Class: Cobweb

Inherits:
Object
  • Object
show all
Defined in:
lib/cobweb.rb

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(options = {}) ⇒ Cobweb

Returns a new instance of Cobweb.



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
 
# File 'lib/cobweb.rb', line 35

def initialize(options = {})
  @options = options
  default_use_encoding_safe_process_job_to  false
  default_follow_redirects_to               true
  default_redirect_limit_to                 10
  default_processing_queue_to               CobwebProcessJob
  default_crawl_finished_queue_to           CobwebFinishedJob
  default_quiet_to                          true
  default_debug_to                          false
  default_cache_to                          300
  default_timeout_to                        10
  default_redis_options_to                  Hash.new
  default_internal_urls_to                  []
  default_first_page_redirect_internal_to   true
  
end

Dynamic Method Handling

This class handles dynamic methods through the method_missing method

#method_missing(method_sym, *arguments, &block) ⇒ Object 



26
27
28
29
30
31
32
33
 
# File 'lib/cobweb.rb', line 26

def method_missing(method_sym, *arguments, &block)
  if method_sym.to_s =~ /^default_(.*)_to$/
    tag_name = method_sym.to_s.split("_")[1..-2].join("_").to_sym
    @options[tag_name] = arguments[0] unless @options.has_key?(tag_name)
  else
    super
  end
end

Class Method Details

.version ⇒ Object

redesign to have a resque stack and a single threaded stack dry the code below, its got a lot of duplication detect the end of the crawl (queued == 0 ?) on end of crawl, return statistic hash (could call specified method ?) if single threaded or enqueue to a specified queue the stat hash investigate using event machine for single threaded crawling



22
23
24
 
# File 'lib/cobweb.rb', line 22

def self.version
  "0.0.39"
end

Instance Method Details

#deep_symbolize_keys(hash) ⇒ Object 



348
349
350
351
352
353
354
355
356
357
358
 
# File 'lib/cobweb.rb', line 348

def deep_symbolize_keys(hash)
  hash.keys.each do |key|
    value = hash[key]
    hash.delete(key)
    hash[key.to_sym] = value
    if hash[key.to_sym].instance_of? Hash
      hash[key.to_sym] = deep_symbolize_keys(hash[key.to_sym])
    end
  end
  hash
end

#get(url, options = @options) ⇒ Object 



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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
 
# File 'lib/cobweb.rb', line 79

def get(url, options = @options)
  raise "url cannot be nil" if url.nil?
  uri = Addressable::URI.parse(url)
  uri.fragment=nil
  url = uri.to_s

  # get the unique id for this request
  unique_id = Digest::SHA1.hexdigest(url.to_s)
  if options.has_key?(:redirect_limit) and !options[:redirect_limit].nil?
    redirect_limit = options[:redirect_limit].to_i
  else
    redirect_limit = 10
  end
  
  # connect to redis
  if options.has_key? :crawl_id
    redis = NamespacedRedis.new(@options[:redis_options], "cobweb-#{Cobweb.version}-#{options[:crawl_id]}")
  else
    redis = NamespacedRedis.new(@options[:redis_options], "cobweb-#{Cobweb.version}")
  end
  
  content = {:base_url => url}

  # check if it has already been cached
  if redis.get(unique_id) and @options[:cache]
    puts "Cache hit for #{url}" unless @options[:quiet]
    content = deep_symbolize_keys(Marshal.load(redis.get(unique_id)))
  else
    # this url is valid for processing so lets get on with it
    #TODO the @http here is different from in head.  Should it be? - in head we are using a method-scoped variable.

    # retrieve data
    unless @http && @http.address == uri.host && @http.port == uri.inferred_port
      puts "Creating connection to #{uri.host}..." unless @options[:quiet]
      @http = Net::HTTP.new(uri.host, uri.inferred_port)
    end
    if uri.scheme == "https"
      @http.use_ssl = true
      @http.verify_mode = OpenSSL::SSL::VERIFY_NONE
    end
    
    request_time = Time.now.to_f
    @http.read_timeout = @options[:timeout].to_i
    @http.open_timeout = @options[:timeout].to_i
    begin
      print "Retrieving #{url }... " unless @options[:quiet]
      request = Net::HTTP::Get.new uri.request_uri

      response = @http.request request
      
      if @options[:follow_redirects] and response.code.to_i >= 300 and response.code.to_i < 400
        puts "redirected... " unless @options[:quiet]
        
