http_crawler 0.3.2.3 → 0.3.2.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/http_crawler/client.rb +14 -0
- data/lib/http_crawler/version.rb +1 -1
- data/lib/http_crawler/web/client.rb +0 -1
- data/lib/http_crawler/web/{baidu → httpbin}/README.md +2 -2
- data/lib/http_crawler/web/httpbin/client.rb +25 -0
- data/lib/http_crawler/web/{baidu → httpbin}/response.rb +1 -1
- data/lib/http_crawler/web/httpbin/response/ip.rb +31 -0
- metadata +6 -6
- data/lib/http_crawler/web/baidu/client.rb +0 -35
- data/lib/http_crawler/web/baidu/response/index.rb +0 -16
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3ccf1f8dd94a975491c31e136eaaa74bd15fe2588d047a653847ee4f5899bdfb
|
4
|
+
data.tar.gz: d0669d6313fe3aa10c1eb8c9bafeb2707ca3a081de79b11171bb99e81657143d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 176cbcffb613e41738ff51246fbf13270d19190498ecd933567d4610edc561760657ebfa6c5620ef2982a32374d7ea0a113b1d97eb8a63d584fd5f995abc05e1
|
7
|
+
data.tar.gz: 3a74d6abb7ef3577a1962614d79991290a90fc60b6be7654b730dec2b13553ce087a1544cf9091b2006cd6a07633290de08f65f3930fc7f9a69b7dd66848f02d
|
data/lib/http_crawler/client.rb
CHANGED
@@ -204,6 +204,20 @@ module HttpCrawler
|
|
204
204
|
def init_cookies
|
205
205
|
@cookies = {}
|
206
206
|
end
|
207
|
+
|
208
|
+
# 创建时间: 2020/4/7 16:54
|
209
|
+
# 更新时间: 2020/4/7
|
210
|
+
# 作者: Jagger
|
211
|
+
# 方法名称: remove_traces
|
212
|
+
# 方法说明: 清除痕迹
|
213
|
+
# 调用方式: #remove_traces
|
214
|
+
#
|
215
|
+
# @return
|
216
|
+
#
|
217
|
+
def remove_traces
|
218
|
+
@response = nil
|
219
|
+
self.init_cookies
|
220
|
+
end
|
207
221
|
|
208
222
|
# 创建时间: 2019/9/16 17:13
|
209
223
|
# 更新时间: 2019/9/16
|
data/lib/http_crawler/version.rb
CHANGED
@@ -0,0 +1,25 @@
|
|
1
|
+
|
2
|
+
module HttpCrawler
|
3
|
+
module Web
|
4
|
+
module Httpbin
|
5
|
+
class Client < HttpCrawler::Web::Client
|
6
|
+
|
7
|
+
def init_client
|
8
|
+
# 设置整体超时时间 3 秒
|
9
|
+
@all_timeout = 3
|
10
|
+
end
|
11
|
+
|
12
|
+
def init_uri
|
13
|
+
@uri = URI("http://httpbin.org/")
|
14
|
+
end
|
15
|
+
|
16
|
+
def ip(parameter = {})
|
17
|
+
r = get("ip")
|
18
|
+
r.extend(HttpCrawler::Web::Httpbin::Response::Ip)
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
end # module Baidu
|
23
|
+
end # module Web
|
24
|
+
end # module HttpCrawler
|
25
|
+
|
@@ -0,0 +1,31 @@
|
|
1
|
+
# 查询
|
2
|
+
module HttpCrawler
|
3
|
+
module Web
|
4
|
+
module Httpbin
|
5
|
+
module Response
|
6
|
+
module Ip
|
7
|
+
|
8
|
+
# 创建时间: 2019/4/28 21:03
|
9
|
+
# 作者: Jagger
|
10
|
+
# 方法名称: parsing
|
11
|
+
# 方法说明: 解析数据
|
12
|
+
# 调用方式: #results
|
13
|
+
#
|
14
|
+
# @option parameter [Hash] Hash模式传参
|
15
|
+
# @param parameter [Hash]
|
16
|
+
# {
|
17
|
+
# "": , # 参数说明
|
18
|
+
# }
|
19
|
+
#
|
20
|
+
# @return JSON
|
21
|
+
#
|
22
|
+
def parsing(parameter = {})
|
23
|
+
self.json
|
24
|
+
end
|
25
|
+
end # module Index
|
26
|
+
end # module Response
|
27
|
+
end # module Baidu
|
28
|
+
end # module Web
|
29
|
+
end # module HttpCrawler
|
30
|
+
|
31
|
+
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: http_crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.2.
|
4
|
+
version: 0.3.2.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- jagger
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-04-07 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rspec
|
@@ -153,11 +153,11 @@ files:
|
|
153
153
|
- lib/http_crawler/version.rb
|
154
154
|
- lib/http_crawler/web.rb
|
155
155
|
- lib/http_crawler/web/README.md
|
156
|
-
- lib/http_crawler/web/baidu/README.md
|
157
|
-
- lib/http_crawler/web/baidu/client.rb
|
158
|
-
- lib/http_crawler/web/baidu/response.rb
|
159
|
-
- lib/http_crawler/web/baidu/response/index.rb
|
160
156
|
- lib/http_crawler/web/client.rb
|
157
|
+
- lib/http_crawler/web/httpbin/README.md
|
158
|
+
- lib/http_crawler/web/httpbin/client.rb
|
159
|
+
- lib/http_crawler/web/httpbin/response.rb
|
160
|
+
- lib/http_crawler/web/httpbin/response/ip.rb
|
161
161
|
homepage: https://rubygems.org/gems/http_crawler
|
162
162
|
licenses:
|
163
163
|
- MIT
|
@@ -1,35 +0,0 @@
|
|
1
|
-
|
2
|
-
module HttpCrawler
|
3
|
-
module Web
|
4
|
-
module Baidu
|
5
|
-
class Client < HttpCrawler::Web::Client
|
6
|
-
|
7
|
-
def init_client
|
8
|
-
# 设置整体超时时间 3 秒
|
9
|
-
@all_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 = get("/")
|
18
|
-
r.extend(HttpCrawler::Web::Baidu::Response::Index)
|
19
|
-
end
|
20
|
-
|
21
|
-
def search(parameter = {})
|
22
|
-
raise "parameter[:keyword] 不能为空" unless parameter[:keyword]
|
23
|
-
params = {
|
24
|
-
"wd": parameter[:keyword]
|
25
|
-
}
|
26
|
-
r = get("/s",params)
|
27
|
-
r
|
28
|
-
end
|
29
|
-
|
30
|
-
end
|
31
|
-
end # module Baidu
|
32
|
-
end # module Web
|
33
|
-
end # module HttpCrawler
|
34
|
-
|
35
|
-
load File.dirname(__FILE__) + '/response/index.rb'
|
@@ -1,16 +0,0 @@
|
|
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 Index
|
11
|
-
end # module Response
|
12
|
-
end # module Baidu
|
13
|
-
end # module Web
|
14
|
-
end # module HttpCrawler
|
15
|
-
|
16
|
-
|