)
r <- GET(path, query=list(q="HIV",
                              "api-key"=apikey,
                              "begin_date"=20160101,
                              "end_date"=20191031))
response <- content(r, as = "text", encoding = "UTF-8")

Creation of a dataframe using from JSON:

df <- fromJSON(response, flatten = TRUE) %>% 
  data.frame()

head(df)

nrow(df)

## [1] 10

Selection and renaming of columns of interest:

df2 <- select(df, Date = response.docs.pub_date, Source = response.docs.source, 
              Section = response.docs.section_name, "Word Count" = response.docs.word_count,  URL =
                response.docs.web_url)

df2