使用Ruby和Nokogiri模拟爬虫导出RSS种子的实例详解

# encoding: utf-8
require &＃39;thread&＃39;
require &＃39;nokogiri&＃39;
require &＃39;open-uri&＃39;
require &＃39;rss/maker&＃39;
 
$result=Queue.new
def extract_readme_header(no,name,url)
  frame = Nokogiri::HTML(open(url))
  return unless frame
  readme=$url+frame.css(&＃39;frame&＃39;)[1][&＃39;src&＃39;]
  return unless readme
  open(readme) do |f|
    doc = Nokogiri::HTML(f.read)
    text=doc.css("p#content p#filecontents p")[0..4].map { |c| c.content }.join(" ").strip
    return if text.length==0
    if text !~ /(rails)|(activ_)/i
      puts "========= #{no} #{name} : #{text[0..50]}"
      date = f.last_modified
      $result <<[no,name,readme,date,text]
    end
  end
rescue
  puts $!.to_s
end
 
def make_rss(items)
  RSS::Maker.make("2.0") do |m|
    m.channel.title = "GtitHub recently updated projects"
    m.channel.link = "http://localhost"
    m.channel.description = "GitHub recently updated projects"
    m.items.do_sort = true
    items.each do |no,name,url,date,descr|
      i = m.items.new_item
      i.title = name
      i.link = url
      i.description=descr
      i.date = date
    end
  end
end
 
############################## M A I N ########################
 
############# Scan list of recent project
 
lth=[]
$url="http://rdoc.info"
puts "get url #{$url}..."
doc = Nokogiri::HTML(open($url))
doc.css(&＃39;ul.libraries&＃39;)[1].css(&＃39;li&＃39;).each_with_index do |li,i|
  aname =li.css(&＃39;a&＃39;).first
  name=aname.content
  purl=$url+aname[&＃39;href&＃39;]
  lth <0
result.sort!  { |a,b| a[0] <=> b[0] }
 
 
################ format results in rss
 
File.open("RubyFeeds.rss","w") do |file|
  file.write make_rss(result)
end

以上就是使用Ruby和Nokogiri模拟爬虫导出RSS种子的实例详解的详细内容，更多请关注 第一PHP社区 其它相关文章！