apollo-crawler 0.0.3 → 0.0.5
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/apollo_crawler/crawler.rb +0 -0
- data/lib/apollo_crawler/plugin.rb +37 -0
- data/lib/apollo_crawler/plugins/alexa_com/alexa.rb +36 -0
- data/lib/apollo_crawler/plugins/firmy_cz/firmy.rb +35 -0
- data/lib/apollo_crawler/plugins/slashdot_org/slashdot.rb +35 -0
- data/lib/apollo_crawler/plugins/ycombinator_com/hacker_news.rb +35 -0
- data/main.rb +170 -0
- metadata +9 -2
File without changes
|
@@ -0,0 +1,37 @@
|
|
1
|
+
require "open-uri"
|
2
|
+
require "nokogiri"
|
3
|
+
|
4
|
+
module Apollo
|
5
|
+
module Crawler
|
6
|
+
module Plugins
|
7
|
+
class Plugin
|
8
|
+
|
9
|
+
# Name of the plugin, used in docs, lookups, etc ...
|
10
|
+
def name
|
11
|
+
return "Plugin Base"
|
12
|
+
end
|
13
|
+
|
14
|
+
# - Fetch default URL (and transform it to document)
|
15
|
+
# - Extract and Load (Store) important data
|
16
|
+
# - Look for another documents
|
17
|
+
# Examples:
|
18
|
+
# - "next page"
|
19
|
+
# - "people you may know on Linked in"
|
20
|
+
# - "will attend on FB")
|
21
|
+
def run
|
22
|
+
return {
|
23
|
+
:plugin => self.class.name
|
24
|
+
}
|
25
|
+
end
|
26
|
+
|
27
|
+
# Extracts data from currently processed URL (called document here)
|
28
|
+
def extract_doc_data
|
29
|
+
end
|
30
|
+
|
31
|
+
# This function tries to get links of another URLs (called leaf here) to crawl
|
32
|
+
def fetch_leafs
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require File.join(F'..', '..', '..', 'plugin')
|
2
|
+
|
3
|
+
module Apollo
|
4
|
+
module Crawler
|
5
|
+
module Plugins
|
6
|
+
# PARAMATRIZE: Plugin class name
|
7
|
+
class Alexa < Plugin
|
8
|
+
@@URL = "http://www.alexa.com/"
|
9
|
+
|
10
|
+
@@MATCHER_ITEM = "//div[@id = 'alphabetically']/ul/li/a"
|
11
|
+
|
12
|
+
def name()
|
13
|
+
return "Alexa Rank"
|
14
|
+
end
|
15
|
+
|
16
|
+
def run()
|
17
|
+
# TODO: Encapsulate and make more robust => invalid hostname, timeouts and so
|
18
|
+
doc = Nokogiri::HTML(open(@@URL))
|
19
|
+
|
20
|
+
res = doc.xpath(@@MATCHER_ITEM).map { |i|
|
21
|
+
{
|
22
|
+
:text => i.text,
|
23
|
+
:link => URI.join(@@URL, i['href'])
|
24
|
+
}
|
25
|
+
}
|
26
|
+
|
27
|
+
return {
|
28
|
+
:plugin => self.class.name,
|
29
|
+
:title => doc.title,
|
30
|
+
:res => res
|
31
|
+
}
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end # Plugins
|
35
|
+
end # Crawler
|
36
|
+
end # Apollo
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require File.join('..', '..', '..', 'plugin')
|
2
|
+
|
3
|
+
module Apollo
|
4
|
+
module Crawler
|
5
|
+
module Plugins
|
6
|
+
# PARAMATRIZE: Plugin class name
|
7
|
+
class Firmy < Plugin
|
8
|
+
@@URL = "http://www.firmy.cz/"
|
9
|
+
|
10
|
+
@@MATCHER_ITEM = "//div[@id = 'alphabetically']/ul/li/a"
|
11
|
+
|
12
|
+
def name()
|
13
|
+
return "Firmy.cz"
|
14
|
+
end
|
15
|
+
|
16
|
+
def run()
|
17
|
+
doc = Nokogiri::HTML(open(@@URL))
|
18
|
+
|
19
|
+
res = doc.xpath(@@MATCHER_ITEM).map { |i|
|
20
|
+
{
|
21
|
+
:text => i.text,
|
22
|
+
:link => URI.join(@@URL, i['href'])
|
23
|
+
}
|
24
|
+
}
|
25
|
+
|
26
|
+
return {
|
27
|
+
:plugin => self.class.name,
|
28
|
+
:title => doc.title,
|
29
|
+
:res => res
|
30
|
+
}
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end # Plugins
|
34
|
+
end # Crawler
|
35
|
+
end # Apollo
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require File.join('..', '..', '..', 'plugin')
|
2
|
+
|
3
|
+
module Apollo
|
4
|
+
module Crawler
|
5
|
+
module Plugins
|
6
|
+
# PARAMATRIZE: Plugin class name
|
7
|
+
class Slashdot < Plugin
|
8
|
+
@@URL = "http://slashdot.org/"
|
9
|
+
|
10
|
+
@@MATCHER_ITEM = "//article/header/h2/span/a"
