email_crawler 0.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.env.example +2 -0
- data/.gitignore +19 -0
- data/.ruby-version +1 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +57 -0
- data/Rakefile +9 -0
- data/bin/email-crawler +47 -0
- data/email_crawler.gemspec +26 -0
- data/lib/email_crawler/email_scanner.rb +42 -0
- data/lib/email_crawler/mechanize_helper.rb +22 -0
- data/lib/email_crawler/page_links.rb +60 -0
- data/lib/email_crawler/proxy.rb +28 -0
- data/lib/email_crawler/scraper.rb +31 -0
- data/lib/email_crawler/version.rb +3 -0
- data/lib/email_crawler.rb +69 -0
- data/spec/lib/email_crawler/email_scanner_spec.rb +16 -0
- data/spec/lib/email_crawler/page_links_spec.rb +13 -0
- data/spec/lib/email_crawler/scraper_spec.rb +13 -0
- data/spec/spec_helper.rb +2 -0
- metadata +140 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 62e4b0ccd69dee8523ebdbb12e3a14c6820b7592
|
4
|
+
data.tar.gz: dc1c7941ed58d5de961ad7bcad9f95af16fb164f
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a71df8fb24765c8acafef1da841b1dfc5c4b7ffdb1f429fc0ffddc375f2ef28107fe353eb4deb352b697d84584c666adfab4370d635487305d38d64a1f5cb1d3
|
7
|
+
data.tar.gz: 43de8cb5b8fa2456ffed8a3e08c04e580079170eb47593587e5abee57103ba6c0bbde70fc62bd0d86a90cce5fb2b11c76ba7c5a2c7357b1a29f9fd6ba479a770
|
data/.env.example
ADDED
data/.gitignore
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.1.0
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Cristian Rasch
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
# EmailCrawler
|
2
|
+
|
3
|
+
Email crawler: crawls the top ten Google search results looking for email addresses and exports them to CSV.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'email_crawler'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install email_crawler
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
1. Ask for help
|
22
|
+
|
23
|
+
```bash
|
24
|
+
email-crawler --help
|
25
|
+
```
|
26
|
+
|
27
|
+
2. Simplest Google search
|
28
|
+
|
29
|
+
```bash
|
30
|
+
email-crawler -q "berlin walks"
|
31
|
+
```
|
32
|
+
|
33
|
+
3. Select which Google website to use (defaults to google.com.br)
|
34
|
+
|
35
|
+
```bash
|
36
|
+
email-crawler -q "berlin walks" -g google.de
|
37
|
+
```
|
38
|
+
|
39
|
+
4. Specify how many internal links are to be scanned for email addresses (defaults to 100)
|
40
|
+
|
41
|
+
```bash
|
42
|
+
email-crawler -q "berlin walks" -g google.de -m 250
|
43
|
+
```
|
44
|
+
|
45
|
+
5. Redirect output to a file
|
46
|
+
|
47
|
+
```bash
|
48
|
+
email-crawler -q "berlin walks" -g google.de -m 250 > ~/Desktop/belin-walks-emails.csv
|
49
|
+
```
|
50
|
+
|
51
|
+
## Contributing
|
52
|
+
|
53
|
+
1. Fork it ( http://github.com/cristianrasch/email_crawler/fork )
|
54
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
55
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
56
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
57
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/email-crawler
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
require 'ostruct'
|
5
|
+
|
6
|
+
class OptionsParser
|
7
|
+
def self.parse(args)
|
8
|
+
options = OpenStruct.new
|
9
|
+
options.google_website = "google.com.br"
|
10
|
+
options.max_links = 100
|
11
|
+
|
12
|
+
opt_parser = OptionParser.new do |opts|
|
13
|
+
opts.banner = "Usage: email-crawler [options]"
|
14
|
+
opts.separator ""
|
15
|
+
|
16
|
+
opts.on("-q", '--query "SEARCH TERM/EXPRESSION"',
|
17
|
+
"The term/expression you want to search for") do |q|
|
18
|
+
options.q = q
|
19
|
+
end
|
20
|
+
|
21
|
+
opts.on("-g", "--google-website google.com.au",
|
22
|
+
"An alternative Google website",
|
23
|
+
" (defaults to Google Brazil)") do |google_website|
|
24
|
+
options.google_website = google_website
|
25
|
+
end
|
26
|
+
|
27
|
+
opts.on("-m", "--max-links 250",
|
28
|
+
"Max # of internal links to visit searching for emails",
|
29
|
+
" (per search result, defaults to 100)") do |max_links|
|
30
|
+
options.max_links = max_links.to_i
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
opt_parser.parse!(args)
|
35
|
+
options
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
options = OptionsParser.parse(ARGV)
|
40
|
+
if options.q.empty?
