From 39ae3a9edcf31ee9af0357290a71733835d74c0a Mon Sep 17 00:00:00 2001
From: Lukas Gehrke <lukasgehrke@Lukass-MacBook-Pro.local>
Date: Thu, 3 Jan 2019 14:23:10 +0100
Subject: [PATCH] Aendert Documentation.
---
r/GetBirthdate.R | 46 +++++++++++++++++++++++++---------------------
1 file changed, 25 insertions(+), 21 deletions(-)
diff --git a/r/GetBirthdate.R b/r/GetBirthdate.R
index dbe0cdd..efe63b1 100644
--- a/r/GetBirthdate.R
+++ b/r/GetBirthdate.R
@@ -1,56 +1,57 @@
#!/usr/bin/env Rscript
-### Extracts birthdate fronm the infobox
-### If there is no infobox the Introduction text can be checked
# Author: Lukas
-## Librarys
-
library(rvest)
library(stringr)
library(data.table)
-### Try to extract birthdate from infobox
-### If there is no infobox, try to extract from introduction text
+#' Extract birthdate from infobox
+#' Will try to get infobox as table and extract birthdate
+#' from 'Born'-entry
+#' If there is no infobox, first paragraph of the article
+#' will be checked for birthdate
+#'
+#' @param article Article in HTML-format
+#' @return String birthdate as string
getBirthdate <- function(article) {
- # check
+ # Check if there is an infobox
if(!grepl("vcard", article)) {
- # check first paragraph
+ # Check first paragraph
introduction <- getIntroduction(article)
if(!introduction == "") {
- # get birthdate inside of parentheses
+ # Get birthdate inside of parentheses
birthdate <- str_extract_all(introduction, "\\([^()]+\\)")[[1]]
- # remove parentheses
+ # Remove parentheses
birthdate <- substring(birthdate, 2, nchar(birthdate)-1)
} else {
- # retrun Null if there is no birthdate
+ # Retrun Null if there is no birthdate
return(0)
}
}
- # try to get birthdate via infobox
+ # Try to get birthdate via infobox
infoBox <- getInfoBox(article)
- # get the born field
+ # Get the born field
birthdate <- infoBox[infoBox$Desc %like% "Born",]$Content
- # remove everything except the birthdate
- # remove everything in round brackets
+ # Remove everything except the birthdate
+ # Remove everything in round brackets
birthdate <- gsub("\\s*\\([^\\)]+\\)", "", birthdate)
- # remove everything starting with newline
+ # Remove everything starting with newline
birthdate <- gsub("\\n.*$", "", birthdate)
return(birthdate)
}
-### Uses Davids function to get infobox
### Converts info box to table
getInfoBox <- function(article) {
# Read page as html
page <- read_html(article)
# Extracting text from the html will erase all <br> tags,
- # this will replace them with line breaks
+ # This will replace them with line breaks
xml_find_all(page, ".//br") %>%
xml_add_sibling("p", "\n")
@@ -71,7 +72,10 @@ getInfoBox <- function(article) {
return(table)
}
-### Get Introduction Text from Wikipedia page that contains birthdate
+#' Get Introduction Text from Wikipedia page that contains birthdate
+#'
+#' @param article article in HTML-format
+#' @return string introduction text from wikipedia article
getIntroduction <- function(article) {
# Read page as html
page <- read_html(article)
@@ -90,8 +94,8 @@ getIntroduction <- function(article) {
html_nodes("p") %>%
html_text()
- # there will be some leading paragraphs containing only "\n"
- # remove those leading paragraphs
+ # There will be some leading paragraphs containing only "\n"
+ # Remove those leading paragraphs
remove <- c("\n")
cleaned <- setdiff(paragraphs, remove)
introduction <- cleaned[1]
--
GitLab