requestmanager 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/requestmanager.rb +77 -0
- metadata +45 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4f67cdd4a24c5e45ff2509d3d934a1a9024178b8
|
4
|
+
data.tar.gz: ff5e527045259cb2207062af68042afd968f4c3f
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 3419dea05f953ecb677c97cb4a7c06ba6cd264e79b4b8baa4cfa94bac8c0081550615a9b2039402c32e960900eb48e651723380b19d5309137c83e6d4ff78a92
|
7
|
+
data.tar.gz: cdfec6f8eda2883212ee9fdb0cd4fabe11c37b6e8cb525f86fbc05576e8f84dca905a3ecb3bc689474b308d9c4faa68ebdbe47163c4cf83896364a6988e2bff9
|
@@ -0,0 +1,77 @@
|
|
1
|
+
require 'selenium-webdriver'
|
2
|
+
require 'uri'
|
3
|
+
require 'pry'
|
4
|
+
|
5
|
+
|
6
|
+
class RequestManager
|
7
|
+
def initialize(proxy_list, request_interval)
|
8
|
+
@proxy_list = parse_proxy_list(proxy_list)
|
9
|
+
@request_interval = request_interval
|
10
|
+
@used_proxies = Hash.new
|
11
|
+
end
|
12
|
+
|
13
|
+
# Get the page requested
|
14
|
+
def get_page(url, form_input = nil)
|
15
|
+
chosen_proxy = @proxy_list != nil ? get_random_proxy(url) : nil
|
16
|
+
driver = gen_driver(chosen_proxy)
|
17
|
+
driver.navigate.to url
|
18
|
+
puts "Getting page " + url
|
19
|
+
|
20
|
+
# Handle form input if there is any
|
21
|
+
if form_input
|
22
|
+
element = driver.find_element(name: "q")
|
23
|
+
element.send_keys form_input
|
24
|
+
element.submit
|
25
|
+
end
|
26
|
+
|
27
|
+
page_html = driver.page_source
|
28
|
+
driver.quit
|
29
|
+
return page_html
|
30
|
+
end
|
31
|
+
|
32
|
+
# Generate driver for searches
|
33
|
+
def gen_driver(chosen_proxy)
|
34
|
+
# Profile settings
|
35
|
+
profile = Selenium::WebDriver::Firefox::Profile.new
|
36
|
+
profile['intl.accept_languages'] = 'en'
|
37
|
+
|
38
|
+
# Set proxy if proxy list, otherwise sleep
|
39
|
+
if chosen_proxy
|
40
|
+
proxy = Selenium::WebDriver::Proxy.new(http: chosen_proxy, ssl: chosen_proxy)
|
41
|
+
profile.proxy = proxy
|
42
|
+
else
|
43
|
+
sleep(rand(@request_interval[0]..@request_interval[1]))
|
44
|
+
end
|
45
|
+
|
46
|
+
return Selenium::WebDriver.for :firefox, profile: profile
|
47
|
+
end
|
48
|
+
|
49
|
+
# Choose a random proxy that hasn't been used recently
|
50
|
+
def get_random_proxy(url)
|
51
|
+
max = @proxy_list.length
|
52
|
+
chosen = @proxy_list[Random.rand(max)]
|
53
|
+
|
54
|
+
# Only use proxy if it hasn't been used in last n seconds on same host
|
55
|
+
if is_not_used?(chosen, url)
|
56
|
+
@used_proxies[chosen] = [Time.now, URI.parse(url).host]
|
57
|
+
return chosen[0]+":"+chosen[1]
|
58
|
+
else
|
59
|
+
sleep(0.005)
|
60
|
+
get_random_proxy(url)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
# Checks if a proxy has been used on domain in the last 20 seconds
|
65
|
+
def is_not_used?(chosen, url)
|
66
|
+
return (!@used_proxies[chosen] ||
|
67
|
+
@used_proxies[chosen][0] <= Time.now-@request_interval[0] ||
|
68
|
+
@used_proxies[chosen][1] != URI.parse(url).host)
|
69
|
+
end
|
70
|
+
|
71
|
+
# Parse the proxy list
|
72
|
+
def parse_proxy_list(proxy_file)
|
73
|
+
if proxy_file
|
74
|
+
return IO.readlines(proxy_file).map{ |proxy| proxy.strip.split(":")}
|
75
|
+
end
|
76
|
+
end
|
77
|
+
end
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: requestmanager
|
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: 2015-11-01 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Manages proxies, wait intervals, etc
|
14
|
+
email: shidash@shidash.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/requestmanager.rb
|
20
|
+
homepage: https://github.com/TransparencyToolkit/linkedincrawler
|
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: 2.4.8
|
41
|
+
signing_key:
|
42
|
+
specification_version: 4
|
43
|
+
summary: Manages scraper http requests
|
44
|
+
test_files: []
|
45
|
+
has_rdoc:
|