ltn_news_crawler

ltn_news_crawler

library(rvest)

## Warning: package 'rvest' was built under R version 3.2.5

## Loading required package: xml2

library(stringr)
res <- read_html('http://news.ltn.com.tw/list/BreakingNews')
lipic <- res %>% html_nodes('li.lipic')
title <- lipic %>% html_nodes('a.picword') %>% 
    html_text() %>% iconv(from='UTF-8', to='UTF-8')
link <- lipic %>% html_nodes('a.picword') %>% 
    html_attr('href') 
dt <- lipic %>% html_nodes('span') %>% 
  html_text() 

category <- lipic %>% html_nodes('span a') %>% 
  html_attr('class') 


map_table = read_html('http://news.ltn.com.tw/css/news/style.css?201509', encoding='UTF-8') %>%
iconv(from='UTF-8', to='UTF-8') %>% 
str_match_all(pattern='.list span a.(.*?):after\\{content:"(.*?)";.*\\}', string =.)  

#map_table[[1]][,2]
#map_table[[1]][,3]

map_list = list()
map_list[map_table[[1]][,2]] = map_table[[1]][,3]
tag = map_list[category] %>% unlist()

ltn_news  = data.frame(datetime = dt, 
                       link = link, 
                       title = title,
                       category = tag)