Sha256: 6b76b356f2e2d0b817c7d1f8d9ef8e3a0303407a7ca9a9e7489290d93f3ce08a
Contents?: true
Size: 1.64 KB
Versions: 21
Compression:
Stored size: 1.64 KB
Contents
require 'open-uri'
require 'nokogiri'
module Scrapers
module Xkcd
XKCD_URL = "http://xkcd.com"
PUBDATE_FORMAT = "%F"
# Get the current or numbered xkcd comic
#
# +comic+ = (string) the number of the xkcd comic to
#retreive. Gets current comic if nil.
#
# returns hash containing comic info:
#
# {:title => "comic' title",
# :url => "url to comic",
# :img_src => "source url to comic image",
# :hover_text => "the hover (mouse-over) text",
# :pubdate => "publication date",
# }
#
def self.scrape(comic=nil)
results = Hash.new
url = URI.parse XKCD_URL
url.path = "/#{comic}/" unless comic.nil?
results[:url] = url.to_s
doc = Nokogiri::HTML(open(url.to_s))
comic = doc.at_css("#comic img")
results[:img_src] = comic.attr("src")
results[:img_title] = comic.attr("title")
results[:title] = results[:img_alt] = comic.attr("alt")
results[:pubdate] = get_pubdate(results[:img_src])
results
end
# Get the http header of the image file which reveals the last_modified date.
# We'll use this as the publication date.
def self.get_pubdate(url)
url = URI.parse(url.dup)
head_req = Net::HTTP::Head.new url
head = Net::HTTP.start(url.host, url.port) do |http|
http.request head_req
end
return Time.now.strftime(PUBDATE_FORMAT) if head["Last-Modified"].nil?
last_modified = Time.parse(head["Last-Modified"]) rescue nil
return Time.now.strftime(PUBDATE_FORMAT) if last_modified.nil?
last_modified.strftime(PUBDATE_FORMAT)
end
end
end
Version data entries
21 entries across 21 versions & 1 rubygems