summaryrefslogtreecommitdiff
path: root/data/rbot/plugins/url.rb
blob: b7e10b3d57965b442dca52a6f02c3fc802b0651a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
require 'net/http'
require 'uri'
require 'cgi'

Url = Struct.new("Url", :channel, :nick, :time, :url)
TITLE_RE = /<\s*?title\s*?>(.+?)<\s*?\/title\s*?>/im

class UrlPlugin < Plugin
  BotConfig.register BotConfigIntegerValue.new('url.max_urls',
    :default => 100, :validate => Proc.new{|v| v > 0},
    :desc => "Maximum number of urls to store. New urls replace oldest ones.")
  BotConfig.register BotConfigBooleanValue.new('url.display_link_info',
    :default => true, 
    :desc => "Get the title of any links pasted to the channel and display it (also tells if the link is broken or the site is down)")
  
  def initialize
    super
    @registry.set_default(Array.new)
  end

  def help(plugin, topic="")
    "urls [<max>=4] => list <max> last urls mentioned in current channel, urls search [<max>=4] <regexp> => search for matching urls. In a private message, you must specify the channel to query, eg. urls <channel> [max], urls search <channel> [max] <regexp>"
  end

  def get_title_from_html(pagedata)
    return unless TITLE_RE.match(pagedata)
    title = $1.strip.gsub(/\s*\n+\s*/, " ")
    title = CGI::unescapeHTML title
    title = title[0..255] if title.length > 255
    "[Link Info] title: #{title}"
  end

  def get_title_for_url(uri_str)
    # This god-awful mess is what the ruby http library has reduced me to.
    # Python's HTTP lib is so much nicer. :~(
    
    puts "+ Getting #{uri_str}"
    url = URI.parse(uri_str)
    return if url.scheme !~ /https?/
    
    puts "+ connecting to #{url.host}:#{url.port}"
    http = @bot.httputil.get_proxy(url) 
    title = http.start do |http|
      url.path = '/' if url.path == ''
      head = http.request_head(url.path)
      case head
        when Net::HTTPRedirection then
          # call self recursively if this is a redirect
          redirect_to = head['location']
          puts "+ redirect location: #{redirect_to}"
          absolute_uris = URI.extract redirect_to
          raise "wtf! redirect = #{redirect_to}" if absolute_uris.size > 1
          if absolute_uris.size == 1
            url = URI.parse absolute_uris[0]
          else
            url.path = redirect_to
          end
          puts "+ whee, redirect to #{url.to_s}!"
          title = get_title_for_url(url.to_s)
        when Net::HTTPSuccess then
          if head['content-type'] =~ /^text\//
            # content is 'text/*'
            # retrieve the title from the page
            puts "+ getting #{url.path}"
            response = http.request_get(url.path)
            return get_title_from_html(response.body)
          else
            # content isn't 'text/*'... display info about the file.
            size = head['content-length'].gsub(/(\d)(?=\d{3}+(?:\.|$))(\d{3}\..*)?/,'\1,\2')
            #lastmod = head['last-modified']
            return "[Link Info] type: #{head['content-type']}#{size ? ", size: #{size} bytes" : ""}"
          end
        when Net::HTTPClientError then
          return "[Link Info] Error getting link (#{head.code} - #{head.message})"
        when Net::HTTPServerError then
          return "[Link Info] Error getting link (#{head.code} - #{head.message})"
      end
    end
  rescue SocketError => e
    return "[Link Info] Error connecting to site (#{e.message})"
  end

  def listen(m)
    return unless m.kind_of?(PrivMessage)
    return if m.address?
    # TODO support multiple urls in one line
    if m.message =~ /(f|ht)tps?:\/\//
      if m.message =~ /((f|ht)tps?:\/\/.*?)(?:\s+|$)/
        urlstr = $1
        list = @registry[m.target]

        if @bot.config['url.say_titles']
          debug "Getting title for #{urlstr}..."
          title = get_title_for_url urlstr
          if title
            m.reply title
            debug "Title found!"
          else
            debug "Title not found!"
          end        
        end
    
        # check to see if this url is already listed
        return if list.find {|u| u.url == urlstr }
        
        url = Url.new(m.target, m.sourcenick, Time.new, urlstr)
        debug "#{list.length} urls so far"
        if list.length > @bot.config['url.max_urls']
          list.pop
        end
        debug "storing url #{url.url}"
        list.unshift url
        debug "#{list.length} urls now"
        @registry[m.target] = list
      end
    end
  end

  def urls(m, params)
    channel = params[:channel] ? params[:channel] : m.target
    max = params[:limit].to_i
    max = 10 if max > 10
    max = 1 if max < 1
    list = @registry[channel]
    if list.empty?
      m.reply "no urls seen yet for channel #{channel}"
    else
      list[0..(max-1)].each do |url|
        m.reply "[#{url.time.strftime('%Y/%m/%d %H:%M:%S')}] <#{url.nick}> #{url.url}"
      end
    end
  end

  def search(m, params)
    channel = params[:channel] ? params[:channel] : m.target
    max = params[:limit].to_i
    string = params[:string]
    max = 10 if max > 10
    max = 1 if max < 1
    regex = Regexp.new(string)
    list = @registry[channel].find_all {|url|
      regex.match(url.url) || regex.match(url.nick)
    }
    if list.empty?
      m.reply "no matches for channel #{channel}"
    else
      list[0..(max-1)].each do |url|
        m.reply "[#{url.time.strftime('%Y/%m/%d %H:%M:%S')}] <#{url.nick}> #{url.url}"
      end
    end
  end
end
plugin = UrlPlugin.new
plugin.map 'urls search :channel :limit :string', :action => 'search',
                          :defaults => {:limit => 4},
                          :requirements => {:limit => /^\d+$/},
                          :public => false
plugin.map 'urls search :limit :string', :action => 'search',
                          :defaults => {:limit => 4},
                          :requirements => {:limit => /^\d+$/},
                          :private => false
plugin.map 'urls :channel :limit', :defaults => {:limit => 4},
                          :requirements => {:limit => /^\d+$/},
                          :public => false
plugin.map 'urls :limit', :defaults => {:limit => 4},
                          :requirements => {:limit => /^\d+$/},
                          :private => false