|
11
|
+
|
12
|
+
def name
|
13
|
+
return "Slashdot"
|
14
|
+
end
|
15
|
+
|
16
|
+
def run()
|
17
|
+
doc = Nokogiri::HTML(open(@@URL))
|
18
|
+
|
19
|
+
res = doc.xpath(@@MATCHER_ITEM).map { |i|
|
20
|
+
{
|
21
|
+
:text => i.text,
|
22
|
+
:link => URI.join(@@URL, i['href'])
|
23
|
+
}
|
24
|
+
}
|
25
|
+
|
26
|
+
return {
|
27
|
+
:plugin => self.class.name,
|
28
|
+
:title => doc.title,
|
29
|
+
:res => res
|
30
|
+
}
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end # Plugins
|
34
|
+
end # Crawler
|
35
|
+
end # Apollo
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require File.join('..', '..', '..', 'plugin')
|
2
|
+
|
3
|
+
module Apollo
|
4
|
+
module Crawler
|
5
|
+
module Plugins
|
6
|
+
# PARAMATRIZE: Plugin class name
|
7
|
+
class HackerNews < Plugin
|
8
|
+
@@URL = "http://news.ycombinator.com/"
|
9
|
+
|
10
|
+
@@MATCHER_ITEM = "//td[@class = 'title']/a"
|
11
|
+
|
12
|
+
def name
|
13
|
+
return "Hacker News"
|
14
|
+
end
|
15
|
+
|
16
|
+
def run()
|
17
|
+
doc = Nokogiri::HTML(open(@@URL))
|
18
|
+
|
19
|
+
res = doc.xpath(@@MATCHER_ITEM).map { |i|
|
20
|
+
{
|
21
|
+
:text => i.text,
|
22
|
+
:link => URI.join(@@URL, i['href'])
|
23
|
+
}
|
24
|
+
}
|
25
|
+
|
26
|
+
return {
|
27
|
+
:plugin => self.class.name,
|
28
|
+
:title => doc.title,
|
29
|
+
:res => res
|
30
|
+
}
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end # Plugins
|
34
|
+
end # Crawler
|
35
|
+
end # Apollo
|
data/main.rb
ADDED
@@ -0,0 +1,170 @@
|
|
1
|
+
#! /usr/bin/env ruby
|
2
|
+
|
3
|
+
require "rubygems"
|
4
|
+
require "bundler/setup"
|
5
|
+
|
6
|
+
require 'json'
|
7
|
+
|
8
|
+
require "thor"
|
9
|
+
|
10
|
+
require "open-uri"
|
11
|
+
require "nokogiri"
|
12
|
+
|
13
|
+
require "pp"
|
14
|
+
require "optparse"
|
15
|
+
|
16
|
+
module Crawler
|
17
|
+
class Program
|
18
|
+
# This hash will hold all of the options
|
19
|
+
# parsed from the command-line by
|
20
|
+
# OptionParser.
|
21
|
+
@options = nil
|
22
|
+
@optparser = nil
|
23
|
+
@plugins = nil
|
24
|
+
|
25
|
+
# Initializer - Constructor
|
26
|
+
def initialize
|
27
|
+
@plugins = {}
|
28
|
+
end
|
29
|
+
|
30
|
+
# Initialize command-line options
|
31
|
+
def init_options
|
32
|
+
@options = {}
|
33
|
+
@options[:verbose] = false
|
34
|
+
|
35
|
+
@optparser = OptionParser.new do | opts |
|
36
|
+
# This displays the help screen, all programs are
|
37
|
+
# assumed to have this option.
|
38
|
+
opts.on('-h', '--help', 'Display this screen') do
|
39
|
+
puts opts
|
40
|
+
exit
|
41
|
+
end
|
42
|
+
|
43
|
+
opts.on('-a', '--all', 'Run all plugins') do
|
44
|
+
@options[:run_all] = true
|
45
|
+
end
|
46
|
+
|
47
|
+
opts.on('-v', '--verbose', 'Enable verbose output') do
|
48
|
+
@options[:verbose] = true
|
49
|
+
end
|
50
|
+
|
51
|
+
opts.on('-l', '--list-plugins', 'List of plugins') do
|
52
|
+
@options[:list_plugins] = true
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
56
|
+
|
57
|
+
# Parse the options passed to command-line
|
58
|
+
def parse_options
|
59
|
+
# Parse the command-line. Remember there are two forms
|
60
|
+
# of the parse method. The 'parse' method simply parses
|
61
|
+
# ARGV, while the 'parse!' method parses ARGV and removes
|
62
|
+
# any options found there, as well as any parameters for
|
63
|
+
# the options. What's left is the list of files to resize.
|
64
|
+
@optparser.parse!
|
65
|
+
end
|
66
|
+
|
67
|
+
# Load global options first
|
68
|
+
# Merge it with local options (if they exists)
|
69
|
+
def load_config_file()
|
70
|
+
config = File.join(File.dirname(__FILE__), "config", "crawler.rb")
|
71
|
+
puts "Inspecting #{config} ..."
