scrapey 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +16 -8
- data/examples/multi.rb +13 -0
- data/lib/scrapey/constants.rb +4 -0
- data/lib/scrapey/database.rb +0 -1
- data/lib/scrapey/multi.rb +25 -0
- data/lib/scrapey/scrapey.rb +8 -10
- data/lib/scrapey/version.rb +1 -1
- data/lib/scrapey.rb +3 -2
- data/template/config/config.yml +11 -15
- data/template/src/template.rb +4 -0
- metadata +20 -7
data/README.md
CHANGED
@@ -16,14 +16,22 @@ Or install it yourself as:
|
|
16
16
|
|
17
17
|
$ gem install scrapey
|
18
18
|
|
19
|
-
##
|
19
|
+
## Examples
|
20
20
|
|
21
|
-
|
21
|
+
### Concurrent downloads
|
22
22
|
|
23
|
-
|
23
|
+
```ruby
|
24
|
+
require 'scrapey'
|
25
|
+
require 'scrapey/multi'
|
24
26
|
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
27
|
+
fields 'url', 'title'
|
28
|
+
|
29
|
+
def scrape url, response
|
30
|
+
doc = Nokogiri::HTML response
|
31
|
+
@items << {'url' => url, 'title' => doc.at('title').text}
|
32
|
+
end
|
33
|
+
|
34
|
+
@items = []
|
35
|
+
multi_get ['http://www.yahoo.com/', 'http://www.google.com.', 'http://www.bing.com/'], 3, :scrape
|
36
|
+
@items.each{|item| save item}
|
37
|
+
```
|
data/examples/multi.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'scrapey'
|
2
|
+
require 'scrapey/multi'
|
3
|
+
|
4
|
+
fields 'url', 'title'
|
5
|
+
|
6
|
+
def scrape url, response
|
7
|
+
doc = Nokogiri::HTML response
|
8
|
+
@items << {'url' => url, 'title' => doc.at('title').text}
|
9
|
+
end
|
10
|
+
|
11
|
+
@items = []
|
12
|
+
multi_get ['http://www.yahoo.com/', 'http://www.google.com.', 'http://www.bing.com/'], 3, :scrape
|
13
|
+
@items.each{|item| save item}
|
data/lib/scrapey/database.rb
CHANGED
@@ -0,0 +1,25 @@
|
|
1
|
+
require 'em-http-request'
|
2
|
+
|
3
|
+
module Scrapey
|
4
|
+
def multi_get all_urls, num_threads = 20, callback = :save_cache
|
5
|
+
all_urls.each_slice(num_threads) do |urls|
|
6
|
+
next unless urls.size > 0
|
7
|
+
EventMachine.run do
|
8
|
+
multi = EventMachine::MultiRequest.new
|
9
|
+
urls.each_with_index do |url, i|
|
10
|
+
multi.add i, EventMachine::HttpRequest.new(url).get(:redirects => 10)
|
11
|
+
end
|
12
|
+
multi.callback do
|
13
|
+
(0...multi.requests.length).each do |i|
|
14
|
+
if multi.responses[:callback][i]
|
15
|
+
send callback, urls[i], multi.responses[:callback][i].response
|
16
|
+
else
|
17
|
+
puts "problem downloading #{urls[i]}!"
