Matt Lieber Is

mattlieberis

library(rvest)
library(dplyr)
library(stringr)

toMatch <- "Matt Lieber is"

# Try with first page
url <- "https://gimletmedia.com/show/reply-all/episodes/"
pgfull <- read_html(url)
texts <- pgfull %>% 
  html_nodes(".feedItem~ .feedItem+ .feedItem .primary-color , .feedItem:nth-child(1) .primary-color") %>%
  html_attr("href") %>%
  xml2::url_absolute(url)

p1 <- lapply(texts, . %>% read_html() %>% html_text())
p1 <- as.character(unlist(p1))
p1 <- unlist(strsplit(p1,split="\\."))[grep(paste(toMatch, collapse="|"),unlist(strsplit(p1,split="\\.")))]
p1

# Functionalize
getallpages <- function(pgno) {
    url <- paste0("https://gimletmedia.com/show/reply-all/episodes/page/", pgno)
pgfull <- read_html(url)
try(
    texts <- pgfull %>% 
      html_nodes(".feedItem~ .feedItem+ .feedItem .primary-color , .feedItem:nth-child(1) .primary-color") %>%
      html_attr("href") %>%
      xml2::url_absolute(url)
   )
p1 <- lapply(texts, . %>% read_html() %>% html_text())
p1 <- as.character(unlist(p1))
toMatch <- "Matt Lieber is"
unlist(strsplit(p1,split="\\."))[grep(paste(toMatch, collapse="|"),unlist(strsplit(p1,split="\\.")))]
}

pgnos <- c(2:8)
total <- lapply(pgnos, getallpages)
phrases <- unlist(total)

phrases <- c(phrases, p1)

# Anonymize list:

blank <- str_replace(phrases, "\n", '')
blank <- str_replace(blank, "Matt Lieber", '')
blank <- str_trim(blank, side = "left")
blank

blankdf <- data.frame(x = blank)
head(blankdf)

save(blankdf, file = "blanks.Rda") # becomes the template for the internal dataframe in the MattLiebeR package