http_crawler 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.idea/vcs.xml +6 -0
- data/.rspec +1 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +10 -0
- data/README.md +55 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/http_crawler.gemspec +45 -0
- data/lib/http_crawler/client.rb +88 -0
- data/lib/http_crawler/http.rb +211 -0
- data/lib/http_crawler/net/http.rb +7 -0
- data/lib/http_crawler/net/response.rb +96 -0
- data/lib/http_crawler/object.rb +13 -0
- data/lib/http_crawler/proxy/README.md +3 -0
- data/lib/http_crawler/proxy/client.rb +7 -0
- data/lib/http_crawler/proxy/response.rb +10 -0
- data/lib/http_crawler/proxy/test_proxy_api/README.md +18 -0
- data/lib/http_crawler/proxy/test_proxy_api/client.rb +29 -0
- data/lib/http_crawler/proxy/test_proxy_api/response/get_proxy.rb +24 -0
- data/lib/http_crawler/proxy/test_proxy_api/response.rb +12 -0
- data/lib/http_crawler/proxy.rb +18 -0
- data/lib/http_crawler/string.rb +9 -0
- data/lib/http_crawler/version.rb +3 -0
- data/lib/http_crawler/web/README.md +4 -0
- data/lib/http_crawler/web/baidu/README.md +19 -0
- data/lib/http_crawler/web/baidu/client.rb +25 -0
- data/lib/http_crawler/web/baidu/response/index.rb +16 -0
- data/lib/http_crawler/web/baidu/response.rb +10 -0
- data/lib/http_crawler/web.rb +7 -0
- data/lib/http_crawler.rb +9 -0
- metadata +175 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f034023a8c50c41be3d4e423d39fa2ad44e75930
|
4
|
+
data.tar.gz: 745c8a86a328387f8b8c7ef68e351c5d63d4d61a
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: aab1febfdc72a126e9edb1b496b661d236d3ae6689d5bf29350d4bffdbb4e9551e03487c2a7fc01d6ec7f15ff55d0872db8f90fb791474834982168aca88e531
|
7
|
+
data.tar.gz: 317de9a4ef0d5423b57de20cb9220cdecd598d431d67f03b025fd05c0a2ce2d013eec4e3da816ce50a35722c161aef01a90ee376add0e0ebc06c779b0e296370
|
data/.gitignore
ADDED
data/.idea/vcs.xml
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--require spec_helper
|
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at 1336098842@qq.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
@@ -0,0 +1,10 @@
|
|
1
|
+
source "https://rubygems.org"
|
2
|
+
|
3
|
+
git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
|
4
|
+
# gem 'rchardet', '~> 1.8'
|
5
|
+
# gem 'nokogiri', '~> 1.8.4'
|
6
|
+
#
|
7
|
+
# gem "ruby-readability", :require => 'readability'
|
8
|
+
|
9
|
+
# Specify your gem's dependencies in http_crawler.gemspec
|
10
|
+
gemspec
|
data/README.md
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
# HttpCrawler
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/http_crawler`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'http_crawler'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install http_crawler
|
22
|
+
|
23
|
+
|
24
|
+
## 示例:百度爬虫维护
|
25
|
+
|
26
|
+
|
27
|
+
### 通过对象调用
|
28
|
+
|
29
|
+
```ruby
|
30
|
+
client = HttpCrawler::Client::Baidu::Client.new
|
31
|
+
client.index # 抓取首页
|
32
|
+
```
|
33
|
+
|
34
|
+
### 通过别名调用
|
35
|
+
```ruby
|
36
|
+
client = HttpCrawler::Client.for("baidu") #
|
37
|
+
client.index # 抓取首页
|
38
|
+
```
|
39
|
+
|
40
|
+
|
41
|
+
## 示例:测试API
|
42
|
+
|
43
|
+
|
44
|
+
### 通过对象调用
|
45
|
+
|
46
|
+
```ruby
|
47
|
+
client = HttpCrawler::Proxy::TestProxyApi::Client.new
|
48
|
+
client.index # 抓取首页
|
49
|
+
```
|
50
|
+
|
51
|
+
### 通过别名调用
|
52
|
+
```ruby
|
53
|
+
client = HttpCrawler::Proxy.for("test_proxy_api") #
|
54
|
+
client.index # 抓取首页
|
55
|
+
```
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "http_crawler"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "http_crawler/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "http_crawler"
|
8
|
+
spec.version = HttpCrawler::VERSION
|
9
|
+
spec.authors = ["jagger"]
|
10
|
+
spec.email = ["1336098842@qq.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{http 爬虫。}
|
13
|
+
spec.description = %q{初级开发工程师,基于net/http 写的爬虫扩展包。}
|
14
|
+
spec.homepage = "https://rubygems.org/gems/http_crawler"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
if spec.respond_to?(:metadata)
|
20
|
+
spec.metadata["allowed_push_host"] = "https://rubygems.org"
|
21
|
+
else
|
22
|
+
raise "RubyGems 2.0 or newer is required to protect against " \
|
23
|
+
"public gem pushes."
|
24
|
+
end
|
25
|
+
|
26
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
27
|
+
f.match(%r{^(test|spec|features)/})
|
28
|
+
end
|
29
|
+
|
30
|
+
spec.files += Dir['lib/**/*.rb']
|
31
|
+
|
32
|
+
spec.bindir = "exe"
|
33
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
34
|
+
spec.require_paths = ["lib"]
|
35
|
+
|
36
|
+
spec.add_development_dependency "rspec", "~> 3.8"
|
37
|
+
spec.add_development_dependency "bundler", "~> 1.15"
|
38
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
39
|
+
|
40
|
+
spec.add_dependency "rchardet", "~> 1.8"
|
41
|
+
spec.add_dependency "nokogiri", "~> 1.8"
|
42
|
+
spec.add_dependency "ruby-readability", "~> 0.7.0"
|
43
|
+
spec.add_dependency "brotli", "~> 0.2.1"
|
44
|
+
|
45
|
+
end
|
@@ -0,0 +1,88 @@
|
|
1
|
+
load File.dirname(__FILE__) + '/http.rb'
|
2
|
+
load File.dirname(__FILE__) + '/object.rb'
|
3
|
+
load File.dirname(__FILE__) + '/string.rb'
|
4
|
+
|
5
|
+
module HttpCrawler
|
6
|
+
module Client
|
7
|
+
|
8
|
+
class << self
|
9
|
+
|
10
|
+
# 接收格式
|
11
|
+
# web_name = "biquge_duquanben"
|
12
|
+
# 返回 HttpCrawler::Web::BiqugeDuquanben::Client 实例
|
13
|
+
#
|
14
|
+
def for(web_name, *args)
|
15
|
+
"HttpCrawler::Web::#{web_name.camelize}::Client".constantize.new(*args)
|
16
|
+
end
|
17
|
+
|
18
|
+
#
|
19
|
+
# 接收格式
|
20
|
+
# module_name = "HttpCrawler::Web::BiqugeDuquanben"
|
21
|
+
# 返回 HttpCrawler::Web::BiqugeDuquanben::Client 实例
|
22
|
+
#
|
23
|
+
def for_module(module_name, *args)
|
24
|
+
"#{module_name}::Client".constantize.new(*args)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
attr_reader :http, :uri
|
29
|
+
|
30
|
+
#
|
31
|
+
# init_uri 如果未初始化@uri,则会报错
|
32
|
+
# 继承类需要重定义 init_uri
|
33
|
+
#
|
34
|
+
def initialize
|
35
|
+
raise "Client uri为空" unless init_uri
|
36
|
+
@http = Crawler::HTTP.new(uri.host, uri.port)
|
37
|
+
|
38
|
+
@http.use_ssl = (uri.scheme == "https")
|
39
|
+
|
40
|
+
@http.open_timeout = 5
|
41
|
+
@http.read_timeout = 5
|
42
|
+
@http.proxy_key = "#{self.class}"
|
43
|
+
init_http
|
44
|
+
|
45
|
+
Rails.logger.debug "proxy_key => #{@http.proxy_key}"
|
46
|
+
end
|
47
|
+
|
48
|
+
# 初始化http参数
|
49
|
+
def init_http
|
50
|
+
|
51
|
+
end
|
52
|
+
|
53
|
+
# init_uri 如果未初始化@uri,则会报错
|
54
|
+
# 继承类需要实现 @uri = URI("http://host")
|
55
|
+
#
|
56
|
+
def init_uri
|
57
|
+
@uri = nil
|
58
|
+
end
|
59
|
+
|
60
|
+
def header
|
61
|
+
@header ||= init_header
|
62
|
+
end
|
63
|
+
|
64
|
+
def init_header
|
65
|
+
nil
|
66
|
+
end
|
67
|
+
|
68
|
+
def update_header(parameter = {})
|
69
|
+
nil
|
70
|
+
end
|
71
|
+
|
72
|
+
def update_proxy(proxy = {})
|
73
|
+
@http.update_proxy(proxy)
|
74
|
+
end
|
75
|
+
|
76
|
+
def auto_proxy=(value)
|
77
|
+
Rails.logger.debug "自动更新代理"
|
78
|
+
@http.auto_proxy = value
|
79
|
+
@http.update_proxy if (value == true && @http.proxy? == false)
|
80
|
+
end
|
81
|
+
|
82
|
+
# 是否验证码界面
|
83
|
+
def validation_page?(*arg)
|
84
|
+
false
|
85
|
+
end
|
86
|
+
|
87
|
+
end
|
88
|
+
end
|
@@ -0,0 +1,211 @@
|
|
1
|
+
load File.dirname(__FILE__) + '/net/http.rb'
|
2
|
+
load File.dirname(__FILE__) + '/net/response.rb'
|
3
|
+
|
4
|
+
module HttpCrawler
|
5
|
+
class HTTP < Net::HTTP
|
6
|
+
|
7
|
+
# 自动获取代理,true 表示自动获取代理 、false 表示不自动获取
|
8
|
+
attr_accessor :auto_proxy
|
9
|
+
# 代理API的别名 主要关联 Crawler::Proxy中维护的代理API
|
10
|
+
attr_accessor :proxy_api
|
11
|
+
# 调用自己的代理池所需要的主键 key
|
12
|
+
attr_accessor :proxy_key
|
13
|
+
# 请求错误后的重复最大请求次数
|
14
|
+
attr_accessor :max_error_num
|
15
|
+
|
16
|
+
def initialize(address, port = nil)
|
17
|
+
super(address, port)
|
18
|
+
@max_error_num = 2
|
19
|
+
@error_num = 0
|
20
|
+
@proxy_key = "default"
|
21
|
+
end
|
22
|
+
|
23
|
+
def http_error_sleep
|
24
|
+
sleep(0.5)
|
25
|
+
end
|
26
|
+
|
27
|
+
def server_error_sleep
|
28
|
+
sleep(3)
|
29
|
+
end
|
30
|
+
|
31
|
+
def proxy_api
|
32
|
+
@proxy_api ||= "my"
|
33
|
+
end
|
34
|
+
@@proxy_list = []
|
35
|
+
# 为 @http 重设代理
|
36
|
+
def proxy(p = {})
|
37
|
+
|
38
|
+
raise '代理设置 p_addr 不能为空' unless p["p_addr"]
|
39
|
+
raise '代理设置 p_port 不能为空' unless p["p_port"]
|
40
|
+
|
41
|
+
p["p_user"] ||= nil
|
42
|
+
p["p_pass"] ||= nil
|
43
|
+
|
44
|
+
Rails.logger.info("切换代理至 => #{p}")
|
45
|
+
# 设为 false 否则不会启用代理
|
46
|
+
@proxy_from_env = false
|
47
|
+
|
48
|
+
# 初始化代理数据
|
49
|
+
@proxy_address = p["p_addr"]
|
50
|
+
@proxy_port = p["p_port"]
|
51
|
+
@proxy_user = p["p_user"]
|
52
|
+
@proxy_pass = p["p_pass"]
|
53
|
+
|
54
|
+
end
|
55
|
+
|
56
|
+
# 通过调用 api 获取代理或者通过自定义设置代理
|
57
|
+
def get_proxy
|
58
|
+
|
59
|
+
while @@proxy_list.blank?
|
60
|
+
Rails.logger.debug("@@proxy_list 为空进行更新")
|
61
|
+
proxy_client = Crawler::Proxy.for(proxy_api)
|
62
|
+
proxy_r = proxy_client.get_proxy(key: proxy_key)
|
63
|
+
@@proxy_list << proxy_r.parsing
|
64
|
+
Rails.logger.debug("@@proxy_list => #{@@proxy_list}")
|
65
|
+
sleep(1)
|
66
|
+
end
|
67
|
+
|
68
|
+
p = @@proxy_list.delete_at(0)
|
69
|
+
|
70
|
+
Rails.logger.debug("当前IP => #{@proxy_address}:#{@proxy_port},获取最新代理 => #{p}")
|
71
|
+
|
72
|
+
unless p && p["p_addr"] && p["p_port"]
|
73
|
+
Rails.logger.warn "无最新代理等待5秒后重新获取"
|
74
|
+
sleep(5)
|
75
|
+
p = get_proxy
|
76
|
+
end
|
77
|
+
|
78
|
+
if (@proxy_address == p["p_addr"] && @proxy_port == p["p_port"])
|
79
|
+
Rails.logger.warn "无最新代理等待5秒后重新获取"
|
80
|
+
sleep(5)
|
81
|
+
p = get_proxy
|
82
|
+
end
|
83
|
+
p
|
84
|
+
end
|
85
|
+
|
86
|
+
def update_proxy(p = {})
|
87
|
+
if p.blank?
|
88
|
+
proxy(get_proxy)
|
89
|
+
else
|
90
|
+
proxy(p)
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
# 如果自动更新代理 则更新代理返回 true,否则返回false
|
95
|
+
def update_proxy?(p = {})
|
96
|
+
if auto_proxy
|
97
|
+
if p.blank?
|
98
|
+
proxy(get_proxy)
|
99
|
+
else
|
100
|
+
proxy(p)
|
101
|
+
end
|
102
|
+
return true
|
103
|
+
else
|
104
|
+
return false
|
105
|
+
end
|
106
|
+
end
|
107
|
+
|
108
|
+
|
109
|
+
# 重定向请求
|
110
|
+
def get_fetch(uri_or_path, initheader = nil, dest = nil, limit = 10, &block)
|
111
|
+
# You should choose a better exception.
|
112
|
+
raise ArgumentError, 'too many HTTP repeated' if limit == 0
|
113
|
+
# 更新uri_or_path
|
114
|
+
uri_or_path = URI.encode(uri_or_path) if String === uri_or_path && CharDet.detect(uri_or_path)["encoding"] != "ascii"
|
115
|
+
|
116
|
+
response = get(uri_or_path, initheader, dest, &block)
|
117
|
+
case response
|
118
|
+
when Net::HTTPSuccess then
|
119
|
+
response
|
120
|
+
when Net::HTTPRedirection then
|
121
|
+
location = response['location']
|
122
|
+
Rails.logger.warn "redirected to #{location}"
|
123
|
+
# 传入 location 进行跳转
|
124
|
+
get_fetch(location, initheader, dest, limit - 1, &block)
|
125
|
+
when Net::HTTPServerError then
|
126
|
+
Rails.logger.warn "Net::HTTPServerError 5XX to #{address}"
|
127
|
+
server_error_sleep
|
128
|
+
# 重新请求
|
129
|
+
get_fetch(uri_or_path, initheader, dest, &block)
|
130
|
+
else
|
131
|
+
server_error_sleep
|
132
|
+
response.error!
|
133
|
+
end
|
134
|
+
end
|
135
|
+
|
136
|
+
# 重定向请求
|
137
|
+
def post_fetch(uri_or_path, data, initheader = nil, dest = nil, &block)
|
138
|
+
# 更新uri_or_path 如果 uri_or_path 是 String类型 同时 又不是 ascii编码格式就进行转码
|
139
|
+
uri_or_path = URI.encode(uri_or_path) if String === uri_or_path && CharDet.detect(uri_or_path)["encoding"] != "ascii"
|
140
|
+
Rails.logger.debug "post_fetch => #{uri_or_path}"
|
141
|
+
response = post(uri_or_path, data, initheader, dest, &block)
|
142
|
+
case response
|
143
|
+
when Net::HTTPSuccess then
|
144
|
+
response
|
145
|
+
when Net::HTTPRedirection then
|
146
|
+
location = response['location']
|
147
|
+
Rails.logger.warn "redirected to #{location}"
|
148
|
+
# 传入 location 进行跳转
|
149
|
+
get_fetch(location, initheader, dest, 9, &block)
|
150
|
+
when Net::HTTPServerError then
|
151
|
+
Rails.logger.warn "Net::HTTPServerError 5XX to #{address}"
|
152
|
+
server_error_sleep
|
153
|
+
# 重新请求
|
154
|
+
post_fetch(uri_or_path, initheader, dest, &block)
|
155
|
+
else
|
156
|
+
server_error_sleep
|
157
|
+
response.error!
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
# def post_fetch
|
162
|
+
|
163
|
+
#
|
164
|
+
# 重写 发送请求的方法
|
165
|
+
#
|
166
|
+
def request(req, body = nil, &block)
|
167
|
+
begin
|
168
|
+
Rails.logger.debug("#{req.class} => #{use_ssl? ? "https://" : "http://" }#{address}:#{port}#{req.path}") if started?
|
169
|
+
super(req, body, &block)
|
170
|
+
rescue => error
|
171
|
+
if started?
|
172
|
+
# started? 是为了判断是否结束http请求,如果不添加则会处理2次异常
|
173
|
+
raise error
|
174
|
+
else
|
175
|
+
# 最大错误尝试次数
|
176
|
+
if @error_num < @max_error_num
|
177
|
+
@error_num += 1
|
178
|
+
http_error_sleep
|
179
|
+
retry # 这将把控制移到 begin 的开头
|
180
|
+
else
|
181
|
+
# 超过最大错误限制 判断错误类型
|
182
|
+
case error
|
183
|
+
when Net::HTTPFatalError
|
184
|
+
raise error
|
185
|
+
when EOFError
|
186
|
+
Rails.logger.warn "EOFError!"
|
187
|
+
if update_proxy?
|
188
|
+
proxy(get_proxy)
|
189
|
+
http_error_sleep
|
190
|
+
retry # 这将把控制移到 begin 的开头
|
191
|
+
else
|
192
|
+
raise error
|
193
|
+
end
|
194
|
+
when Timeout::Error
|
195
|
+
Rails.logger.warn "请求超时!"
|
196
|
+
if update_proxy?
|
197
|
+
@error_num = 0
|
198
|
+
http_error_sleep
|
199
|
+
retry # 这将把控制移到 begin 的开头
|
200
|
+
else
|
201
|
+
raise error
|
202
|
+
end
|
203
|
+
else
|
204
|
+
raise error
|
205
|
+
end
|
206
|
+
end
|
207
|
+
end
|
208
|
+
end # begin
|
209
|
+
end # def request(req, body = nil, &block)
|
210
|
+
end
|
211
|
+
end
|
@@ -0,0 +1,96 @@
|
|
1
|
+
module Net
|
2
|
+
class HTTPResponse
|
3
|
+
|
4
|
+
# 解压并转码 body 数据
|
5
|
+
def decoding_body
|
6
|
+
|
7
|
+
return @decoding_body if @decoding_body
|
8
|
+
return nil unless body
|
9
|
+
|
10
|
+
# 数据解压
|
11
|
+
case header['Content-Encoding']
|
12
|
+
when 'gzip' then
|
13
|
+
sio = StringIO.new(body)
|
14
|
+
gz = Zlib::GzipReader.new(sio)
|
15
|
+
@decoding_body = gz.read()
|
16
|
+
when 'br'
|
17
|
+
@decoding_body = Brotli.inflate(body)
|
18
|
+
when 'deflate'
|
19
|
+
# 可能错误代码 暂时没解决 deflate 编码格式
|
20
|
+
@decoding_body = Zlib::Inflate.inflate(body)
|
21
|
+
else
|
22
|
+
@decoding_body = body
|
23
|
+
end
|
24
|
+
|
25
|
+
# 判断解压后数据编码格式
|
26
|
+
|
27
|
+
# 从header取编码格式
|
28
|
+
encoding = header['Content-Type'][/charset=([^, ;"]*)/, 1]
|
29
|
+
|
30
|
+
# 从html中的 charset 取编码格式
|
31
|
+
encoding = @decoding_body[/charset=([^, ;"]*)/, 1] unless encoding
|
32
|
+
|
33
|
+
# 通过 CharDet 判断编码格式
|
34
|
+
encoding = CharDet.detect(@decoding_body)["encoding"] unless encoding
|
35
|
+
|
36
|
+
# 进行转码
|
37
|
+
begin
|
38
|
+
@decoding_body.force_encoding(encoding).encode!('utf-8') if encoding != @decoding_body.encoding
|
39
|
+
rescue => e
|
40
|
+
# 转码错误后再次使用 CharDet 判断编码格式后进行转码
|
41
|
+
cd = CharDet.detect(@decoding_body)["encoding"]
|
42
|
+
if (cd && cd != encoding)
|
43
|
+
@decoding_body.force_encoding(cd).encode!('utf-8') if encoding != @decoding_body.encoding
|
44
|
+
else
|
45
|
+
# 还是转码错误则抛出异常
|
46
|
+
raise e
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
@decoding_body
|
51
|
+
end
|
52
|
+
|
53
|
+
# def decoding_body
|
54
|
+
|
55
|
+
def html
|
56
|
+
@html ||= Nokogiri::HTML(decoding_body)
|
57
|
+
end
|
58
|
+
|
59
|
+
def json
|
60
|
+
@json ||= JSON.parse(decoding_body)
|
61
|
+
@json = JSON.parse(@json) if String === @json
|
62
|
+
@json
|
63
|
+
end
|
64
|
+
|
65
|
+
# 通过readability 解析数据
|
66
|
+
def readability
|
67
|
+
@readability ||= Readability::Document.new(decoding_body, {do_not_guess_encoding: true})
|
68
|
+
end
|
69
|
+
|
70
|
+
# 解析
|
71
|
+
def parsing
|
72
|
+
nil
|
73
|
+
end
|
74
|
+
|
75
|
+
def get_date(str)
|
76
|
+
time = Time.now
|
77
|
+
case str
|
78
|
+
when /^(\d{1,2})小时前$/
|
79
|
+
time = time - $1.to_i.hours
|
80
|
+
when /^(\d{1,2})月(\d{1,2})日$/
|
81
|
+
time = Time.local(time.year, $1.to_i, $2.to_i)
|
82
|
+
when /^(\d{4})年(\d{1,2})月(\d{1,2})日$/
|
83
|
+
time = Time.local($1.to_i, $2.to_i, $3.to_i)
|
84
|
+
when /^(\d{1,2})月(\d{1,2})日[ ]{0,3}(\d{1,2}):(\d{1,2})$/ # 09月30日 12:04
|
85
|
+
time = Time.local(time.year, $1.to_i, $2.to_i, $3.to_i, $4.to_i)
|
86
|
+
end
|
87
|
+
return time
|
88
|
+
end
|
89
|
+
|
90
|
+
|
91
|
+
# 是否是网站验证 true表示正常数据、false表示弹出网站验证
|
92
|
+
def web_verify(*arg)
|
93
|
+
true
|
94
|
+
end
|
95
|
+
end # class Net::HTTPResponse
|
96
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
# 示例:测试API
|
2
|
+
|
3
|
+
|
4
|
+
### 通过对象调用
|
5
|
+
|
6
|
+
```ruby
|
7
|
+
client = HttpCrawler::Proxy::TestProxyApi::Client.new
|
8
|
+
client.get_proxy # 获取代理
|
9
|
+
```
|
10
|
+
|
11
|
+
### 通过别名调用
|
12
|
+
```ruby
|
13
|
+
client = HttpCrawler::Proxy.for("test_proxy_api") #
|
14
|
+
client.get_proxy # 获取代理
|
15
|
+
```
|
16
|
+
|
17
|
+
### response.rb
|
18
|
+
用于维护不同响应结果的处理方法
|
@@ -0,0 +1,29 @@
|
|
1
|
+
module HttpCrawler
|
2
|
+
module Proxy
|
3
|
+
module TestProxyApi
|
4
|
+
class Client
|
5
|
+
|
6
|
+
include(Crawler::Client)
|
7
|
+
include(Crawler::Proxy::Client)
|
8
|
+
|
9
|
+
class << self
|
10
|
+
def new(*args)
|
11
|
+
@client ||= super(*args)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
def init_uri
|
16
|
+
@uri = URI("http://127.0.0.1:1111/")
|
17
|
+
end
|
18
|
+
|
19
|
+
# http://39.108.59.38:7772/Tools/proxyIP.ashx?OrderNumber=ccd4c8912691f28861a1ed048fec88dc&poolIndex=22717&cache=1&qty=2
|
20
|
+
def get_proxy(parameter = {})
|
21
|
+
r = http.get_fetch("/api/get_proxy")
|
22
|
+
r.extend(Crawler::Proxy::Laofu::Response::GetProxy)
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
end # module BiQuGe_DuQuanBen
|
27
|
+
end # module Web
|
28
|
+
end # module Crawler
|
29
|
+
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# 查询
|
2
|
+
module HttpCrawler
|
3
|
+
module Proxy
|
4
|
+
module Laofu
|
5
|
+
module Response
|
6
|
+
module TestProxyApi
|
7
|
+
def parsing
|
8
|
+
array = []
|
9
|
+
decoding_body.scan(/([^\n\r:]*):([^\n\r]*)/) do |v1, v2|
|
10
|
+
if v1 =~ /\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}/
|
11
|
+
array[array.length] = {"p_addr" => v1, "p_port" => v2, "p_user" => nil, "p_pass" => nil}
|
12
|
+
else
|
13
|
+
Rails.logger.warn decoding_body
|
14
|
+
end
|
15
|
+
end
|
16
|
+
array
|
17
|
+
end
|
18
|
+
end # module GetProxy
|
19
|
+
end # module Response
|
20
|
+
end # module Laofu
|
21
|
+
end # module Proxy
|
22
|
+
end # module Crawler
|
23
|
+
|
24
|
+
|
@@ -0,0 +1,18 @@
|
|
1
|
+
module HttpCrawler
|
2
|
+
module Proxy
|
3
|
+
|
4
|
+
class << self
|
5
|
+
|
6
|
+
# 接收格式
|
7
|
+
# web_name = "feilong"
|
8
|
+
# 返回 Crawler::Proxy::Feilong::Client 实例
|
9
|
+
#
|
10
|
+
def for(web_name, *arg)
|
11
|
+
"Crawler::Proxy::#{web_name.camelize}::Client".constantize.new(*arg)
|
12
|
+
end
|
13
|
+
|
14
|
+
end
|
15
|
+
|
16
|
+
|
17
|
+
end
|
18
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
# 示例:百度爬虫维护
|
2
|
+
|
3
|
+
|
4
|
+
### 通过对象调用
|
5
|
+
|
6
|
+
```ruby
|
7
|
+
client = HttpCrawler::Client::Baidu::Client.new
|
8
|
+
client.index # 抓取首页
|
9
|
+
```
|
10
|
+
|
11
|
+
### 通过别名调用
|
12
|
+
```ruby
|
13
|
+
client = HttpCrawler::Client.for("baidu") #
|
14
|
+
client.index # 抓取首页
|
15
|
+
```
|
16
|
+
|
17
|
+
|
18
|
+
### response.rb
|
19
|
+
用于维护不同响应结果的处理方法
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module HttpCrawler
|
2
|
+
module Web
|
3
|
+
module Baidu
|
4
|
+
class Client
|
5
|
+
include(Crawler::Client)
|
6
|
+
|
7
|
+
def init_http
|
8
|
+
@http.open_timeout = 3
|
9
|
+
@http.read_timeout = 3
|
10
|
+
end
|
11
|
+
|
12
|
+
def init_uri
|
13
|
+
@uri = URI("https://www.baidu.com/")
|
14
|
+
end
|
15
|
+
|
16
|
+
def index(parameter = {})
|
17
|
+
r = http.get_fetch("/", header)
|
18
|
+
r.extend(HttpCrawler::Web::Baidu::Response::Index)
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
end # module Baidu
|
23
|
+
end # module Web
|
24
|
+
end # module Crawler
|
25
|
+
|
@@ -0,0 +1,16 @@
|
|
1
|
+
# 查询
|
2
|
+
module HttpCrawler
|
3
|
+
module Web
|
4
|
+
module Baidu
|
5
|
+
module Response
|
6
|
+
module Index
|
7
|
+
def parsing(parameter = {})
|
8
|
+
html
|
9
|
+
end
|
10
|
+
end # module Search
|
11
|
+
end # module Response
|
12
|
+
end # module Qichacha
|
13
|
+
end # module Web
|
14
|
+
end # module Crawler
|
15
|
+
|
16
|
+
|
data/lib/http_crawler.rb
ADDED
metadata
ADDED
@@ -0,0 +1,175 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: http_crawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.2.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- jagger
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-12-28 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rspec
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '3.8'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '3.8'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.15'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.15'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rchardet
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.8'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.8'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: nokogiri
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '1.8'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '1.8'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: ruby-readability
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 0.7.0
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 0.7.0
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: brotli
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 0.2.1
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 0.2.1
|
111
|
+
description: 初级开发工程师,基于net/http 写的爬虫扩展包。
|
112
|
+
email:
|
113
|
+
- 1336098842@qq.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- ".gitignore"
|
119
|
+
- ".idea/vcs.xml"
|
120
|
+
- ".rspec"
|
121
|
+
- CODE_OF_CONDUCT.md
|
122
|
+
- Gemfile
|
123
|
+
- README.md
|
124
|
+
- Rakefile
|
125
|
+
- bin/console
|
126
|
+
- bin/setup
|
127
|
+
- http_crawler.gemspec
|
128
|
+
- lib/http_crawler.rb
|
129
|
+
- lib/http_crawler/client.rb
|
130
|
+
- lib/http_crawler/http.rb
|
131
|
+
- lib/http_crawler/net/http.rb
|
132
|
+
- lib/http_crawler/net/response.rb
|
133
|
+
- lib/http_crawler/object.rb
|
134
|
+
- lib/http_crawler/proxy.rb
|
135
|
+
- lib/http_crawler/proxy/README.md
|
136
|
+
- lib/http_crawler/proxy/client.rb
|
137
|
+
- lib/http_crawler/proxy/response.rb
|
138
|
+
- lib/http_crawler/proxy/test_proxy_api/README.md
|
139
|
+
- lib/http_crawler/proxy/test_proxy_api/client.rb
|
140
|
+
- lib/http_crawler/proxy/test_proxy_api/response.rb
|
141
|
+
- lib/http_crawler/proxy/test_proxy_api/response/get_proxy.rb
|
142
|
+
- lib/http_crawler/string.rb
|
143
|
+
- lib/http_crawler/version.rb
|
144
|
+
- lib/http_crawler/web.rb
|
145
|
+
- lib/http_crawler/web/README.md
|
146
|
+
- lib/http_crawler/web/baidu/README.md
|
147
|
+
- lib/http_crawler/web/baidu/client.rb
|
148
|
+
- lib/http_crawler/web/baidu/response.rb
|
149
|
+
- lib/http_crawler/web/baidu/response/index.rb
|
150
|
+
homepage: https://rubygems.org/gems/http_crawler
|
151
|
+
licenses:
|
152
|
+
- MIT
|
153
|
+
metadata:
|
154
|
+
allowed_push_host: https://rubygems.org
|
155
|
+
post_install_message:
|
156
|
+
rdoc_options: []
|
157
|
+
require_paths:
|
158
|
+
- lib
|
159
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
160
|
+
requirements:
|
161
|
+
- - ">="
|
162
|
+
- !ruby/object:Gem::Version
|
163
|
+
version: '0'
|
164
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
165
|
+
requirements:
|
166
|
+
- - ">="
|
167
|
+
- !ruby/object:Gem::Version
|
168
|
+
version: '0'
|
169
|
+
requirements: []
|
170
|
+
rubyforge_project:
|
171
|
+
rubygems_version: 2.6.14
|
172
|
+
signing_key:
|
173
|
+
specification_version: 4
|
174
|
+
summary: http 爬虫。
|
175
|
+
test_files: []
|