generalscraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/generalscraper.rb +78 -0
- metadata +45 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 1e568d1e9d1c0fa9c98f814128439bd009194c0d
|
4
|
+
data.tar.gz: f26d58116e50b61ad308eed4df0ce03e76cbfba8
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 92120914fbe80f8a0b5b3b5b996753b07a218745a88d7cd201fb533fa3de4e116499c1cc2d218d030771bf3d25dbf42743efc83ed7f1d2e4cb44939229ec31a6
|
7
|
+
data.tar.gz: b7d4070620f7a43ff7008ae414ea3aed53da287c697f32cb80f6afbd66186d94151a7393ac9547428f9ddeabf37e3500e7e55165ad11f7d2e1f994975e539f96
|
@@ -0,0 +1,78 @@
|
|
1
|
+
require 'mechanize'
|
2
|
+
require 'json'
|
3
|
+
require 'nokogiri'
|
4
|
+
require 'open-uri'
|
5
|
+
|
6
|
+
class GeneralScraper
|
7
|
+
def initialize(scrapesite, input)
|
8
|
+
@input = input
|
9
|
+
@scrapesite = scrapesite
|
10
|
+
@output = Array.new
|
11
|
+
@startindex = 10
|
12
|
+
end
|
13
|
+
|
14
|
+
# Searches for links on Google
|
15
|
+
def search
|
16
|
+
agent = Mechanize.new
|
17
|
+
agent.user_agent_alias = 'Linux Firefox'
|
18
|
+
gform = agent.get("http://google.com").form("f")
|
19
|
+
gform.q = "site:" + @scrapesite + " " + @input
|
20
|
+
page = agent.submit(gform, gform.buttons.first)
|
21
|
+
examine(page)
|
22
|
+
end
|
23
|
+
|
24
|
+
# Examines a search page
|
25
|
+
def examine(page)
|
26
|
+
page.links.each do |link|
|
27
|
+
if (link.href.include? @scrapesite) && (!link.href.include? "webcache") && (!link.href.include? "site:"+@scrapesite)
|
28
|
+
saveurl = link.href.split("?q=")
|
29
|
+
|
30
|
+
if saveurl[1]
|
31
|
+
url = saveurl[1].split("&")
|
32
|
+
getPage(url[0])
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
if (link.href.include? "&sa=N") && (link.href.include? "&start=")
|
37
|
+
url1 = link.href.split("&start=")
|
38
|
+
url2 = url1[1].split("&sa=N")
|
39
|
+
|
40
|
+
if url2[0].to_i == @startindex
|
41
|
+
sleep(rand(30..90))
|
42
|
+
@startindex += 10
|
43
|
+
agent = Mechanize.new
|
44
|
+
examine(agent.get("http://google.com" + link.href))
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
# Scrape the page content
|
51
|
+
def getPage(url)
|
52
|
+
pagehash = Hash.new
|
53
|
+
begin
|
54
|
+
url.gsub!("%3F", "?")
|
55
|
+
url.gsub!("%3D", "=")
|
56
|
+
pagehash[:url] = url
|
57
|
+
pagehash[:date_retrieved] = Time.now
|
58
|
+
html = Nokogiri::HTML(open(url))
|
59
|
+
pagehash[:title] = html.css("title").text
|
60
|
+
html.css("meta").each do |m|
|
61
|
+
if m
|
62
|
+
pagehash[m['name']] = m['content']
|
63
|
+
end
|
64
|
+
end
|
65
|
+
pagehash[:page] = html.css("body").text
|
66
|
+
@output.push(pagehash)
|
67
|
+
rescue
|
68
|
+
puts "URL: " + url
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
# Gets all data and returns in JSON
|
73
|
+
def getData
|
74
|
+
search
|
75
|
+
return JSON.pretty_generate(@output)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: generalscraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- M. C. McGrath
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-05-15 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Scrapes all pages on a site you specify including terms you specify.
|
14
|
+
email: shidash@shidash.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/generalscraper.rb
|
20
|
+
homepage: https://github.com/TransparencyToolkit/generalscraper
|
21
|
+
licenses:
|
22
|
+
- GPL
|
23
|
+
metadata: {}
|
24
|
+
post_install_message:
|
25
|
+
rdoc_options: []
|
26
|
+
require_paths:
|
27
|
+
- lib
|
28
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
34
|
+
requirements:
|
35
|
+
- - '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
requirements: []
|
39
|
+
rubyforge_project:
|
40
|
+
rubygems_version: 2.0.14
|
41
|
+
signing_key:
|
42
|
+
specification_version: 4
|
43
|
+
summary: Get all pages on a site for terms specified
|
44
|
+
test_files: []
|
45
|
+
has_rdoc:
|