\n \n \n \n \n\n
\n \n \n \n
  def<\/span> self<\/span>.<\/span>scrape<\/span><\/div> <\/div>    merb<\/span> =<\/span> 'http://github.com/wycats/merb/commits/1.0.x'<\/span><\/div>    negotiation<\/span> =<\/span> 'http://github.com/wycats/rails/commits/master'<\/span><\/div>    blog<\/span>=<\/span> 'http://yehudakatz.com'<\/span><\/div> <\/div>    self<\/span>.<\/span>get_commits_and_bark<\/span>(<\/span>merb<\/span>,<\/span> "edgemerb"<\/span>)<\/span><\/div>    self<\/span>.<\/span>get_commits_and_bark<\/span>(<\/span>negotiation<\/span>,<\/span> "wycats_rails"<\/span>)<\/span><\/div>    self<\/span>.<\/span>get_blog_and_bark<\/span>(<\/span>blog<\/span>)<\/span><\/div>  end<\/span>    <\/div>    <\/div> <\/div>#parsing github commits <\/span><\/div>  def<\/span> self<\/span>.<\/span>get_commits_and_bark<\/span>(<\/span>url<\/span>,<\/span> category<\/span>)<\/span><\/div>    temp<\/span> =<\/span> []<\/span>      <\/div>    @doc<\/span>  =<\/span> Nokogiri<\/span>::<\/span>HTML<\/span>(<\/span>open<\/span>(<\/span>url<\/span>))<\/span><\/div>    @doc<\/span>.<\/span>css<\/span>(<\/span>'div.human'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>h<\/span>|<\/span><\/div>      h<\/span>.<\/span>search<\/span>(<\/span>'div.message'<\/span>)<\/span>.<\/span>each<\/span> {<\/span>|<\/span>k<\/span>|<\/span> @message<\/span> =<\/span> k<\/span>.<\/span>content<\/span>}<\/span><\/div>      h<\/span>.<\/span>search<\/span>(<\/span>'div.name'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>k<\/span>|<\/span> <\/div>        @name<\/span> =<\/span>  (<\/span>k<\/span>.<\/span>content<\/span>)<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>" (author)"<\/span>,<\/span> ""<\/span>)<\/span>.<\/span>gsub<\/span>(<\/span>"(committer)"<\/span>,<\/span>""<\/span>)<\/span><\/div>      end<\/span><\/div>      h<\/span>.<\/span>search<\/span>(<\/span>'div.date'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>k<\/span>|<\/span> <\/div>         @date<\/span> =<\/span> k<\/span>.<\/span>content<\/span><\/div>         @new_date<\/span> =<\/span> Time<\/span>.<\/span>parse<\/span>(<\/span>@date<\/span>.<\/span>strip<\/span>)<\/span><\/div>      end<\/span><\/div>      h<\/span>.<\/span>search<\/span>(<\/span>'pre a[href]'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>k<\/span>|<\/span> <\/div>       @link<\/span> =<\/span>  (<\/span>k<\/span>.<\/span>attributes<\/span>)<\/span><\/div>         begin<\/span><\/div>           @new_link<\/span> =<\/span>  ShortURL<\/span>.<\/span>shorten<\/span>(<\/span>"http://github.com"<\/span> +<\/span> @link<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>"href"<\/span>,<\/span> ''<\/span>),<\/span> :rubyurl<\/span>)<\/span><\/div>         rescue<\/span>  =><\/span> e<\/span><\/div>           @new_link<\/span> =<\/span>  ShortURL<\/span>.