        # get location to redirect to
        url = UriHelper.join_no_fragment(uri, response['location'])
        
        # decrement redirect limit
        redirect_limit = redirect_limit - 1

        # raise exception if we're being redirected to somewhere we've been redirected to in this content request          
        #raise RedirectError("Loop detected in redirect for - #{url}") if content[:redirect_through].include? url
        
        # raise exception if redirect limit has reached 0
        raise RedirectError, "Redirect Limit reached" if redirect_limit == 0

        # get the content from redirect location
        content = get(url, options.merge(:redirect_limit => redirect_limit))
        content[:url] = uri.to_s
        content[:redirect_through] = [] if content[:redirect_through].nil?
        content[:redirect_through].insert(0, url)
      
        content[:response_time] = Time.now.to_f - request_time
      else
        content[:response_time] = Time.now.to_f - request_time
        
        puts "Retrieved." unless @options[:quiet]

        # create the content container
        content[:url] = uri.to_s
        content[:status_code] = response.code.to_i
        content[:mime_type] = ""
        content[:mime_type] = response.content_type.split(";")[0].strip unless response.content_type.nil?
        if !response["Content-Type"].nil? && response["Content-Type"].include?(";")
          charset = response["Content-Type"][response["Content-Type"].index(";")+2..-1] if !response["Content-Type"].nil? and response["Content-Type"].include?(";")
          charset = charset[charset.index("=")+1..-1] if charset and charset.include?("=")
          content[:character_set] = charset
        end
        content[:length] = response.content_length
        if content[:mime_type].include?("text/html") or content[:mime_type].include?("application/xhtml+xml")
          if response["Content-Encoding"]=="gzip"
            content[:body] = Zlib::GzipReader.new(StringIO.new(response.body)).read
          else
            content[:body] = response.body
          end
        else
          content[:body] = Base64.encode64(response.body)
        end
        content[:location] = response["location"]
        content[:headers] = deep_symbolize_keys(response.to_hash)
        # parse data for links
        link_parser = ContentLinkParser.new(content[:url], content[:body])
        content[:links] = link_parser.link_data
        
      end
      # add content to cache if required
      if @options[:cache]
        redis.set(unique_id, Marshal.dump(content))
        redis.expire unique_id, @options[:cache].to_i
      end
    rescue RedirectError => e
      puts "ERROR: #{e.message}"
      
      ## generate a blank content
      content = {}
      content[:url] = uri.to_s
      content[:response_time] = Time.now.to_f - request_time
      content[:status_code] = 0
      content[:length] = 0
      content[:body] = ""
      content[:error] = e.message
      content[:mime_type] = "error/dnslookup"
      content[:headers] = {}
      content[:links] = {}
      
    rescue SocketError => e
      puts "ERROR: SocketError#{e.message}"
      
      ## generate a blank content
      content = {}
      content[:url] = uri.to_s
      content[:response_time] = Time.now.to_f - request_time
      content[:status_code] = 0
      content[:length] = 0
      content[:body] = ""
      content[:error] = e.message
      content[:mime_type] = "error/dnslookup"
      content[:headers] = {}
      content[:links] = {}
    
    rescue Timeout::Error => e
      puts "ERROR Timeout::Error: #{e.message}"
      
      ## generate a blank content
      content = {}
      content[:url] = uri.to_s
      content[:response_time] = Time.now.to_f - request_time
      content[:status_code] = 0
      content[:length] = 0
      content[:body] = ""
      content[:error] = e.message
      content[:mime_type] = "error/serverdown"
      content[:headers] = {}
      content[:links] = {}
    end
  end
  content  
end

#head(url, options = @options) ⇒ Object 



237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
 
# File 'lib/cobweb.rb', line 237

def head(url, options = @options)
  raise "url cannot be nil" if url.nil?    
  uri = Addressable::URI.parse(url)
  uri.fragment=nil
  url = uri.to_s

  # get the unique id for this request
  unique_id = Digest::SHA1.hexdigest(url)
  if options.has_key?(:redirect_limit) and !options[:redirect_limit].nil?
    redirect_limit = options[:redirect_limit].to_i
  else
    redirect_limit = 10
  end
  
  # connect to redis
  if options.has_key? :crawl_id
    redis = NamespacedRedis.new(@options[:redis_options], "cobweb-#{Cobweb.version}-#{options[:crawl_id]}")
  else
    redis = NamespacedRedis.new(@options[:redis_options], "cobweb-#{Cobweb.version}")
  end
  
  content = {}
  
  # check if it has already been cached
  if redis.get("head-#{unique_id}") and @options[:cache]
    puts "Cache hit for #{url}" unless @options[:quiet]
    content = deep_symbolize_keys(Marshal.load(redis.get("head-#{unique_id}")))
  else
    print "Retrieving #{url }... " unless @options[:quiet]

    # retrieve data
    http = Net::HTTP.new(uri.host, uri.inferred_port)
    if uri.scheme == "https"
      http.use_ssl = true
      http.verify_mode = OpenSSL::SSL::VERIFY_NONE
    end 
    
    request_time = Time.now.to_f
    http.read_timeout = @options[:timeout].to_i
    http.open_timeout = @options[:timeout].to_i
    
    begin      
      request = Net::HTTP::Head.new uri.request_uri
      response = http.request request

      if @options[:follow_redirects] and response.code.to_i >= 300 and response.code.to_i < 400
        puts "redirected... " unless @options[:quiet]
        url = UriHelper.join_no_fragment(uri, response['location'])
        redirect_limit = redirect_limit - 1
        options = options.clone
        options[:redirect_limit]=redirect_limit
        content = head(url, options)
        content[:url] = uri.to_s
        content[:redirect_through] = [] if content[:redirect_through].nil?
        content[:redirect_through].insert(0, url)
      else
        content[:url] = uri.to_s
        content[:status_code] = response.code.to_i
        unless response.content_type.nil?
          content[:mime_type] = response.content_type.split(";")[0].strip 
          if response["Content-Type"].include? ";"
            charset = response["Content-Type"][response["Content-Type"].index(";")+2..-1] if !response["Content-Type"].nil? and response["Content-Type"].include?(";")
            charset = charset[charset.index("=")+1..-1] if charset and charset.include?("=")
            content[:character_set] = charset
          end
        end 
        
        # add content to cache if required
        if @options[:cache]
          puts "Stored in cache [head-#{unique_id}]" if @options[:debug]
          redis.set("head-#{unique_id}", Marshal.dump(content))
          redis.expire "head-#{unique_id}", @options[:cache].to_i
        else
          puts "Not storing in cache as cache disabled" if @options[:debug]
        end
      end
    rescue SocketError => e
      puts "ERROR: #{e.message}"
      
      ## generate a blank content
      content = {}
      content[:url] = uri.to_s
      content[:response_time] = Time.now.to_f - request_time
      content[:status_code] = 0
      content[:length] = 0
      content[:body] = ""
      content[:error] = e.message
      content[:mime_type] = "error/dnslookup"
      content[:headers] = {}
      content[:links] = {}
    
    rescue Timeout::Error => e
      puts "ERROR: #{e.message}"
      
      ## generate a blank content
      content = {}
      content[:url] = uri.to_s
      content[:response_time] = Time.now.to_f - request_time
      content[:status_code] = 0
      content[:length] = 0
      content[:body] = ""
      content[:error] = e.message
      content[:mime_type] = "error/serverdown"
      content[:headers] = {}
      content[:links] = {}
    end
    
    content
  end
end

#start(base_url) ⇒ Object 



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
 
# File 'lib/cobweb.rb', line 52

def start(base_url)
  raise ":base_url is required" unless base_url
  request = {
    :crawl_id => Digest::SHA1.hexdigest("#{Time.now.to_i}.#{Time.now.usec}"),
    :url => base_url 
  }  
  
  if @options[:internal_urls].empty?
    uri = Addressable::URI.parse(base_url)
    @options[:internal_urls] << [uri.scheme, "://", uri.host, "/*"].join
  end
  
  request.merge!(@options)
  @redis = NamespacedRedis.new(request[:redis_options], "cobweb-#{Cobweb.version}-#{request[:crawl_id]}")
  @redis.hset "statistics", "queued_at", DateTime.now
  @redis.set("crawl-counter", 0)
  @redis.set("queue-counter", 1)
  
  @stats = Stats.new(request)
  @stats.start_crawl(request)
  
  # add internal_urls into redis
  @options[:internal_urls].map{|url| @redis.sadd("internal_urls", url)}
  
  Resque.enqueue(CrawlJob, request)
end