|
72
|
+
if(File.exists?(config))
|
73
|
+
if(@options[:verbose])
|
74
|
+
puts "Loading config '#{config}'"
|
75
|
+
end
|
76
|
+
|
77
|
+
puts "Let's require '#{@options[:verbose]}'"
|
78
|
+
require config
|
79
|
+
else
|
80
|
+
if(@options[:verbose])
|
81
|
+
# TODO: Add support for initial rake task generation
|
82
|
+
# Something like this:
|
83
|
+
# rake config:init # Initializes config files with
|
84
|
+
# their defaults (if not exists already)
|
85
|
+
puts "Default config does not exist, skipping - '#{config}'"
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
# Register plugins (specific crawlers)
|
91
|
+
def register_plugins()
|
92
|
+
dir = File.join(File.dirname(__FILE__), "lib", "apollo_crawler", "plugins")
|
93
|
+
if(@options[:verbose])
|
94
|
+
puts "Registering plugins - '#{dir}'"
|
95
|
+
end
|
96
|
+
|
97
|
+
sites = File.join(dir, "**", "*.rb")
|
98
|
+
Dir.glob(sites).each do |site|
|
99
|
+
require site
|
100
|
+
end
|
101
|
+
|
102
|
+
tmp = Apollo::Crawler::Plugins.constants.select { |c|
|
103
|
+
Class === Apollo::Crawler::Plugins.const_get(c)
|
104
|
+
}
|
105
|
+
|
106
|
+
tmp.each do |x|
|
107
|
+
klass = Object.const_get('Apollo').const_get('Crawler').const_get('Plugins').const_get(x)
|
108
|
+
@plugins.merge!({ x.downcase.to_s => klass})
|
109
|
+
end
|
110
|
+
|
111
|
+
if(@options[:verbose])
|
112
|
+
@plugins.each do |plugin, klass|
|
113
|
+
name = klass.new.class.name
|
114
|
+
|
115
|
+
if name == "Apollo::Crawler::Plugins::Plugin"
|
116
|
+
next
|
117
|
+
end
|
118
|
+
|
119
|
+
puts "Registered '#{plugin}' -> '#{name}'"
|
120
|
+
end
|
121
|
+
end
|
122
|
+
end
|
123
|
+
|
124
|
+
def run
|
125
|
+
init_options()
|
126
|
+
|
127
|
+
load_config_file()
|
128
|
+
|
129
|
+
parse_options()
|
130
|
+
|
131
|
+
# Register sites which can be crawled
|
132
|
+
register_plugins()
|
133
|
+
|
134
|
+
if(@options[:list_plugins])
|
135
|
+
puts "Listing plugins"
|
136
|
+
puts "----------------------------------------"
|
137
|
+
i = 0
|
138
|
+
@plugins.sort.each do |plugin, klass|
|
139
|
+
instance = klass.new
|
140
|
+
# puts klass.class_eval("@@NAME")
|
141
|
+
puts "(#{i}) #{plugin} - #{instance.name}"
|
142
|
+
i += 1
|
143
|
+
end
|
144
|
+
puts "----------------------------------------"
|
145
|
+
return
|
146
|
+
end
|
147
|
+
|
148
|
+
plugins = ARGV
|
149
|
+
|
150
|
+
if(@options[:run_all])
|
151
|
+
plugins = @plugins.keys
|
152
|
+
end
|
153
|
+
|
154
|
+
if(plugins.empty?)
|
155
|
+
puts @optparser
|
156
|
+
end
|
157
|
+
|
158
|
+
plugins.each do |plugin|
|
159
|
+
p = @plugins[plugin.downcase].new
|
160
|
+
|
161
|
+
# puts "Running '#{plugin}'"
|
162
|
+
puts JSON.pretty_generate(p.run)
|
163
|
+
end
|
164
|
+
end
|
165
|
+
end
|
166
|
+
end
|
167
|
+
|
168
|
+
if __FILE__ == $0
|
169
|
+
Crawler::Program.new.run()
|
170
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: apollo-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.5
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -16,7 +16,14 @@ email: korczis@gmail.com
|
|
16
16
|
executables: []
|
17
17
|
extensions: []
|
18
18
|
extra_rdoc_files: []
|
19
|
-
files:
|
19
|
+
files:
|
20
|
+
- ./main.rb
|
21
|
+
- ./lib/apollo_crawler/crawler.rb
|
22
|
+
- ./lib/apollo_crawler/plugins/slashdot_org/slashdot.rb
|
23
|
+
- ./lib/apollo_crawler/plugins/firmy_cz/firmy.rb
|
24
|
+
- ./lib/apollo_crawler/plugins/alexa_com/alexa.rb
|
25
|
+
- ./lib/apollo_crawler/plugins/ycombinator_com/hacker_news.rb
|
26
|
+
- ./lib/apollo_crawler/plugin.rb
|
20
27
|
homepage: https://github.com/korczis/apollo-crawler
|
21
28
|
licenses: []
|
22
29
|
post_install_message:
|