<\/span>shorten<\/span>(<\/span>"http://github.com"<\/span> +<\/span> @link<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>"href"<\/span>,<\/span> ''<\/span>),<\/span> :tinyurl<\/span>)<\/span><\/div>         rescue<\/span> Timeout<\/span>::<\/span>Error<\/span> =><\/span> e<\/span><\/div>          @new_link<\/span> =<\/span>  "http://github.com"<\/span> +<\/span> @link<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>"href"<\/span>,<\/span> ''<\/span>)<\/span><\/div>         end<\/span><\/div>      end<\/span><\/div>      temp<\/span> <<<\/span>{<\/span>:message<\/span> =><\/span> @message<\/span>,<\/span> :name<\/span> =><\/span> @name<\/span>,<\/span> :date<\/span> =><\/span> @new_date<\/span>,<\/span> :link<\/span> =><\/span> @new_link<\/span>,<\/span> :category<\/span> =><\/span> category<\/span>}<\/span>           <\/div>    end<\/span>  <\/div>      temp<\/span>.<\/span>slice!<\/span>(<\/span>4<\/span>,<\/span> temp<\/span>.<\/span>length<\/span>)<\/span> <\/div>      temp<\/span>.<\/span>sort_by<\/span>{<\/span>|<\/span>a<\/span>|<\/span> a<\/span>[<\/span>:date<\/span>]<\/span>}<\/span>.<\/span>each<\/span> do<\/span> |<\/span>data<\/span>|<\/span><\/div>       self<\/span>.<\/span>save_this<\/span>(<\/span>data<\/span>)<\/span><\/div>      end<\/span><\/div>  end<\/span><\/div> <\/div> <\/div>  <\/div>#parsing a blog  <\/span><\/div>  def<\/span> self<\/span>.<\/span>get_blog_and_bark<\/span>(<\/span>url<\/span>)<\/span><\/div>      temp<\/span> =<\/span> []<\/span><\/div>      @doc<\/span>  =<\/span> Nokogiri<\/span>::<\/span>HTML<\/span>(<\/span>open<\/span>(<\/span>url<\/span>))<\/span><\/div>      @doc<\/span>.<\/span>css<\/span>(<\/span>'div.entry'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>h<\/span>|<\/span><\/div>        @name<\/span> =<\/span> "Katz"<\/span><\/div>        h<\/span>.<\/span>search<\/span>(<\/span>'h3.entrytitle'<\/span>)<\/span>.<\/span>each<\/span> {<\/span>|<\/span>k<\/span>|<\/span> @title<\/span> =<\/span> k<\/span>.<\/span>content<\/span> }<\/span>        <\/div>        h<\/span>.<\/span>search<\/span>(<\/span>'h3 a[href]'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>k<\/span>|<\/span> <\/div>          @link<\/span> =<\/span>  (<\/span>k<\/span>.<\/span>attributes<\/span>)<\/span><\/div>           begin<\/span><\/div>             @new_link<\/span> =<\/span>  ShortURL<\/span>.<\/span>shorten<\/span>(<\/span>@link<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>"href"<\/span>,<\/span> ''<\/span>)<\/span>.<\/span>gsub<\/span>(<\/span>'relbookmark'<\/span>,<\/span>''<\/span>),<\/span> :rubyurl<\/span>)<\/span><\/div>           rescue<\/span>  =><\/span> e<\/span><\/div>             @new_link<\/span> =<\/span>  ShortURL<\/span>.<\/span>shorten<\/span>(<\/span>@link<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>"href"<\/span>,<\/span> ''<\/span>)<\/span>.<\/span>gsub<\/span>(<\/span>'relbookmark'<\/span>,<\/span>''<\/span>),<\/span> :tinyurl<\/span>)<\/span><\/div>           rescue<\/span> Timeout<\/span>::<\/span>Error<\/span> =><\/span> e<\/span><\/div>             @new_link<\/span> =<\/span> @link<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>"href"<\/span>,<\/span> ''<\/span>)<\/span>.<\/span>gsub<\/span>(<\/span>'relbookmark'<\/span>,<\/span>''<\/span>)<\/span><\/div>           end<\/span>          <\/div>        end<\/span><\/div>        h<\/span>.<\/span>search<\/span>(<\/span>'div.meta'<\/span>)<\/span>.