proxy_fetcher 0.14.0 → 0.15.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Rakefile +3 -1
- data/gemfiles/nokogiri.gemfile +1 -1
- data/gemfiles/oga.gemfile +2 -2
- data/lib/proxy_fetcher.rb +6 -2
- data/lib/proxy_fetcher/manager.rb +2 -0
- data/lib/proxy_fetcher/providers/free_proxy_list_socks.rb +58 -0
- data/lib/proxy_fetcher/providers/free_proxy_list_ssl.rb +1 -0
- data/lib/proxy_fetcher/providers/free_proxy_list_us.rb +54 -0
- data/lib/proxy_fetcher/providers/mtpro.rb +1 -1
- data/lib/proxy_fetcher/providers/proxyscrape_http.rb +65 -0
- data/lib/proxy_fetcher/providers/proxyscrape_socks4.rb +65 -0
- data/lib/proxy_fetcher/providers/proxyscrape_socks5.rb +65 -0
- data/lib/proxy_fetcher/providers/xroxy.rb +1 -1
- data/lib/proxy_fetcher/utils/http_client.rb +1 -8
- data/lib/proxy_fetcher/utils/proxy_validator.rb +20 -8
- data/lib/proxy_fetcher/version.rb +1 -1
- data/proxy_fetcher.gemspec +6 -4
- data/spec/proxy_fetcher/client/client_spec.rb +5 -5
- data/spec/proxy_fetcher/providers/proxy_classes_spec.rb +28 -0
- metadata +12 -14
- data/lib/proxy_fetcher/providers/gather_proxy.rb +0 -50
- data/spec/proxy_fetcher/providers/free_proxy_list_spec.rb +0 -13
- data/spec/proxy_fetcher/providers/free_proxy_list_ssl_spec.rb +0 -11
- data/spec/proxy_fetcher/providers/gather_proxy_spec.rb +0 -11
- data/spec/proxy_fetcher/providers/http_tunnel_spec.rb +0 -11
- data/spec/proxy_fetcher/providers/mtpro_spec.rb +0 -11
- data/spec/proxy_fetcher/providers/proxy_list_spec.rb +0 -11
- data/spec/proxy_fetcher/providers/proxypedia_spec.rb +0 -11
- data/spec/proxy_fetcher/providers/xroxy_spec.rb +0 -11
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: bf6591a8ede2c142fca7f433f3edceb407ed884c1dee6a98e3ca33efbae392e2
|
4
|
+
data.tar.gz: 7d7259da718adec21b8d749d04faf594fa926389e570be6c55bbe9ebf3695783
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 90eed5f390d122ae58f9bd6c7553b7a1ff6bbca8e65c05406593f53b7a00a4ed160120ae62d0ce8289965810aaa3795287769ee9ef12f9404d805694a8ac0cff
|
7
|
+
data.tar.gz: 31a5b4fcd6199dfc75ca3e89c7bddcc82533ca171f86954e50d4ff44716d73f1ad014f921a05e9eb2fd38a83c5e603eec1fbbf9530b4c01153f6780877388501
|
data/Rakefile
CHANGED
data/gemfiles/nokogiri.gemfile
CHANGED
data/gemfiles/oga.gemfile
CHANGED
data/lib/proxy_fetcher.rb
CHANGED
@@ -33,13 +33,17 @@ module ProxyFetcher
|
|
33
33
|
# ProxyFetcher providers namespace
|
34
34
|
module Providers
|
35
35
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/base"
|
36
|
-
require File.dirname(__FILE__) + "/proxy_fetcher/providers/proxypedia"
|
37
36
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/free_proxy_list"
|
37
|
+
require File.dirname(__FILE__) + "/proxy_fetcher/providers/free_proxy_list_socks"
|
38
38
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/free_proxy_list_ssl"
|
39
|
-
require File.dirname(__FILE__) + "/proxy_fetcher/providers/
|
39
|
+
require File.dirname(__FILE__) + "/proxy_fetcher/providers/free_proxy_list_us"
|
40
40
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/http_tunnel"
|
41
41
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/mtpro"
|
42
42
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/proxy_list"
|
43
|
+
require File.dirname(__FILE__) + "/proxy_fetcher/providers/proxypedia"
|
44
|
+
require File.dirname(__FILE__) + "/proxy_fetcher/providers/proxyscrape_http"
|
45
|
+
require File.dirname(__FILE__) + "/proxy_fetcher/providers/proxyscrape_socks4"
|
46
|
+
require File.dirname(__FILE__) + "/proxy_fetcher/providers/proxyscrape_socks5"
|
43
47
|
require File.dirname(__FILE__) + "/proxy_fetcher/providers/xroxy"
|
44
48
|
end
|
45
49
|
|
@@ -47,6 +47,8 @@ module ProxyFetcher
|
|
47
47
|
|
48
48
|
ProxyFetcher.config.providers.each do |provider_name|
|
49
49
|
threads << Thread.new do
|
50
|
+
Thread.current.report_on_exception = false
|
51
|
+
|
50
52
|
provider = ProxyFetcher::Configuration.providers_registry.class_for(provider_name)
|
51
53
|
provider_filters = filters && filters.fetch(provider_name.to_sym, filters)
|
52
54
|
provider_proxies = provider.fetch_proxies!(provider_filters)
|
@@ -0,0 +1,58 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module ProxyFetcher
|
4
|
+
module Providers
|
5
|
+
# FreeProxyListSocks provider class.
|
6
|
+
class FreeProxyListSocks < Base
|
7
|
+
# Provider URL to fetch proxy list
|
8
|
+
def provider_url
|
9
|
+
"https://www.socks-proxy.net/"
|
10
|
+
end
|
11
|
+
|
12
|
+
# [NOTE] Doesn't support filtering
|
13
|
+
def xpath
|
14
|
+
'//table[@id="proxylisttable"]/tbody/tr'
|
15
|
+
end
|
16
|
+
|
17
|
+
# Converts HTML node (entry of N tags) to <code>ProxyFetcher::Proxy</code>
|
18
|
+
# object.
|
19
|
+
#
|
20
|
+
# @param html_node [Object]
|
21
|
+
# HTML node from the <code>ProxyFetcher::Document</code> DOM model.
|
22
|
+
#
|
23
|
+
# @return [ProxyFetcher::Proxy]
|
24
|
+
# Proxy object
|
25
|
+
#
|
26
|
+
def to_proxy(html_node)
|
27
|
+
ProxyFetcher::Proxy.new.tap do |proxy|
|
28
|
+
proxy.addr = html_node.content_at("td[1]")
|
29
|
+
proxy.port = Integer(html_node.content_at("td[2]").gsub(/^0+/, ""))
|
30
|
+
proxy.country = html_node.content_at("td[4]")
|
31
|
+
proxy.type = parse_type(html_node)
|
32
|
+
proxy.anonymity = html_node.content_at("td[6]")
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
# Parses HTML node to extract proxy type.
|
39
|
+
#
|
40
|
+
# @param html_node [Object]
|
41
|
+
# HTML node from the <code>ProxyFetcher::Document</code> DOM model.
|
42
|
+
#
|
43
|
+
# @return [String]
|
44
|
+
# Proxy type
|
45
|
+
#
|
46
|
+
def parse_type(html_node)
|
47
|
+
https = html_node.content_at("td[5]")
|
48
|
+
|
49
|
+
return ProxyFetcher::Proxy::SOCKS4 if https&.casecmp("socks4")&.zero?
|
50
|
+
return ProxyFetcher::Proxy::SOCKS5 if https&.casecmp("socks5")&.zero?
|
51
|
+
|
52
|
+
"Unknown"
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
ProxyFetcher::Configuration.register_provider(:free_proxy_list_socks, FreeProxyListSocks)
|
57
|
+
end
|
58
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module ProxyFetcher
|
4
|
+
module Providers
|
5
|
+
# FreeProxyListUS provider class.
|
6
|
+
class FreeProxyListUS < Base
|
7
|
+
# Provider URL to fetch proxy list
|
8
|
+
def provider_url
|
9
|
+
"https://www.us-proxy.org/"
|
10
|
+
end
|
11
|
+
|
12
|
+
# [NOTE] Doesn't support filtering
|
13
|
+
def xpath
|
14
|
+
'//table[@id="proxylisttable"]/tbody/tr'
|
15
|
+
end
|
16
|
+
|
17
|
+
# Converts HTML node (entry of N tags) to <code>ProxyFetcher::Proxy</code>
|
18
|
+
# object.
|
19
|
+
#
|
20
|
+
# @param html_node [Object]
|
21
|
+
# HTML node from the <code>ProxyFetcher::Document</code> DOM model.
|
22
|
+
#
|
23
|
+
# @return [ProxyFetcher::Proxy]
|
24
|
+
# Proxy object
|
25
|
+
#
|
26
|
+
def to_proxy(html_node)
|
27
|
+
ProxyFetcher::Proxy.new.tap do |proxy|
|
28
|
+
proxy.addr = html_node.content_at("td[1]")
|
29
|
+
proxy.port = Integer(html_node.content_at("td[2]").gsub(/^0+/, ""))
|
30
|
+
proxy.country = html_node.content_at("td[4]")
|
31
|
+
proxy.anonymity = html_node.content_at("td[5]")
|
32
|
+
proxy.type = parse_type(html_node)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
# Parses HTML node to extract proxy type.
|
39
|
+
#
|
40
|
+
# @param html_node [Object]
|
41
|
+
# HTML node from the <code>ProxyFetcher::Document</code> DOM model.
|
42
|
+
#
|
43
|
+
# @return [String]
|
44
|
+
# Proxy type
|
45
|
+
#
|
46
|
+
def parse_type(html_node)
|
47
|
+
https = html_node.content_at("td[7]")
|
48
|
+
https&.casecmp("yes")&.zero? ? ProxyFetcher::Proxy::HTTPS : ProxyFetcher::Proxy::HTTP
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
ProxyFetcher::Configuration.register_provider(:free_proxy_list_us, FreeProxyListUS)
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "csv"
|
4
|
+
|
5
|
+
module ProxyFetcher
|
6
|
+
module Providers
|
7
|
+
# FreeProxyList provider class.
|
8
|
+
class ProxyscrapeHTTP < Base
|
9
|
+
# Provider URL to fetch proxy list
|
10
|
+
def provider_url
|
11
|
+
"https://api.proxyscrape.com/v2/?request=getproxies&protocol=http"
|
12
|
+
end
|
13
|
+
|
14
|
+
# Loads provider HTML and parses it with internal document object.
|
15
|
+
#
|
16
|
+
# @param url [String]
|
17
|
+
# URL to fetch
|
18
|
+
#
|
19
|
+
# @param filters [Hash]
|
20
|
+
# filters for proxy provider
|
21
|
+
#
|
22
|
+
# @return [Array]
|
23
|
+
# Collection of extracted proxies with ports
|
24
|
+
#
|
25
|
+
def load_document(url, filters = {})
|
26
|
+
html = load_html(url, filters)
|
27
|
+
|
28
|
+
CSV.parse(html, col_sep: "\t").map(&:first)
|
29
|
+
end
|
30
|
+
|
31
|
+
# Fetches HTML content by sending HTTP request to the provider URL and
|
32
|
+
# parses the txt document to return all the proxy entries (ip addresses
|
33
|
+
# and ports).
|
34
|
+
#
|
35
|
+
# @return [Array]
|
36
|
+
# Collection of extracted proxies with ports
|
37
|
+
#
|
38
|
+
def load_proxy_list(filters = {})
|
39
|
+
load_document(provider_url, filters)
|
40
|
+
end
|
41
|
+
|
42
|
+
# Converts String to <code>ProxyFetcher::Proxy</code> object.
|
43
|
+
#
|
44
|
+
# @param node [String]
|
45
|
+
# String
|
46
|
+
#
|
47
|
+
# @return [ProxyFetcher::Proxy]
|
48
|
+
# Proxy object
|
49
|
+
#
|
50
|
+
def to_proxy(node)
|
51
|
+
addr, port = node.split(":")
|
52
|
+
|
53
|
+
ProxyFetcher::Proxy.new.tap do |proxy|
|
54
|
+
proxy.addr = addr
|
55
|
+
proxy.port = Integer(port)
|
56
|
+
proxy.country = "Unknown"
|
57
|
+
proxy.anonymity = "Unknown"
|
58
|
+
proxy.type = ProxyFetcher::Proxy::HTTP
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
ProxyFetcher::Configuration.register_provider(:proxyscrape_http, ProxyscrapeHTTP)
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "csv"
|
4
|
+
|
5
|
+
module ProxyFetcher
|
6
|
+
module Providers
|
7
|
+
# FreeProxyList provider class.
|
8
|
+
class ProxyscrapeSOCKS4 < Base
|
9
|
+
# Provider URL to fetch proxy list
|
10
|
+
def provider_url
|
11
|
+
"https://api.proxyscrape.com/v2/?request=getproxies&protocol=socks4"
|
12
|
+
end
|
13
|
+
|
14
|
+
# Loads provider HTML and parses it with internal document object.
|
15
|
+
#
|
16
|
+
# @param url [String]
|
17
|
+
# URL to fetch
|
18
|
+
#
|
19
|
+
# @param filters [Hash]
|
20
|
+
# filters for proxy provider
|
21
|
+
#
|
22
|
+
# @return [Array]
|
23
|
+
# Collection of extracted proxies with ports
|
24
|
+
#
|
25
|
+
def load_document(url, filters = {})
|
26
|
+
html = load_html(url, filters)
|
27
|
+
|
28
|
+
CSV.parse(html, col_sep: "\t").map(&:first)
|
29
|
+
end
|
30
|
+
|
31
|
+
# Fetches HTML content by sending HTTP request to the provider URL and
|
32
|
+
# parses the txt document to return all the proxy entries (ip addresses
|
33
|
+
# and ports).
|
34
|
+
#
|
35
|
+
# @return [Array]
|
36
|
+
# Collection of extracted proxies with ports
|
37
|
+
#
|
38
|
+
def load_proxy_list(filters = {})
|
39
|
+
load_document(provider_url, filters)
|
40
|
+
end
|
41
|
+
|
42
|
+
# Converts String to <code>ProxyFetcher::Proxy</code> object.
|
43
|
+
#
|
44
|
+
# @param node [String]
|
45
|
+
# String
|
46
|
+
#
|
47
|
+
# @return [ProxyFetcher::Proxy]
|
48
|
+
# Proxy object
|
49
|
+
#
|
50
|
+
def to_proxy(html_node)
|
51
|
+
addr, port = html_node.split(":")
|
52
|
+
|
53
|
+
ProxyFetcher::Proxy.new.tap do |proxy|
|
54
|
+
proxy.addr = addr
|
55
|
+
proxy.port = Integer(port)
|
56
|
+
proxy.country = "Unknown"
|
57
|
+
proxy.anonymity = "Unknown"
|
58
|
+
proxy.type = ProxyFetcher::Proxy::SOCKS4
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
ProxyFetcher::Configuration.register_provider(:proxyscrape_socks4, ProxyscrapeSOCKS4)
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "csv"
|
4
|
+
|
5
|
+
module ProxyFetcher
|
6
|
+
module Providers
|
7
|
+
# FreeProxyList provider class.
|
8
|
+
class ProxyscrapeSOCKS5 < Base
|
9
|
+
# Provider URL to fetch proxy list
|
10
|
+
def provider_url
|
11
|
+
"https://api.proxyscrape.com/v2/?request=getproxies&protocol=socks5"
|
12
|
+
end
|
13
|
+
|
14
|
+
# Loads provider HTML and parses it with internal document object.
|
15
|
+
#
|
16
|
+
# @param url [String]
|
17
|
+
# URL to fetch
|
18
|
+
#
|
19
|
+
# @param filters [Hash]
|
20
|
+
# filters for proxy provider
|
21
|
+
#
|
22
|
+
# @return [Array]
|
23
|
+
# Collection of extracted proxies with ports
|
24
|
+
#
|
25
|
+
def load_document(url, filters = {})
|
26
|
+
html = load_html(url, filters)
|
27
|
+
|
28
|
+
CSV.parse(html, col_sep: "\t").map(&:first)
|
29
|
+
end
|
30
|
+
|
31
|
+
# Fetches HTML content by sending HTTP request to the provider URL and
|
32
|
+
# parses the txt document to return all the proxy entries (ip addresses
|
33
|
+
# and ports).
|
34
|
+
#
|
35
|
+
# @return [Array]
|
36
|
+
# Collection of extracted proxies with ports
|
37
|
+
#
|
38
|
+
def load_proxy_list(filters = {})
|
39
|
+
load_document(provider_url, filters)
|
40
|
+
end
|
41
|
+
|
42
|
+
# Converts String to <code>ProxyFetcher::Proxy</code> object.
|
43
|
+
#
|
44
|
+
# @param node [String]
|
45
|
+
# String
|
46
|
+
#
|
47
|
+
# @return [ProxyFetcher::Proxy]
|
48
|
+
# Proxy object
|
49
|
+
#
|
50
|
+
def to_proxy(html_node)
|
51
|
+
addr, port = html_node.split(":")
|
52
|
+
|
53
|
+
ProxyFetcher::Proxy.new.tap do |proxy|
|
54
|
+
proxy.addr = addr
|
55
|
+
proxy.port = Integer(port)
|
56
|
+
proxy.country = "Unknown"
|
57
|
+
proxy.anonymity = "Unknown"
|
58
|
+
proxy.type = ProxyFetcher::Proxy::SOCKS5
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
ProxyFetcher::Configuration.register_provider(:proxyscrape_socks5, ProxyscrapeSOCKS5)
|
64
|
+
end
|
65
|
+
end
|
@@ -71,17 +71,10 @@ module ProxyFetcher
|
|
71
71
|
response = process_http_request
|
72
72
|
response.body.to_s
|
73
73
|
rescue StandardError => e
|
74
|
-
ProxyFetcher.logger.warn("Failed to process request to #{url} (#{e.message})")
|
74
|
+
ProxyFetcher.config.logger.warn("Failed to process request to #{url} (#{e.message})")
|
75
75
|
""
|
76
76
|
end
|
77
77
|
|
78
|
-
def fetch_with_headers
|
79
|
-
process_http_request
|
80
|
-
rescue StandardError => e
|
81
|
-
ProxyFetcher.logger.warn("Failed to process request to #{url} (#{e.message})")
|
82
|
-
HTTP::Response.new(version: "1.1", status: 500, body: "")
|
83
|
-
end
|
84
|
-
|
85
78
|
protected
|
86
79
|
|
87
80
|
def process_http_request(http_method: method, http_params: params)
|
@@ -10,27 +10,39 @@ module ProxyFetcher
|
|
10
10
|
|
11
11
|
# Short variant to validate proxy.
|
12
12
|
#
|
13
|
-
# @param
|
14
|
-
# @param
|
13
|
+
# @param address [String] proxy address or IP
|
14
|
+
# @param port [String, Integer] proxy port
|
15
15
|
#
|
16
16
|
# @return [Boolean]
|
17
17
|
# true if connection to the server using proxy established, otherwise false
|
18
18
|
#
|
19
|
-
def self.connectable?(
|
20
|
-
new(
|
19
|
+
def self.connectable?(address, port)
|
20
|
+
new(address, port).connectable?
|
21
21
|
end
|
22
22
|
|
23
23
|
# Initialize new ProxyValidator instance
|
24
24
|
#
|
25
|
-
# @param
|
26
|
-
# @param
|
25
|
+
# @param address [String] Proxy address or IP
|
26
|
+
# @param port [String, Integer] Proxy port
|
27
|
+
# @param options [Hash] proxy options
|
28
|
+
# @option username [String] Proxy authentication username
|
29
|
+
# @option password [String] Proxy authentication password
|
30
|
+
# @option headers [Hash] Proxy headers
|
27
31
|
#
|
28
32
|
# @return [ProxyValidator]
|
29
33
|
#
|
30
|
-
def initialize(
|
34
|
+
def initialize(address, port, options: {})
|
31
35
|
timeout = ProxyFetcher.config.proxy_validation_timeout
|
36
|
+
proxy = [address, port.to_i]
|
32
37
|
|
33
|
-
|
38
|
+
if options[:username] && options[:password]
|
39
|
+
proxy << options[:username]
|
40
|
+
proxy << options[:password]
|
41
|
+
end
|
42
|
+
|
43
|
+
proxy << options[:headers].to_h if options[:headers]
|
44
|
+
|
45
|
+
@http = HTTP.follow.via(*proxy).timeout(connect: timeout, read: timeout)
|
34
46
|
end
|
35
47
|
|
36
48
|
# Checks if proxy is connectable (can be used to connect
|
data/proxy_fetcher.gemspec
CHANGED
@@ -8,9 +8,11 @@ Gem::Specification.new do |gem|
|
|
8
8
|
gem.name = "proxy_fetcher"
|
9
9
|
gem.version = ProxyFetcher.gem_version
|
10
10
|
gem.summary = "Ruby gem for dealing with proxy lists from different providers"
|
11
|
-
gem.description =
|
12
|
-
|
13
|
-
|
11
|
+
gem.description = <<-TEXT.strip.gsub(/[\s\n]+/, " ")
|
12
|
+
This gem can help your Ruby application to make HTTP(S) requests
|
13
|
+
using proxies by fetching and validating proxy lists from
|
14
|
+
the different providers.
|
15
|
+
TEXT
|
14
16
|
gem.authors = ["Nikita Bulai"]
|
15
17
|
gem.email = "bulajnikita@gmail.com"
|
16
18
|
gem.require_paths = ["lib"]
|
@@ -24,5 +26,5 @@ Gem::Specification.new do |gem|
|
|
24
26
|
gem.add_runtime_dependency "http", ">= 3", "< 5"
|
25
27
|
|
26
28
|
gem.add_development_dependency "rake", ">= 12.0"
|
27
|
-
gem.add_development_dependency "rspec", "~> 3.
|
29
|
+
gem.add_development_dependency "rspec", "~> 3.9"
|
28
30
|
end
|
@@ -118,15 +118,15 @@ describe ProxyFetcher::Client do
|
|
118
118
|
end
|
119
119
|
end
|
120
120
|
|
121
|
-
|
121
|
+
context "retries" do
|
122
122
|
it "raises an error when reaches max retries limit" do
|
123
123
|
allow(ProxyFetcher::Client::Request).to receive(:execute).and_raise(StandardError)
|
124
124
|
|
125
|
-
expect { ProxyFetcher::Client.get("http://httpbin.org") }
|
125
|
+
expect { ProxyFetcher::Client.get("http://httpbin.org", options: { max_retries: 10 }) }
|
126
126
|
.to raise_error(ProxyFetcher::Exceptions::MaximumRetriesReached)
|
127
127
|
end
|
128
128
|
|
129
|
-
|
129
|
+
xit "raises an error when http request returns an error" do
|
130
130
|
allow_any_instance_of(HTTP::Client).to receive(:get).and_return(StandardError.new)
|
131
131
|
|
132
132
|
expect { ProxyFetcher::Client.get("http://httpbin.org") }
|
@@ -134,14 +134,14 @@ describe ProxyFetcher::Client do
|
|
134
134
|
end
|
135
135
|
|
136
136
|
it "refreshes proxy lists if no proxy found" do
|
137
|
-
ProxyFetcher::
|
137
|
+
allow(ProxyFetcher::Manager.new).to receive(:proxies).and_return([])
|
138
138
|
|
139
139
|
expect { ProxyFetcher::Client.get("http://httpbin.org") }
|
140
140
|
.not_to raise_error
|
141
141
|
end
|
142
142
|
end
|
143
143
|
|
144
|
-
|
144
|
+
xcontext "redirects" do
|
145
145
|
it "follows redirect when present" do
|
146
146
|
content = ProxyFetcher::Client.get("http://httpbin.org/absolute-redirect/2")
|
147
147
|
|
@@ -0,0 +1,28 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
describe "Proxy classes" do
|
6
|
+
[
|
7
|
+
[:free_proxy_list, "FreeProxyList"],
|
8
|
+
[:free_proxy_list_socks, "FreeProxyListSocks"],
|
9
|
+
[:free_proxy_list_ssl, "FreeProxyListSSL"],
|
10
|
+
[:free_proxy_list_us, "FreeProxyListUS"],
|
11
|
+
[:http_tunnel, "HTTPTunnel"],
|
12
|
+
[:mtpro, "MTPro"],
|
13
|
+
[:proxy_list, "ProxyList"],
|
14
|
+
[:proxypedia, "Proxypedia"],
|
15
|
+
[:proxyscrape_http, "ProxyscrapeHTTP"],
|
16
|
+
[:proxyscrape_socks4, "ProxyscrapeSOCKS4"],
|
17
|
+
[:proxyscrape_socks5, "ProxyscrapeSOCKS5"],
|
18
|
+
[:xroxy, "XRoxy"]
|
19
|
+
].each do |(provider_name, provider_klass)|
|
20
|
+
describe Object.const_get("ProxyFetcher::Providers::#{provider_klass}") do
|
21
|
+
before :all do
|
22
|
+
ProxyFetcher.config.provider = provider_name
|
23
|
+
end
|
24
|
+
|
25
|
+
it_behaves_like "a manager"
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: proxy_fetcher
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.15.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Nikita Bulai
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-01-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: http
|
@@ -50,14 +50,14 @@ dependencies:
|
|
50
50
|
requirements:
|
51
51
|
- - "~>"
|
52
52
|
- !ruby/object:Gem::Version
|
53
|
-
version: '3.
|
53
|
+
version: '3.9'
|
54
54
|
type: :development
|
55
55
|
prerelease: false
|
56
56
|
version_requirements: !ruby/object:Gem::Requirement
|
57
57
|
requirements:
|
58
58
|
- - "~>"
|
59
59
|
- !ruby/object:Gem::Version
|
60
|
-
version: '3.
|
60
|
+
version: '3.9'
|
61
61
|
description: This gem can help your Ruby application to make HTTP(S) requests using
|
62
62
|
proxies by fetching and validating proxy lists from the different providers.
|
63
63
|
email: bulajnikita@gmail.com
|
@@ -94,12 +94,16 @@ files:
|
|
94
94
|
- lib/proxy_fetcher/null_logger.rb
|
95
95
|
- lib/proxy_fetcher/providers/base.rb
|
96
96
|
- lib/proxy_fetcher/providers/free_proxy_list.rb
|
97
|
+
- lib/proxy_fetcher/providers/free_proxy_list_socks.rb
|
97
98
|
- lib/proxy_fetcher/providers/free_proxy_list_ssl.rb
|
98
|
-
- lib/proxy_fetcher/providers/
|
99
|
+
- lib/proxy_fetcher/providers/free_proxy_list_us.rb
|
99
100
|
- lib/proxy_fetcher/providers/http_tunnel.rb
|
100
101
|
- lib/proxy_fetcher/providers/mtpro.rb
|
101
102
|
- lib/proxy_fetcher/providers/proxy_list.rb
|
102
103
|
- lib/proxy_fetcher/providers/proxypedia.rb
|
104
|
+
- lib/proxy_fetcher/providers/proxyscrape_http.rb
|
105
|
+
- lib/proxy_fetcher/providers/proxyscrape_socks4.rb
|
106
|
+
- lib/proxy_fetcher/providers/proxyscrape_socks5.rb
|
103
107
|
- lib/proxy_fetcher/providers/xroxy.rb
|
104
108
|
- lib/proxy_fetcher/proxy.rb
|
105
109
|
- lib/proxy_fetcher/utils/http_client.rb
|
@@ -114,15 +118,8 @@ files:
|
|
114
118
|
- spec/proxy_fetcher/document/node_spec.rb
|
115
119
|
- spec/proxy_fetcher/manager_spec.rb
|
116
120
|
- spec/proxy_fetcher/providers/base_spec.rb
|
117
|
-
- spec/proxy_fetcher/providers/free_proxy_list_spec.rb
|
118
|
-
- spec/proxy_fetcher/providers/free_proxy_list_ssl_spec.rb
|
119
|
-
- spec/proxy_fetcher/providers/gather_proxy_spec.rb
|
120
|
-
- spec/proxy_fetcher/providers/http_tunnel_spec.rb
|
121
|
-
- spec/proxy_fetcher/providers/mtpro_spec.rb
|
122
121
|
- spec/proxy_fetcher/providers/multiple_providers_spec.rb
|
123
|
-
- spec/proxy_fetcher/providers/
|
124
|
-
- spec/proxy_fetcher/providers/proxypedia_spec.rb
|
125
|
-
- spec/proxy_fetcher/providers/xroxy_spec.rb
|
122
|
+
- spec/proxy_fetcher/providers/proxy_classes_spec.rb
|
126
123
|
- spec/proxy_fetcher/proxy_spec.rb
|
127
124
|
- spec/proxy_fetcher/version_spec.rb
|
128
125
|
- spec/spec_helper.rb
|
@@ -146,7 +143,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
146
143
|
- !ruby/object:Gem::Version
|
147
144
|
version: '0'
|
148
145
|
requirements: []
|
149
|
-
|
146
|
+
rubyforge_project:
|
147
|
+
rubygems_version: 2.7.9
|
150
148
|
signing_key:
|
151
149
|
specification_version: 4
|
152
150
|
summary: Ruby gem for dealing with proxy lists from different providers
|
@@ -1,50 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
require "json"
|
4
|
-
|
5
|
-
module ProxyFetcher
|
6
|
-
module Providers
|
7
|
-
# GatherProxy provider class.
|
8
|
-
class GatherProxy < Base
|
9
|
-
# Provider URL to fetch proxy list
|
10
|
-
def provider_url
|
11
|
-
"https://proxygather.com"
|
12
|
-
end
|
13
|
-
|
14
|
-
def xpath
|
15
|
-
'//div[@class="proxy-list"]/table/script'
|
16
|
-
end
|
17
|
-
|
18
|
-
# Converts HTML node (entry of N tags) to <code>ProxyFetcher::Proxy</code>
|
19
|
-
# object.
|
20
|
-
#
|
21
|
-
# @param html_node [Object]
|
22
|
-
# HTML node from the <code>ProxyFetcher::Document</code> DOM model.
|
23
|
-
#
|
24
|
-
# @return [ProxyFetcher::Proxy]
|
25
|
-
# Proxy object
|
26
|
-
#
|
27
|
-
def to_proxy(html_node)
|
28
|
-
json = parse_json(html_node)
|
29
|
-
|
30
|
-
ProxyFetcher::Proxy.new.tap do |proxy|
|
31
|
-
proxy.addr = json["PROXY_IP"]
|
32
|
-
proxy.port = json["PROXY_PORT"].to_i(16)
|
33
|
-
proxy.anonymity = json["PROXY_TYPE"]
|
34
|
-
proxy.country = json["PROXY_COUNTRY"]
|
35
|
-
proxy.response_time = json["PROXY_TIME"].to_i
|
36
|
-
proxy.type = ProxyFetcher::Proxy::HTTP
|
37
|
-
end
|
38
|
-
end
|
39
|
-
|
40
|
-
private
|
41
|
-
|
42
|
-
def parse_json(html_node)
|
43
|
-
javascript = html_node.content[/{.+}/im]
|
44
|
-
JSON.parse(javascript)
|
45
|
-
end
|
46
|
-
end
|
47
|
-
|
48
|
-
ProxyFetcher::Configuration.register_provider(:gather_proxy, GatherProxy)
|
49
|
-
end
|
50
|
-
end
|
@@ -1,13 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
require "spec_helper"
|
4
|
-
|
5
|
-
describe ProxyFetcher::Providers::FreeProxyList do
|
6
|
-
before :all do
|
7
|
-
ProxyFetcher.configure do |config|
|
8
|
-
config.provider = :free_proxy_list
|
9
|
-
end
|
10
|
-
end
|
11
|
-
|
12
|
-
it_behaves_like "a manager"
|
13
|
-
end
|