diff --git a/processing/wikiproc/R/get_birthdate.R b/processing/wikiproc/R/get_birthdate.R index 09f243e43ac8b035282127d22b130adc66b4c988..a316ca2e2c40317d361184d837c1d732d36a602c 100644 --- a/processing/wikiproc/R/get_birthdate.R +++ b/processing/wikiproc/R/get_birthdate.R @@ -63,7 +63,7 @@ getIntroduction <- function(article) { xml2::xml_add_sibling("p", "\n") xml2::xml_find_all(page, ".//br") %>% - xml2::xml_remove + xml2::xml_remove(.) # Get all paragraphs paragraphs <- page %>% @@ -73,7 +73,7 @@ getIntroduction <- function(article) { # There will be some leading paragraphs containing only "\n" # Remove those leading paragraphs remove <- c("\n") - cleaned <- data.table::setdiff(paragraphs, remove) + cleaned <- setdiff(paragraphs, remove) introduction <- cleaned[1] # Return first paragraph diff --git a/processing/wikiproc/R/utils.R b/processing/wikiproc/R/utils.R index a44ba86b6ce56472e5669c727f55b72a4720235d..f4b088cbf20d54aceaa01103229508a1775ca36b 100644 --- a/processing/wikiproc/R/utils.R +++ b/processing/wikiproc/R/utils.R @@ -26,8 +26,8 @@ get_infobox <- function(article) { xml2::xml_add_sibling("p", "\n") xml2::xml_find_all(page, ".//br") %>% - xml2::xml_remove() - + xml2::xml_remove(.) + # Get the info box # Will throw an error if there isnt any, so that should be checked beforehand