escape pacman

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: paperboy
 Title: Comprehensive Collection of News Media Scrapers
 Version: 0.0.5.9000
-Date: 2023-10-25
+Date: 2023-10-26
 Authors@R:
     person(given = "Johannes B.",
            family = "Gruber",

R/deliver.R

@@ -66,17 +66,20 @@ pb_deliver.data.frame <- function(x, try_default = TRUE, verbose = NULL, ...) {
   pb <- NULL
   if (verbose) {
     oldstyle <- getOption("cli.progress_bar_style")
+    oldstyle_ascii <- getOption("cli.progress_bar_style_ascii")
     options(cli.progress_bar_style = list(
-      current = cli::col_yellow("ᗧ"),
+      current = cli::col_yellow("\u15E7"),
+      complete = cli::col_grey("\u2010"),
+      incomplete = cli::col_red("\u2022")
+    ))
+    options(cli.progress_bar_style_ascii = list(
+      current = cli::col_yellow("C"),
       complete = cli::col_grey("-"),
       incomplete = cli::col_grey("o")
     ))
     pb <- cli::cli_progress_bar("Parsing raw html:", total = nrow(x))
   }
 
-
-
-
   out <- purrr::list_rbind(purrr::map(domains, function(u) {
 
     class(u) <- c(
@@ -96,6 +99,7 @@ pb_deliver.data.frame <- function(x, try_default = TRUE, verbose = NULL, ...) {
   if (verbose) {
     cli::cli_progress_done()
     options(cli.progress_bar_style = oldstyle)
+    options(cli.progress_bar_style_ascii = oldstyle_ascii)
   }
 
   # tell user about warnings

R/deliver_parlamentnilisty_cz.R

@@ -1,13 +1,14 @@
 pb_deliver_paper.parlamentnilisty_cz <- function(x, verbose = NULL, pb, ...) {
 
   # raw html is stored in column content_raw
-  html <- rvest::read_html(x$content_raw)
+  html <- rvest::read_html(charToRaw(enc2utf8(x$content_raw)))
   pb_tick(x, verbose, pb)
 
   # data about the article is nicely stored in a json string
   data <- html %>%
     rvest::html_elements("[type=\"application/ld+json\"]") %>%
     rvest::html_text() %>%
+    gsub("[\r\n]", "", .) %>% # sometimes uses illegal line breaks
     lapply(jsonlite::fromJSON, simplifyVector = FALSE)
 
   # usually there are more than one,