Created
April 11, 2013 09:59
-
-
Save pudo/5362165 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
events = require 'events' | |
request = require 'request' | |
cheerio = require 'cheerio' | |
externalize = (url) -> | |
return 'http://spiegel.de' + url | |
getChannels = () -> | |
ee = new events.EventEmitter() | |
request.get 'http://spiegel.de/', (err, res, body) -> | |
$ = cheerio.load body | |
channels = $ '#spHeader #spChannel li:first-child a' | |
for channel in channels | |
channel = $ channel | |
url = channel.attr 'href' | |
if -1 isnt url.search 'http' | |
continue | |
name = channel.text() | |
if name is 'NACHRICHTEN' | |
continue | |
ee.emit 'channel', url, name | |
return ee | |
getHeadlines = () -> | |
ee = new events.EventEmitter() | |
request.get 'http://www.spiegel.de/schlagzeilen/index-siebentage.html', (err, res, body) -> | |
$ = cheerio.load body | |
headlines = $ '#spMainContent .spMarkVisited a' | |
for headline in headlines | |
headline = $ headline | |
url = headline.attr 'href' | |
title = headline.attr 'title' | |
ee.emit 'headline', url, title | |
return ee | |
#feed = getHeadlines() | |
#feed.on 'headline', (url, title) -> | |
# console.log title + ' -- ' + url | |
getRankings = () -> | |
sample_time = new Date() | |
feed = getChannels() | |
feed.on 'channel', (url, name) -> | |
#if url isnt '/' | |
# return | |
extUrl = externalize url | |
request.get extUrl, (err, res, body) -> | |
$ = cheerio.load body | |
topics = $ '.spTopThema' | |
rank = 0 | |
for topic in topics | |
topic = $ topic | |
title = $ topic.find 'h2 a' | |
obj = | |
title: title.text() | |
url: title.attr 'href' | |
first: topic.hasClass 'spFirstTeaser' | |
listitem: false | |
channel_url: url | |
channel_name: name | |
time: sample_time | |
rank: rank | |
level: (url.split '/').length - 1 | |
console.log obj | |
for listitem in topic.find '.spDottedLinkList a' | |
listitem = $ listitem | |
obj.listitem = true | |
obj.title = listitem.attr 'title' | |
obj.url = listitem.attr 'href' | |
console.log obj | |
rank++ | |
getRankings() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment