Get tweets from a user's timeline

get_twitter_time_dataframe.R

get_timeline_df <- function(user, n_tweets=200, oauth_sig) {  
  i <- 0
  n_left <- n_tweets
  timeline_df <- NULL
  #loop until n_tweets are all got
  while (n_left > 0) {
    n_to_get <- min(200, n_left)
    i <- i+1
    #incorporae max id in get_url (so as not to download same 200 tweets repeatedly)
    if (i==1) {
      get_url <- paste0("https://api.twitter.com/1.1/statuses/user_timeline.json?screen_name=",
      user,"&count=", n_to_get)
    } else {
      get_url <- paste0("https://api.twitter.com/1.1/statuses/user_timeline.json?screen_name=",
      user,"&count=",n_to_get,"&max_id=", max_id)
    }
    #GET tweets
    response <- httr::GET(get_url, oauth_sig)
    #extract content and clean up
    response_content <- httr::content(response)
    json_content     <- jsonlite::toJSON(response_content)
    #clean out evil special chars
    json_conv <- iconv(json_content, "UTF-8", "ASCII", sub = "") %>%
    stringr::str_replace_all("\003", "") #special character (^C) not caught by above   clean
    timeline_list <- jsonlite::fromJSON(json_conv)
    #extract desired fields
    fields_i_care_about <- c("id", "text", "favorite_count", "retweet_count",   "created_at")
    timeline_df <- purrr::map(fields_i_care_about, ~unlist(timeline_list[[.x]])) %>% 
    purrr::set_names(fields_i_care_about) %>% 
    dplyr::as_data_frame() %>% 
    dplyr::bind_rows(timeline_df) %>% 
    dplyr::distinct()
    #store min id (oldest tweet) to set as max id for next GET
    max_id <- min(purrr::map_dbl(timeline_list$id, 1))
    #update number of tweets left
    n_left <- n_left-n_to_get
  }
  return(timeline_df)
}