lovelybigdata

Web Scraping Workshop

Install our tools (preferably in a new virtualenv):

pip install beautifulsoup4

	library(shiny)
	library(leaflet)
	library(dplyr)

	# read data
	df_map <- read.delim("Sheet_R_MAP.csv",stringsAsFactors=FALSE)

	# define colorBin

	pal <- colorBin(palette=c("green","pink","red","purple"),domain=df_map$Pl,bins=c(0,5,10,15,70),pretty=TRUE,na.color="#808080",alpha=F)

	my_news = data.frame(
	title = html(news_url) %>% html_nodes(".picword") %>% html_text() ,
	title_href = html(news_url) %>% html_nodes(".picword") %>% html_attr( "href") ,
	stringsAsFactors=FALSE)

	library(rvest)
	news_url="http://news.ltn.com.tw/list/BreakingNews"
	title_css = html(news_url) %>% html_nodes(".picword") %>% html_text()
	my_news = data.frame(title = title_css)
	View(my_news)

	library(rvest)

	news_url="http://news.ltn.com.tw/list/BreakingNews"

	title_css = html(news_url) %>% html_nodes(".picword") %>% html_text()

	my_news = data.frame(title = title_css)

	View(my_news)

	// Use Gists to store code you would like to remember later on
	console.log(window); // log the "window" object to the console