rcrawl 0.2.5
Sign up to get free protection for your applications and to get access to all the features.
- data/MIT-LICENSE +20 -0
- data/README +22 -0
- data/Rakefile +39 -0
- data/TODO +1 -0
- data/lib/rcrawl.rb +177 -0
- data/lib/robot_rules.rb +81 -0
- metadata +61 -0
data/MIT-LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2006 Shawn Hansen
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Rcrawl is intended to be a web crawler written entirely in ruby.
|
2
|
+
It's limited right now by the fact that it will stay on the original domain provided.
|
3
|
+
I decided to roll my own crawler in ruby after finding only snippets of code on
|
4
|
+
various web sites or newsgroups, for crawlers written in ruby.
|
5
|
+
|
6
|
+
The structure of the crawling process was inspired by the specs of the Mercator crawler (http://www.cindoc.csic.es/cybermetrics/pdf/68.pdf).
|
7
|
+
|
8
|
+
== Examples
|
9
|
+
bot = Rcrawl.new(url) # This instantiates a new Rcrawl object
|
10
|
+
|
11
|
+
bot.crawl # This will actually crawl the website
|
12
|
+
|
13
|
+
== After the bot is done crawling
|
14
|
+
bot.visited_links # Returns an array of visited links
|
15
|
+
|
16
|
+
bot.dump # Returns a hash where the key is a url and the value is
|
17
|
+
# the raw html from that url
|
18
|
+
|
19
|
+
bot.errors # Returns a hash where the key is a URL and the value is
|
20
|
+
# the error message from stderr
|
21
|
+
|
22
|
+
bot.external_links # Returns an array of external links
|
data/Rakefile
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
Gem::manage_gems
|
3
|
+
require 'rake'
|
4
|
+
require 'rake/rdoctask'
|
5
|
+
require 'rake/gempackagetask'
|
6
|
+
|
7
|
+
|
8
|
+
|
9
|
+
desc "Generate documentation"
|
10
|
+
Rake::RDocTask.new(:rdoc) do |rdoc|
|
11
|
+
rdoc.rdoc_dir = "rdoc"
|
12
|
+
rdoc.title = "Crawler"
|
13
|
+
rdoc.options << "--line-numbers"
|
14
|
+
rdoc.options << "--inline-source"
|
15
|
+
rdoc.rdoc_files.include("README")
|
16
|
+
rdoc.rdoc_files.include("lib/**/*.rb")
|
17
|
+
end
|
18
|
+
|
19
|
+
spec = Gem::Specification.new do |s|
|
20
|
+
s.name = "rcrawl"
|
21
|
+
s.version = "0.2.5"
|
22
|
+
s.author = "Shawn Hansen"
|
23
|
+
s.email = "shawn.hansen@gmail.com"
|
24
|
+
s.homepage = "http://blog.denomi.net"
|
25
|
+
s.platform = Gem::Platform::RUBY
|
26
|
+
s.summary = "A web crawler written in ruby"
|
27
|
+
s.files = FileList["{test,lib}/**/*", "README", "MIT-LICENSE", "Rakefile", "TODO"].to_a
|
28
|
+
s.require_path = "lib"
|
29
|
+
s.autorequire = "rcrawl.rb"
|
30
|
+
s.has_rdoc = true
|
31
|
+
s.extra_rdoc_files = ["README", "MIT-LICENSE", "TODO"]
|
32
|
+
s.add_dependency("scrapi", ">=1.2.0")
|
33
|
+
s.rubyforge_project = "rcrawl"
|
34
|
+
end
|
35
|
+
|
36
|
+
gem = Rake::GemPackageTask.new(spec) do |pkg|
|
37
|
+
pkg.need_tar = true
|
38
|
+
pkg.need_zip = true
|
39
|
+
end
|
data/lib/rcrawl.rb
ADDED
@@ -0,0 +1,177 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# rcrawl/0.2.0
|
3
|
+
|
4
|
+
require 'rubygems'
|
5
|
+
require 'open-uri'
|
6
|
+
require 'scrapi'
|
7
|
+
require 'robot_rules'
|
8
|
+
|
9
|
+
# Rcrawl will retrieve an entire website, one page at a time,
|
10
|
+
# parsing the page using whatever modules you pass it to.
|
11
|
+
class Rcrawl
|
12
|
+
|
13
|
+
# Initializes various variables when a new Rcrawl object is instantiated
|
14
|
+
def initialize(site)
|
15
|
+
@links_to_visit = Array.new
|
16
|
+
@visited_links = Array.new
|
17
|
+
@external_links = Array.new
|
18
|
+
@raw_html = Hash.new
|
19
|
+
@rules = RobotRules.new("Rcrawl")
|
20
|
+
@sites = Hash.new
|
21
|
+
@site = URI.parse(site)
|
22
|
+
@links_to_visit << site
|
23
|
+
@errors = Hash.new
|
24
|
+
puts "Site is #{site}"
|
25
|
+
end
|
26
|
+
|
27
|
+
# Coordinates the whole crawling process
|
28
|
+
def crawl
|
29
|
+
until @links_to_visit.empty? do
|
30
|
+
begin
|
31
|
+
# Get link
|
32
|
+
url_server
|
33
|
+
next unless robot_safe? @url
|
34
|
+
# Parse robots.txt, then download document if robot_safe
|
35
|
+
fetch_http(@url)
|
36
|
+
# Store raw HTML in variable to read/reread as needed
|
37
|
+
# Then call any processing modules you need for the current document
|
38
|
+
ris(@document)
|
39
|
+
rescue
|
40
|
+
puts ""
|
41
|
+
puts "I died on #{@url}"
|
42
|
+
$stderr.puts $!
|
43
|
+
@errors[@url] = $!
|
44
|
+
next
|
45
|
+
ensure
|
46
|
+
# Stuff you want to make sure gets printed out
|
47
|
+
puts " done!"
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
puts "Visited #{@visited_links.size} links."
|
52
|
+
end
|
53
|
+
|
54
|
+
# Authoritative list of URLs to be processed by Rcrawl
|
55
|
+
def url_server
|
56
|
+
unless @links_to_visit.empty?
|
57
|
+
@url = @links_to_visit.pop
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
# Download the document
|
62
|
+
def fetch_http(url)
|
63
|
+
# Make sure robots.txt has been parsed for this site first,
|
64
|
+
# if not, parse robots.txt then grab document.
|
65
|
+
uri = URI.parse(url)
|
66
|
+
print "Visiting: #{url}"
|
67
|
+
@document = uri.read
|
68
|
+
@visited_links << url
|
69
|
+
end
|
70
|
+
|
71
|
+
# Rewind Input Stream, for storing and reading of raw HTML
|
72
|
+
def ris(document)
|
73
|
+
# Store raw HTML into local variable
|
74
|
+
# Based on MIME type, invoke the proper processing modules
|
75
|
+
if document.content_type == "text/html"
|
76
|
+
print "."
|
77
|
+
link_extractor(document) # If HTML
|
78
|
+
process_html(document) # If HTML
|
79
|
+
else
|
80
|
+
print "... not HTML, skipping..."
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
# HTML processing module for extracting links
|
85
|
+
def link_extractor(document)
|
86
|
+
print "."
|
87
|
+
|
88
|
+
# Parse all links from HTML into an array
|
89
|
+
# Set up the scrAPI (http://labnotes.org)
|
90
|
+
links = Scraper.define do
|
91
|
+
array :urls
|
92
|
+
process "a[href]", :urls => "@href"
|
93
|
+
result :urls
|
94
|
+
end
|
95
|
+
|
96
|
+
urls = links.scrape(document)
|
97
|
+
|
98
|
+
urls.each { |url|
|
99
|
+
uri = URI.parse(url)
|
100
|
+
|
101
|
+
# Derelativeize links if necessary
|
102
|
+
if uri.relative?
|
103
|
+
url = @site.merge(url).to_s
|
104
|
+
uri = URI.parse(url)
|
105
|
+
end
|
106
|
+
|
107
|
+
# Check domain, if in same domain, keep link, else trash it
|
108
|
+
if uri.host != @site.host
|
109
|
+
@external_links << url
|
110
|
+
@external_links.uniq!
|
111
|
+
next
|
112
|
+
end
|
113
|
+
|
114
|
+
# Find out if we've seen this link already
|
115
|
+
if (@visited_links.include? url) || (@links_to_visit.include? url)
|
116
|
+
next
|
117
|
+
end
|
118
|
+
|
119
|
+
@links_to_visit << url
|
120
|
+
}
|
121
|
+
|
122
|
+
end
|
123
|
+
|
124
|
+
# HTML processing module for raw HTML storage
|
125
|
+
def process_html(document)
|
126
|
+
# Add link and raw HTML to a hash as key/value
|
127
|
+
# for later storage in database
|
128
|
+
unless @raw_html.has_value?(document)
|
129
|
+
print "."
|
130
|
+
@raw_html[document.base_uri] = document
|
131
|
+
end
|
132
|
+
end
|
133
|
+
|
134
|
+
# robots.txt parsing
|
135
|
+
def robot_safe?(url)
|
136
|
+
uri = URI.parse(url)
|
137
|
+
location = "#{uri.host}:#{uri.port}"
|
138
|
+
|
139
|
+
return true unless %w{http https}.include?(uri.scheme)
|
140
|
+
|
141
|
+
unless @sites.include? location
|
142
|
+
@sites[location] = true
|
143
|
+
|
144
|
+
robot_url = "http://#{location}/robots.txt"
|
145
|
+
begin
|
146
|
+
robot_file = open(robot_url) { |page| page.read }
|
147
|
+
rescue
|
148
|
+
return true
|
149
|
+
end
|
150
|
+
@rules.parse(robot_url, robot_file)
|
151
|
+
end
|
152
|
+
|
153
|
+
@rules.allowed? url
|
154
|
+
end
|
155
|
+
|
156
|
+
# Returns array of links visited during crawl
|
157
|
+
def visited_links
|
158
|
+
return @visited_links
|
159
|
+
end
|
160
|
+
|
161
|
+
# Returns array of external links
|
162
|
+
def external_links
|
163
|
+
return @external_links
|
164
|
+
end
|
165
|
+
|
166
|
+
# Returns a hash where {key => URL, value => HTML} from all pages crawled
|
167
|
+
def dump
|
168
|
+
return @raw_html
|
169
|
+
end
|
170
|
+
|
171
|
+
# Returns a hash where {key => URL, value => "Error message"} from any
|
172
|
+
# errors encountered during the crawl
|
173
|
+
def errors
|
174
|
+
return @errors
|
175
|
+
end
|
176
|
+
|
177
|
+
end
|
data/lib/robot_rules.rb
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# robot_rules.rb
|
4
|
+
#
|
5
|
+
# Created by James Edward Gray II on 2006-01-31.
|
6
|
+
# Copyright 2006 Gray Productions. All rights reserved.
|
7
|
+
# Included with rcrawl by permission from James Edward Gray II
|
8
|
+
|
9
|
+
require "uri"
|
10
|
+
|
11
|
+
# Based on Perl's WWW::RobotRules module, by Gisle Aas.
|
12
|
+
class RobotRules
|
13
|
+
def initialize( user_agent )
|
14
|
+
@user_agent = user_agent.scan(/\S+/).first.sub(%r{/.*},
|
15
|
+
"").downcase
|
16
|
+
@rules = Hash.new { |rules, rule| rules[rule] = Array.new }
|
17
|
+
end
|
18
|
+
|
19
|
+
def parse( text_uri, robots_data )
|
20
|
+
uri = URI.parse(text_uri)
|
21
|
+
location = "#{uri.host}:#{uri.port}"
|
22
|
+
@rules.delete(location)
|
23
|
+
|
24
|
+
rules = robots_data.split(/[\015\012]+/).
|
25
|
+
map { |rule| rule.sub(/\s*#.*$/, "") }
|
26
|
+
anon_rules = Array.new
|
27
|
+
my_rules = Array.new
|
28
|
+
current = anon_rules
|
29
|
+
rules.each do |rule|
|
30
|
+
case rule
|
31
|
+
when /^\s*User-Agent\s*:\s*(.+?)\s*$/i
|
32
|
+
break unless my_rules.empty?
|
33
|
+
|
34
|
+
current = if $1 == "*"
|
35
|
+
anon_rules
|
36
|
+
elsif $1.downcase.index(@user_agent)
|
37
|
+
my_rules
|
38
|
+
else
|
39
|
+
nil
|
40
|
+
end
|
41
|
+
when /^\s*Disallow\s*:\s*(.*?)\s*$/i
|
42
|
+
next if current.nil?
|
43
|
+
|
44
|
+
if $1.empty?
|
45
|
+
current << nil
|
46
|
+
else
|
47
|
+
disallow = URI.parse($1)
|
48
|
+
|
49
|
+
next unless disallow.scheme.nil? or disallow.scheme ==
|
50
|
+
uri.scheme
|
51
|
+
next unless disallow.port.nil? or disallow.port == uri.port
|
52
|
+
next unless disallow.host.nil? or
|
53
|
+
disallow.host.downcase == uri.host.downcase
|
54
|
+
|
55
|
+
disallow = disallow.path
|
56
|
+
disallow = "/" if disallow.empty?
|
57
|
+
disallow = "/#{disallow}" unless disallow[0] == ?/
|
58
|
+
|
59
|
+
current << disallow
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
@rules[location] = if my_rules.empty?
|
65
|
+
anon_rules.compact
|
66
|
+
else
|
67
|
+
my_rules.compact
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
def allowed?( text_uri )
|
72
|
+
uri = URI.parse(text_uri)
|
73
|
+
location = "#{uri.host}:#{uri.port}"
|
74
|
+
path = uri.path
|
75
|
+
|
76
|
+
return true unless %w{http https}.include?(uri.scheme)
|
77
|
+
|
78
|
+
not @rules[location].any? { |rule| path.index(rule) == 0 }
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
metadata
ADDED
@@ -0,0 +1,61 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
rubygems_version: 0.9.0
|
3
|
+
specification_version: 1
|
4
|
+
name: rcrawl
|
5
|
+
version: !ruby/object:Gem::Version
|
6
|
+
version: 0.2.5
|
7
|
+
date: 2006-09-20 00:00:00 -05:00
|
8
|
+
summary: A web crawler written in ruby
|
9
|
+
require_paths:
|
10
|
+
- lib
|
11
|
+
email: shawn.hansen@gmail.com
|
12
|
+
homepage: http://blog.denomi.net
|
13
|
+
rubyforge_project: rcrawl
|
14
|
+
description:
|
15
|
+
autorequire: rcrawl.rb
|
16
|
+
default_executable:
|
17
|
+
bindir: bin
|
18
|
+
has_rdoc: true
|
19
|
+
required_ruby_version: !ruby/object:Gem::Version::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">"
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.0.0
|
24
|
+
version:
|
25
|
+
platform: ruby
|
26
|
+
signing_key:
|
27
|
+
cert_chain:
|
28
|
+
post_install_message:
|
29
|
+
authors:
|
30
|
+
- Shawn Hansen
|
31
|
+
files:
|
32
|
+
- lib/rcrawl.rb
|
33
|
+
- lib/robot_rules.rb
|
34
|
+
- README
|
35
|
+
- MIT-LICENSE
|
36
|
+
- Rakefile
|
37
|
+
- TODO
|
38
|
+
test_files: []
|
39
|
+
|
40
|
+
rdoc_options: []
|
41
|
+
|
42
|
+
extra_rdoc_files:
|
43
|
+
- README
|
44
|
+
- MIT-LICENSE
|
45
|
+
- TODO
|
46
|
+
executables: []
|
47
|
+
|
48
|
+
extensions: []
|
49
|
+
|
50
|
+
requirements: []
|
51
|
+
|
52
|
+
dependencies:
|
53
|
+
- !ruby/object:Gem::Dependency
|
54
|
+
name: scrapi
|
55
|
+
version_requirement:
|
56
|
+
version_requirements: !ruby/object:Gem::Version::Requirement
|
57
|
+
requirements:
|
58
|
+
- - ">="
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: 1.2.0
|
61
|
+
version:
|