Last active
March 9, 2020 14:24
-
-
Save TimTaylor/300f92c3f294bc6a8b1f3f3476b9da29 to your computer and use it in GitHub Desktop.
scrape uk covid updates
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(rvest) | |
# parameters | |
url <- "https://www.gov.uk/government/publications/coronavirus-covid-19-number-of-cases-in-england/coronavirus-covid-19-number-of-cases-in-england" | |
filename <- "~/cases.csv" | |
# get data | |
html <- read_html(url) | |
overview <- html_text(html_nodes(html, "#contents p:nth-child(1)"), trim = TRUE) | |
headings <- html_text(html_nodes(html, "th, th"), trim = TRUE) | |
content <- html_text(html_nodes(html, "td"), trim = TRUE) | |
authority <- content[c(TRUE, FALSE)] | |
cases <- as.integer(content[c(FALSE, TRUE)]) | |
table <- data.frame(authority, as.integer(cases), stringsAsFactors = FALSE) | |
colnames(table) <- headings | |
cat(overview) | |
# save table to file | |
write.csv(table, filename, row.names = FALSE) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment