| library(RKorAPClient) |
| library(tidyverse) |
| library(urltools) |
| VC = "" # no virtual corpus, i.e. all texts |
| deliko <- KorAPConnection("https://korap.dnb.de", verbose = TRUE) |
| query <- corpusQuery( |
| deliko, |
| "<base/s=t>", |
| # this finds each text once |
| vc = VC, |
| fields = c( |
| "textSigle", |
| "title", |
| "subTitle", |
| "author", |
| "textType", |
| "textTypeRef", |
| "publisher", |
| "pubDate", |
| "pubPlace", |
| "ISBN", |
| "URN", |
| "award" |
| ) |
| ) %>% |
| fetchAll() |
| |
| df <- query@collectedMatches %>% |
| mutate(publisher = str_replace_all(publisher, "data:,", ""), |
| URN = URLdecode(str_replace_all(URN, ".*,", ""))) %>% |
| select(-c("matchStart", "matchEnd")) |
| |
| write_tsv(df, "deliko_metadata.tsv") |