|
18
|
+
end
|
19
|
+
end
|
20
|
+
EventMachine.stop
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
data/lib/scrapey/scrapey.rb
CHANGED
@@ -1,5 +1,4 @@
|
|
1
1
|
module Scrapey
|
2
|
-
BASEDIR = File.expand_path(File.dirname($0)).gsub(/\/src$/,'')
|
3
2
|
|
4
3
|
def get_or_post method, url, options={}, *args
|
5
4
|
agent = method == 'goto' ? @browser : @agent
|
@@ -13,7 +12,7 @@ module Scrapey
|
|
13
12
|
end
|
14
13
|
|
15
14
|
doc = load_cache(url) if @use_cache
|
16
|
-
|
15
|
+
return doc if doc
|
17
16
|
|
18
17
|
page = agent.send *new_args
|
19
18
|
save_cache(url, page.body) if @use_cache
|
@@ -23,8 +22,7 @@ module Scrapey
|
|
23
22
|
rescue Exception => e
|
24
23
|
case
|
25
24
|
when defined? on_error
|
26
|
-
on_error e
|
27
|
-
get_or_post method, url, options, *args
|
25
|
+
return on_error e, method, url, options, *args
|
28
26
|
when _retries && _retries > 0
|
29
27
|
puts "Error. Retries remaining: #{options[:retries]}"
|
30
28
|
sleep _sleep if _sleep
|
@@ -59,12 +57,12 @@ module Scrapey
|
|
59
57
|
end
|
60
58
|
end
|
61
59
|
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
60
|
+
def visited? url
|
61
|
+
@visited ||= []
|
62
|
+
return true if @visited.include? url
|
63
|
+
@visited << url
|
64
|
+
false
|
65
|
+
end
|
68
66
|
|
69
67
|
def ts
|
70
68
|
Time.now.to_i.to_s
|
data/lib/scrapey/version.rb
CHANGED
data/lib/scrapey.rb
CHANGED
@@ -3,8 +3,9 @@ require 'csv'
|
|
3
3
|
require 'json'
|
4
4
|
require 'yaml'
|
5
5
|
|
6
|
-
require "scrapey/version"
|
7
6
|
require "scrapey/scrapey"
|
7
|
+
require "scrapey/version"
|
8
|
+
require "scrapey/constants"
|
8
9
|
require "scrapey/cache"
|
9
10
|
require "scrapey/database"
|
10
11
|
|
@@ -15,7 +16,7 @@ include Scrapey
|
|
15
16
|
@agent.user_agent = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.56 Safari/536.5'
|
16
17
|
|
17
18
|
# default output file
|
18
|
-
@output =
|
19
|
+
@output = 'output.csv'
|
19
20
|
|
20
21
|
# read config file
|
21
22
|
config_file = "#{BASEDIR}/config/config.yml"
|
data/template/config/config.yml
CHANGED
@@ -3,21 +3,17 @@
|
|
3
3
|
email: foo@gmail.com
|
4
4
|
password: 12345
|
5
5
|
|
6
|
-
=begin
|
7
6
|
# example database section
|
8
|
-
database:
|
9
|
-
adapter: mysql
|
10
|
-
database: template
|
11
|
-
username: root
|
12
|
-
password: 12345
|
13
|
-
host: localhost
|
14
|
-
encoding: 'utf8'
|
15
|
-
=end
|
7
|
+
#database:
|
8
|
+
# adapter: mysql
|
9
|
+
# database: template
|
10
|
+
# username: root
|
11
|
+
# password: 12345
|
12
|
+
# host: localhost
|
13
|
+
# encoding: 'utf8'
|
16
14
|
|
17
|
-
=begin
|
18
15
|
# example proxies section
|
19
|
-
proxies:
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
=end
|
16
|
+
#proxies:
|
17
|
+
#- www.host1.com:80
|
18
|
+
#- localhost:8080
|
19
|
+
#- 127.0.0.1:8888
|
data/template/src/template.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scrapey
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.3
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-07-
|
12
|
+
date: 2012-07-27 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mechanize
|
16
|
-
requirement:
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ~>
|
@@ -21,10 +21,15 @@ dependencies:
|
|
21
21
|
version: 2.5.0
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements:
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 2.5.0
|
25
30
|
- !ruby/object:Gem::Dependency
|
26
31
|
name: json
|
27
|
-
requirement:
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
28
33
|
none: false
|
29
34
|
requirements:
|
30
35
|
- - ~>
|
@@ -32,7 +37,12 @@ dependencies:
|
|
32
37
|
version: 1.7.0
|
33
38
|
type: :runtime
|
34
39
|
prerelease: false
|
35
|
-
version_requirements:
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 1.7.0
|
36
46
|
description: A simple scraping framework
|
37
47
|
email:
|
38
48
|
- pguardiario@gmail.com
|
@@ -46,8 +56,11 @@ files:
|
|
46
56
|
- README.md
|
47
57
|
- Rakefile
|
48
58
|
- bin/scrapey
|
59
|
+
- examples/multi.rb
|
49
60
|
- lib/scrapey/cache.rb
|
61
|
+
- lib/scrapey/constants.rb
|
50
62
|
- lib/scrapey/database.rb
|
63
|
+
- lib/scrapey/multi.rb
|
51
64
|
- lib/scrapey/scrapey.rb
|
52
65
|
- lib/scrapey/template.rb
|
53
66
|
- lib/scrapey/version.rb
|
@@ -75,7 +88,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
75
88
|
version: '0'
|
76
89
|
requirements: []
|
77
90
|
rubyforge_project:
|
78
|
-
rubygems_version: 1.8.
|
91
|
+
rubygems_version: 1.8.23
|
79
92
|
signing_key:
|
80
93
|
specification_version: 3
|
81
94
|
summary: A simple scraping framework
|