Scrape the performance data from ROH collections

roh_performances_scraper.R

library(rvest)

# URL: http://www.rohcollections.org.uk/SearchResults.aspx?searchtype=performance&page=0&genre=Opera

performances <- c()
for (i in 0:233){
  site_perf <- paste0("http://www.rohcollections.org.uk/SearchResults.aspx?searchtype=performance&page=",
                      i,
                      "&genre=Opera")
  print(site_perf) # optional print to see the progress
  html_perf <- read_html(site_perf)
  cast_perf <- html_nodes(html_perf, "tr td") %>% html_text()
  performances <- append(performances, cast_perf)
}

# turn into a data frame - splits the vector into a 4-column DF
perfdf <- as.data.frame(matrix(performances, ncol = 4, byrow = T))
colnames(perfdf) <- c("Title", "Date", "DayTime", "Company") # rename columns

# turn Date column into date type
perfdf$Date <- as.Date(perfdf$Date, format = "%d %B %Y")

write.csv(perfdf, "perfdf.csv", row.names = F)