|
41
|
+
print "The -q switch is mandatory\n"
|
42
|
+
exit(1)
|
43
|
+
else
|
44
|
+
require_relative "../lib/email_crawler"
|
45
|
+
csv = EmailCrawler::Runner.new(options.google_website).run(options.q, options.max_links)
|
46
|
+
$stdout << "#{csv}\n"
|
47
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'email_crawler/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "email_crawler"
|
8
|
+
spec.version = EmailCrawler::VERSION
|
9
|
+
spec.authors = ["Cristian Rasch"]
|
10
|
+
spec.email = ["cristianrasch@fastmail.fm"]
|
11
|
+
spec.summary = %q{Email crawler: crawls the top ten Google search results looking for email addresses and exports them to CSV.}
|
12
|
+
spec.homepage = "https://github.com/cristianrasch/email_crawler"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0")
|
16
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
17
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_runtime_dependency "mechanize"
|
21
|
+
spec.add_runtime_dependency "dotenv"
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.5"
|
24
|
+
spec.add_development_dependency "rake"
|
25
|
+
spec.add_development_dependency "minitest", "~> 5.2.3"
|
26
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
require "open-uri"
|
2
|
+
|
3
|
+
module EmailCrawler
|
4
|
+
class EmailScanner
|
5
|
+
EMAIL_REGEXP = /\b[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,4}\b/i
|
6
|
+
SLEEP_TIME = 0.5
|
7
|
+
|
8
|
+
def initialize(url)
|
9
|
+
@url = url
|
10
|
+
@logger = ::Logger.new(STDOUT).tap do |logger|
|
11
|
+
logger.level = ENV["DEBUG"] ? Logger::INFO : Logger::ERROR
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
def scan(links)
|
16
|
+
emails_by_link = {}
|
17
|
+
|
18
|
+
links.each do |link|
|
19
|
+
@logger.info "searching for emails on '#{link}'.."
|
20
|
+
|
21
|
+
html = begin
|
22
|
+
open(link).read
|
23
|
+
rescue OpenURI::HTTPError => err
|
24
|
+
@logger.warn(err)
|
25
|
+
nil
|
26
|
+
rescue => err
|
27
|
+
if err.message =~ /redirection forbidden/
|
28
|
+
link = err.message.split(" ").last
|
29
|
+
retry
|
30
|
+
end
|
31
|
+
end
|
32
|
+
next unless html
|
33
|
+
|
34
|
+
emails = html.scan(EMAIL_REGEXP)
|
35
|
+
emails_by_link[link] = Set.new(emails) unless emails.empty?
|
36
|
+
sleep(SLEEP_TIME)
|
37
|
+
end
|
38
|
+
|
39
|
+
emails_by_link
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require "mechanize"
|
2
|
+
|
3
|
+
module EmailCrawler
|
4
|
+
module MechanizeHelper
|
5
|
+
def new_agent
|
6
|
+
Thread.current[:agent] ||= Mechanize.new do |agent|
|
7
|
+
agent.user_agent_alias = "Mac Safari"
|
8
|
+
agent.open_timeout = agent.read_timeout = 30
|
9
|
+
agent.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
10
|
+
agent.history.max_size = 1
|
11
|
+
yield(agent) if block_given?
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
def get(url)
|
16
|
+
begin
|
17
|
+
page = agent.get(url)
|
18
|
+
page if page.is_a?(Mechanize::Page)
|
19
|
+
rescue Mechanize::Error, Net::OpenTimeout; end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,60 @@
|
|
1
|
+
module EmailCrawler
|
2
|
+
class PageLinks
|
3
|
+
MAX_LINKS = 100
|
4
|
+
SLEEP_TIME = 0.5
|
5
|
+
|
6
|
+
include MechanizeHelper
|
7
|
+
|
8
|
+
def initialize(url)
|
9
|
+
@url = url
|
10
|
+
uri = URI(url)
|
11
|
+
scheme_and_host = if uri.host
|
12
|
+
"#{uri.scheme}://#{uri.host}"
|
13
|
+
else
|
14
|
+
url[%r(\A(https?://([^/]+))), 1]
|
15
|
+
end
|
16
|
+
@domain = Regexp.new("#{scheme_and_host}/", true)
|
17
|
+
@logger = ::Logger.new(STDOUT).tap do |logger|
|
18
|
+
logger.level = ENV["DEBUG"] ? Logger::INFO : Logger::ERROR
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.for(url, max_links = MAX_LINKS)
|
23
|
+
new(url).fetch_links(max_links)
|
24
|
+
end
|
25
|
+
|
26
|
+
def fetch_links(max_links = MAX_LINKS)
|
27
|
+
queue, links = Set.new([@url]), Set.new([@url])
|
28
|
+
|
29
|
+
until queue.empty?
|
30
|
+
current_link = queue.first
|
31
|
+
@logger.info "current_link: #{current_link}"
|
32
|
+
page = get(current_link)
|
33
|
+
|
34
|
+
if page
|
35
|
+
new_links = page.links_with(href: @domain).map(&:href)
|
36
|
+
new_links.reject! { |link| links.include?(link) }
|
37
|
+
@logger.debug "found: #{new_links.length} new link(s)"
|
38
|
+
new_links.each { |link| queue << link }
|
39
|
+
links << current_link
|
40
|
+
|
41
|
+
if links.length == max_links
|
42
|
+
break
|
43
|
+
else
|
44
|
+
sleep(SLEEP_TIME)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
queue.delete(current_link)
|
49
|
+
end
|
50
|
+
|
51
|
+
links.to_a
|
52
|
+
end
|
53
|
+
|
54
|
+
private
|
55
|
+
|
56
|
+
def agent
|
57
|
+
@agent ||= new_agent
|
58
|
+
end
|
59
|
+
end
|
60
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
require "open-uri"
|
2
|
+
require "json"
|
3
|
+
require "dotenv"
|
4
|
+
|
5
|
+
module EmailCrawler
|
6
|
+
class Proxy
|
7
|
+
class << self
|
8
|
+
def random
|
9
|
+
all.sample
|
10
|
+
end
|
11
|
+
|
12
|
+
private
|
13
|
+
|
14
|
+
def all
|
15
|
+
@all ||= begin
|
16
|
+
Dotenv.load
|
17
|
+
|
18
|
+
json = JSON.parse(open("https://api.digitalocean.com/droplets/?client_id=#{ENV['DO_CLIENT_ID']}&api_key=#{ENV['DO_API_KEY']}").read)
|
19
|
+
json["droplets"].
|
20
|
+
select{ |droplet| droplet["name"] =~ /proxy\d+/ }.
|
21
|
+
map { |droplet| droplet["ip_address"] }
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
|
@@ -0,0 +1,31 @@
|
|
1
|
+
require_relative "proxy"
|
2
|
+
|
3
|
+
module EmailCrawler
|
4
|
+
class Scraper
|
5
|
+
MAX_URLS = 10
|
6
|
+
|
7
|
+
include MechanizeHelper
|
8
|
+
|
9
|
+
def initialize(google_website)
|
10
|
+
@google_website = "https://www.#{google_website}/"
|
11
|
+
end
|
12
|
+
|
13
|
+
def top_ten_urls_for(q)
|
14
|
+
search_page = agent.get(@google_website)
|
15
|
+
search_form = search_page.form_with(action: "/search")
|
16
|
+
search_form.field_with(name: "q").value = q
|
17
|
+
search_results_page = agent.submit(search_form)
|
18
|
+
search_results_page.search("#search ol li h3.r a").
|
19
|
+
map { |a| a["href"].downcase }.
|
20
|
+
reject { |url| url =~ %r(\A/search[?]q=) }.
|
21
|
+
first(MAX_URLS)
|
22
|
+
end
|
23
|
+
|
24
|
+
private
|
25
|
+
|
26
|
+
def agent
|
27
|
+
@agent ||= new_agent { |agent| agent.set_proxy(Proxy.random, "8888") }
|
28
|
+
# @agent ||= new_agent
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,69 @@
|
|
1
|
+
require "thread"
|
2
|
+
require "logger"
|
3
|
+
require "csv"
|
4
|
+
require "set"
|
5
|
+
|
6
|
+
require_relative "email_crawler/version"
|
7
|
+
require_relative "email_crawler/mechanize_helper"
|
8
|
+
require_relative "email_crawler/scraper"
|
9
|
+
require_relative "email_crawler/page_links"
|
10
|
+
require_relative "email_crawler/email_scanner"
|
11
|
+
|
12
|
+
module EmailCrawler
|
13
|
+
class Runner
|
14
|
+
def initialize(google_website)
|
15
|
+
@google_website = google_website
|
16
|
+
|
17
|
+
log_file = File.join(ENV["HOME"], "email-crawler.log")
|
18
|
+
file = File.open(log_file, File::WRONLY | File::APPEND | File::CREAT)
|
19
|
+
@logger = ::Logger.new(file).tap do |logger|
|
20
|
+
logger.level = ENV["DEBUG"] ? Logger::INFO : Logger::ERROR
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def run(q, max_links = PageLinks::MAX_LINKS)
|
25
|
+
urls = Scraper.new(@google_website).top_ten_urls_for(q)
|
26
|
+
urls.each { |url, links| @logger.info "#{url}" }
|
27
|
+
|
28
|
+
threads = (1..urls.length).map do |i|
|
29
|
+
Thread.new(i, urls[i-1]) do |i, url|
|
30
|
+
@logger.info "[Thread ##{i}] grabbing page links for '#{url}'.."
|
31
|
+
Thread.current[:url] = url
|
32
|
+
Thread.current[:links] = PageLinks.for(url, max_links)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
threads.each(&:join)
|
37
|
+
threads.each { |thread| @logger.info "#{thread[:url]} (#{thread[:links].length} links)" }
|
38
|
+
links_by_url = Hash[threads.map { |thread| [thread[:url], thread[:links]] }]
|
39
|
+
|
40
|
+
threads = (links_by_url).map.with_index do |arr, i|
|
41
|
+
Thread.new(i+1, arr.first, arr.last) do |i, url, links|
|
42
|
+
@logger.info "[Thread ##{i}] scanning for emails on page '#{url}' (#{links.length} links)"
|
43
|
+
Thread.current[:url] = url
|
44
|
+
Thread.current[:emails] = EmailScanner.new(url).scan(links)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
threads.each(&:join)
|
49
|
+
|
50
|
+
read_emails = Set.new
|
51
|
+
CSV.generate do |csv|
|
52
|
+
csv << %w(Email Domain URL)
|
53
|
+
csv << []
|
54
|
+
|
55
|
+
threads.each do |thread|
|
56
|
+
email_count = thread[:emails].inject(0) { |sum, arr| sum += arr.last.length }
|
57
|
+
@logger.info "#{thread[:url]} (#{email_count} emails)"
|
58
|
+
|
59
|
+
url = thread[:url]
|
60
|
+
thread[:emails].each do |link, emails|
|
61
|
+
emails.each do |email|
|
62
|
+
csv << [email, url, link] if read_emails.add?(email)
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require_relative "../../spec_helper"
|
2
|
+
|
3
|
+
require File.expand_path("lib/email_crawler")
|
4
|
+
|
5
|
+
module EmailCrawler
|
6
|
+
describe EmailScanner do
|
7
|
+
subject { EmailScanner.new("google.com") }
|
8
|
+
|
9
|
+
let(:link) { "http://www.kitaylaw.com/contact.php" }
|
10
|
+
|
11
|
+
it "scans links for email addresses" do
|
12
|
+
emails_by_link = subject.scan([link])
|
13
|
+
emails_by_link[link].wont_be_empty
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
require_relative "../../spec_helper"
|
2
|
+
|
3
|
+
require File.expand_path("lib/email_crawler")
|
4
|
+
|
5
|
+
module EmailCrawler
|
6
|
+
describe PageLinks do
|
7
|
+
let(:max_links) { 25 }
|
8
|
+
|
9
|
+
it "returns the first N internal links" do
|
10
|
+
PageLinks.for("http://www.visitberlin.de/en", max_links).length.must_equal max_links
|
11
|
+
end
|
12
|
+
end
|
13
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
require_relative "../../spec_helper"
|
2
|
+
|
3
|
+
require File.expand_path("lib/email_crawler")
|
4
|
+
|
5
|
+
module EmailCrawler
|
6
|
+
describe Scraper do
|
7
|
+
subject { Scraper.new("google.de") }
|
8
|
+
|
9
|
+
it "returns the top 10 URLs for a given search term/expression" do
|
10
|
+
subject.top_ten_urls_for("berlin tours").length.must_equal 10
|
11
|
+
end
|
12
|
+
end
|
13
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,140 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: email_crawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Cristian Rasch
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-02-25 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: mechanize
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: dotenv
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.5'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.5'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: minitest
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 5.2.3
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 5.2.3
|
83
|
+
description:
|
84
|
+
email:
|
85
|
+
- cristianrasch@fastmail.fm
|
86
|
+
executables:
|
87
|
+
- email-crawler
|
88
|
+
extensions: []
|
89
|
+
extra_rdoc_files: []
|
90
|
+
files:
|
91
|
+
- ".env.example"
|
92
|
+
- ".gitignore"
|
93
|
+
- ".ruby-version"
|
94
|
+
- Gemfile
|
95
|
+
- LICENSE.txt
|
96
|
+
- README.md
|
97
|
+
- Rakefile
|
98
|
+
- bin/email-crawler
|
99
|
+
- email_crawler.gemspec
|
100
|
+
- lib/email_crawler.rb
|
101
|
+
- lib/email_crawler/email_scanner.rb
|
102
|
+
- lib/email_crawler/mechanize_helper.rb
|
103
|
+
- lib/email_crawler/page_links.rb
|
104
|
+
- lib/email_crawler/proxy.rb
|
105
|
+
- lib/email_crawler/scraper.rb
|
106
|
+
- lib/email_crawler/version.rb
|
107
|
+
- spec/lib/email_crawler/email_scanner_spec.rb
|
108
|
+
- spec/lib/email_crawler/page_links_spec.rb
|
109
|
+
- spec/lib/email_crawler/scraper_spec.rb
|
110
|
+
- spec/spec_helper.rb
|
111
|
+
homepage: https://github.com/cristianrasch/email_crawler
|
112
|
+
licenses:
|
113
|
+
- MIT
|
114
|
+
metadata: {}
|
115
|
+
post_install_message:
|
116
|
+
rdoc_options: []
|
117
|
+
require_paths:
|
118
|
+
- lib
|
119
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
120
|
+
requirements:
|
121
|
+
- - ">="
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: '0'
|
124
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
125
|
+
requirements:
|
126
|
+
- - ">="
|
127
|
+
- !ruby/object:Gem::Version
|
128
|
+
version: '0'
|
129
|
+
requirements: []
|
130
|
+
rubyforge_project:
|
131
|
+
rubygems_version: 2.2.0
|
132
|
+
signing_key:
|
133
|
+
specification_version: 4
|
134
|
+
summary: 'Email crawler: crawls the top ten Google search results looking for email
|
135
|
+
addresses and exports them to CSV.'
|
136
|
+
test_files:
|
137
|
+
- spec/lib/email_crawler/email_scanner_spec.rb
|
138
|
+
- spec/lib/email_crawler/page_links_spec.rb
|
139
|
+
- spec/lib/email_crawler/scraper_spec.rb
|
140
|
+
- spec/spec_helper.rb
|