Our great sponsors
-
english-words
:memo: A text file containing 479k English words for all your dictionary/word-based projects e.g: auto-completion / autosuggestion
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
# Packages library(tidyverse) library(googlesheets4) library(rvest) # Retrieve data from Google sheet sheet_URL = 'https://docs.google.com/spreadsheets/d/1tkOnw41zj7lQLonV-bEjJFszY5jSlMylmn9ntQO2qcA/edit#gid=0' sheet_id = gs4_get(sheet_URL) page_data = range_read(sheet_id) # Retrieve English dictionary dict = read.table(file = url("https://github.com/dwyl/english-words/raw/master/words_alpha.txt"), col.names = "words") %>% as_tibble() %>% mutate(condition = TRUE) # Read data from web pages and count words per page words_per_page = page_data %>% mutate(words = map(Page, ~return_words(web_page = .x))) %>% mutate(words = words %>% unlist()) # Output data to Google sheets sheet_write(words_per_page, sheet = 'output', ss = sheet_id) # Functions return_words = function(web_page){ words = web_page %>% read_html() %>% html_text() %>% # clean words for table tolower() %>% str_remove_all(pattern = '"') %>% str_remove_all(pattern = ",|:|\\.|\\\n") %>% strsplit(' ') %>% as_tibble('words') %>% set_names("words") %>% # join with English dictionary left_join(dict) %>% # keep only words from the english dictionary filter(condition == TRUE) %>% pull(condition) %>% sum() return(words) }