| # I will try to post a longer handout, but here is the needed code for accessing nytimes. | |
| # See also: https://github.com/mkearney/nytimes | |
| # 1. Install the package from github: | |
| install.packages("devtools") | |
| devtools::install_github("mkearney/nytimes") | |
| # 2. Get an API key from nytimes | |
| # - create an account at https://developer.nytimes.com/accounts/create | |
| # - activate the account from your email and log in | |
| # - create a new 'app' (in your username menu) and select article search API | |
| # - record the API key and enter it below: | |
| Sys.setenv("NYTIMES_KEY"="...") | |
| # 3. Search! | |
| library(nytimes) | |
| nytsearch <- data.frame.search(nyt_search("sanctions", n = 20)) | |
| # To convert to a quanteda dfm: | |
| library(quanteda) | |
| corp = corpus(nytsearch, docid_field = "id", text_field="lead_paragraph") | |
| dfm = dfm(corp, remove=stopwords("english"), remove_punct=T) | |
| textplot_wordcloud(dfm, max_words=100) | |
| # If you want to convert to tidyverse, first convert date to POSIXct | |
| library(tidyverse) | |
| nytsearch$pub_date = as.POSIXct(nytsearch$pub_date) | |
| nytsearch = as_tibble(nytsearch) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment