R/find_BBC_fixture_sites.R

In JimmyClowes/wc2018SweepstakeStats: A package to scrape world cup 2018 stats from BBC sport and compile them

#' Function To Find Sites
#' 
#' This function finds all the individual sites for world cup fixtures
#' @keywords sites links fixtures
#' @importFrom rvest %>%
#' @export
#' @examples
#' find_BBC_fixture_sites()


find_BBC_fixture_sites <- function(){

standard_fixtures_url <- "https://www.bbc.co.uk/sport/football/world-cup/scores-fixtures/"
standard_fixtures_links <- standard_fixtures_url %>%
                            xml2::read_html() %>%
                            XML::htmlTreeParse(useInternalNodes = TRUE) %>%
                            XML::xpathSApply("//a[@href]", XML::xmlGetAttr, "href")

fixture_date_links <- standard_fixtures_links[grepl("scores\\-fixtures\\/2018",standard_fixtures_links)] %>%
                            paste0("https://bbc.co.uk",.)

all_fixture_refs <- character()

for (i in c(1:length(fixture_date_links))){
  
  fixtures_refs <- fixture_date_links[i] %>%
    xml2::read_html() %>%
    XML::htmlTreeParse(useInternalNodes = TRUE) %>%
    XML::xpathSApply("//a[@href]", XML::xmlGetAttr, "href") %>%
    .[grepl("sport\\/football\\/\\d+",.)]
  
  all_fixture_refs <- c(all_fixture_refs,fixtures_refs)
}

all_fixture_refs <- paste0("https://bbc.co.uk",all_fixture_refs)

all_fixture_refs
}