<\/span>each<\/span> do<\/span> |<\/span>k<\/span>|<\/span> <\/div>          @date<\/span> =<\/span> k<\/span>.<\/span>attributes<\/span><\/div>          @new_date<\/span> =<\/span> Time<\/span>.<\/span>parse<\/span>(<\/span>@date<\/span>.<\/span>to_s<\/span>.<\/span>strip<\/span>.<\/span>gsub<\/span>(<\/span>" Posted"<\/span>,<\/span> ""<\/span>)<\/span>.<\/span>gsub<\/span>(<\/span>" Comments("<\/span>,<\/span>""<\/span>)<\/span>.<\/span>gsub<\/span>(<\/span>")"<\/span>,<\/span>""<\/span>))<\/span><\/div>        end<\/span><\/div>        temp<\/span><<<\/span>{<\/span>:message<\/span> =><\/span> @title<\/span>,<\/span> :name<\/span> =><\/span> @name<\/span>,<\/span> :date<\/span>=><\/span> @new_date<\/span>,<\/span> :category<\/span> =><\/span> "Katz's blog"<\/span>,<\/span> :link<\/span> =><\/span> @new_link<\/span>}<\/span><\/div>      end<\/span><\/div>      temp<\/span>.<\/span>slice!<\/span>(<\/span>4<\/span>,<\/span> temp<\/span>.<\/span>length<\/span>)<\/span> <\/div> <\/div> <\/div>      temp<\/span>.<\/span>sort_by<\/span>{<\/span>|<\/span>a<\/span>|<\/span> a<\/span>[<\/span>:date<\/span>]<\/span>}<\/span>.<\/span>each<\/span> do<\/span> |<\/span>data<\/span>|<\/span><\/div>       self<\/span>.<\/span>save_this<\/span>(<\/span>data<\/span>)<\/span><\/div>      end<\/span><\/div>  end<\/span><\/div> <\/div> <\/div>  def<\/span> self<\/span>.<\/span>save_this<\/span>(<\/span>data<\/span>)<\/span>  <\/div>    @tweet<\/span> =<\/span> self<\/span>.<\/span>new<\/span>(<\/span>data<\/span>)<\/span><\/div>    if<\/span> @tweet<\/span>.<\/span>save<\/span><\/div>      puts<\/span> "succeed to save them"<\/span><\/div>        begin<\/span><\/div>         self<\/span>.<\/span>post<\/span>(<\/span>data<\/span>)<\/span><\/div>        rescue<\/span> Twitter<\/span>::<\/span>RESTError<\/span> =><\/span> re<\/span><\/div>          unless<\/span> re<\/span>.<\/span>code<\/span> ==<\/span> "403"<\/span><\/div>            puts<\/span> re<\/span><\/div>          end<\/span><\/div>        end<\/span> #begin-rescue end <\/span><\/div>    else<\/span><\/div>      puts<\/span> "failed to save them"<\/span><\/div>    end<\/span>    <\/div>    return<\/span> @tweet<\/span><\/div>  end<\/span><\/div>  <\/div>  def<\/span> self<\/span>.<\/span>post<\/span>(<\/span>tweet<\/span>)<\/span><\/div>    @poster<\/span> =<\/span> String<\/span>.<\/span>new<\/span><\/div>    @poster<\/span> =<\/span> '['<\/span> +<\/span> tweet<\/span>[<\/span>:category<\/span>]<\/span> +<\/span> ']'<\/span> +<\/span> tweet<\/span>[<\/span>:message<\/span>]<\/span> +<\/span>'('<\/span>+<\/span> tweet<\/span>[<\/span>:name<\/span>]<\/span>  +<\/span>')'<\/span>+<\/span> tweet<\/span>[<\/span>:link<\/span>]<\/span><\/div>     STARLING<\/span>.<\/span>set<\/span>(<\/span>'twitter_post'<\/span>,<\/span> {<\/span>:send<\/span> =><\/span> @poster<\/span>})<\/span><\/div>  end<\/span><\/div><\/pre><\/div>\n          \n        <\/div>\n\n        \n          view raw<\/a>\n          parsing.rb<\/a>\n          This Gist<\/a> brought to you by GitHub<\/a>.\n        <\/div>\n      <\/div>\n    \n  \n<\/div>\n')