Created
April 10, 2021 00:34
-
-
Save dubsnipe/a27eeaa808e5fcc65df49932c96d625b to your computer and use it in GitHub Desktop.
Script to extract infoboxes from Appropedia dumps
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require(xml2, quietly=T) | |
require(tidyverse, quietly=T) | |
require(lubridate, quietly=T) | |
require(tidytext, quietly=T) | |
require(stringr, quietly=T) | |
pages <- read_xml("Appropedia-20210409194434.xml") | |
pages_list <- as_list(pages) | |
pages_tibble <- as_tibble( | |
sapply(pages_list[[1]], function(x){ | |
unlist(c( | |
if(is.list(x$title)) x$title else NA, | |
if(is.list(x$id)) x$id else NA, | |
if(is.list(x$revision$id)) x$revision$id else NA, | |
if(is.list(x$revision$parentid)) x$revision$parentid else NA, | |
if(is.list(x$revision$timestamp)) x$revision$timestamp else NA, | |
if(is.list(x$revision$contributor$username)) x$revision$contributor$username else NA, | |
if(is.list(x$revision$text) & length(x$revision$text)>0) as.character(x$revision$text) else NA, | |
if(is.list(x$revision$minor)) T else F | |
))}), .name_repair = "minimal") | |
# https://stackoverflow.com/questions/42790219/how-do-i-transpose-a-tibble-in-r | |
pages_trans <- as_tibble(t(pages_tibble), name_repair = "minimal") | |
tibble_names <- c("title", | |
"id", | |
"revision_id", | |
"parent_id", | |
"timestamp", | |
"username", | |
"text", | |
"is_minor" | |
) | |
colnames(pages_trans) <- tibble_names | |
all_pages <- pages_trans | |
all_pages$timestamp <- as_date(all_pages$timestamp) | |
pages <- all_pages %>% select(title, text) | |
infoboxes <- pages$text %>% str_extract("\\{\\{Infobox device([^\\}\\}]*)\\}\\}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment