better import of issuelist

2015-02-22 01:43:06 +01:00
parent 778ef2bcfb
commit 6f8ff3db25
2 changed files with 519 additions and 577 deletions
@@ -23,13 +23,15 @@ unlink(id_folder, recursive = TRUE)
 dir.create(id_folder)

 issues <- data.frame(date = drange)
-issuelist <- xmlToList("issues.xml")
+issuelist <- readLines("issues.xml")
+issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
+issuelist <- xmlToList(issuelist)
 issueheads <- names(issuelist)
 issues[issueheads] <- 0
 tweets$issue <- ""
 tweets$tags <- ""

-tagexpand <- c("", "s", "n", "en")
+tagexpand <- c("", "s", "n", "en", "er")

 for(d in 1:nrow(issues)) {
  # Go through every day