http_crawler 0.2.3.2 → 0.2.3.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.idea/http_crawler.iml +1 -2
- data/.idea/workspace.xml +31 -26
- data/lib/http_crawler/http.rb +5 -3
- data/lib/http_crawler/net/response.rb +6 -1
- data/lib/http_crawler/version.rb +1 -1
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 1143552ea7737865d9fe582c48b7fa3f5824da47cbb0e16d8911050bd807dc68
|
4
|
+
data.tar.gz: 0e55bdd075e617e1f60e9fb6a54f75366c7cc670801d6a49b48c007e612b00a3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e26f0d48ec8318b0d977933d95f091a8e9ce00ef872ef8668d66dcbacc653e984871210b132468b530fd7d30261bb2caae592b93f7d0fa73067432c7b4b38750
|
7
|
+
data.tar.gz: 98004bfd606c248e367d18bac5cea84304a5f83854d9c9ac4adedbbf5ee84a6533f6d909ffa73afaf66f0313605093f84da2bde25c78c3e6ed60b86e7e8c71f7
|
data/.idea/http_crawler.iml
CHANGED
@@ -7,7 +7,6 @@
|
|
7
7
|
<content url="file://$MODULE_DIR$" />
|
8
8
|
<orderEntry type="inheritedJdk" />
|
9
9
|
<orderEntry type="sourceFolder" forTests="false" />
|
10
|
-
<orderEntry type="library" scope="PROVIDED" name="bundler (v1.
|
11
|
-
<orderEntry type="library" scope="PROVIDED" name="nokogiri (v1.8.0, RVM: ruby-2.4.1) [gem]" level="application" />
|
10
|
+
<orderEntry type="library" scope="PROVIDED" name="bundler (v1.16.6, RVM: ruby-2.4.1) [gem]" level="application" />
|
12
11
|
</component>
|
13
12
|
</module>
|
data/.idea/workspace.xml
CHANGED
@@ -2,7 +2,11 @@
|
|
2
2
|
<project version="4">
|
3
3
|
<component name="ChangeListManager">
|
4
4
|
<list default="true" id="07223dd4-8944-486b-a29b-7461a5c9ec2d" name="Default" comment="">
|
5
|
+
<change beforePath="$PROJECT_DIR$/.idea/http_crawler.iml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/http_crawler.iml" afterDir="false" />
|
5
6
|
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
7
|
+
<change beforePath="$PROJECT_DIR$/lib/http_crawler/http.rb" beforeDir="false" afterPath="$PROJECT_DIR$/lib/http_crawler/http.rb" afterDir="false" />
|
8
|
+
<change beforePath="$PROJECT_DIR$/lib/http_crawler/net/response.rb" beforeDir="false" afterPath="$PROJECT_DIR$/lib/http_crawler/net/response.rb" afterDir="false" />
|
9
|
+
<change beforePath="$PROJECT_DIR$/lib/http_crawler/version.rb" beforeDir="false" afterPath="$PROJECT_DIR$/lib/http_crawler/version.rb" afterDir="false" />
|
6
10
|
</list>
|
7
11
|
<option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
|
8
12
|
<option name="TRACKING_ENABLED" value="true" />
|
@@ -16,8 +20,8 @@
|
|
16
20
|
<file leaf-file-name="version.rb" pinned="false" current-in-tab="true">
|
17
21
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/version.rb">
|
18
22
|
<provider selected="true" editor-type-id="text-editor">
|
19
|
-
<state relative-caret-position="
|
20
|
-
<caret line="
|
23
|
+
<state relative-caret-position="21">
|
24
|
+
<caret line="1" column="21" selection-start-line="1" selection-start-column="21" selection-end-line="1" selection-end-column="21" />
|
21
25
|
</state>
|
22
26
|
</provider>
|
23
27
|
</entry>
|
@@ -25,7 +29,7 @@
|
|
25
29
|
<file leaf-file-name="web.rb" pinned="false" current-in-tab="false">
|
26
30
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web.rb">
|
27
31
|
<provider selected="true" editor-type-id="text-editor">
|
28
|
-
<state relative-caret-position="
|
32
|
+
<state relative-caret-position="126">
|
29
33
|
<caret line="6" selection-start-line="6" selection-end-line="6" />
|
30
34
|
</state>
|
31
35
|
</provider>
|
@@ -34,8 +38,8 @@
|
|
34
38
|
<file leaf-file-name="http.rb" pinned="false" current-in-tab="false">
|
35
39
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http.rb">
|
36
40
|
<provider selected="true" editor-type-id="text-editor">
|
37
|
-
<state relative-caret-position="
|
38
|
-
<caret line="210" column="
|
41
|
+
<state relative-caret-position="4410">
|
42
|
+
<caret line="210" column="11" lean-forward="true" selection-start-line="210" selection-start-column="11" selection-end-line="210" selection-end-column="11" />
|
39
43
|
</state>
|
40
44
|
</provider>
|
41
45
|
</entry>
|
@@ -43,7 +47,7 @@
|
|
43
47
|
<file leaf-file-name="compat.rb" pinned="false" current-in-tab="false">
|
44
48
|
<entry file="file://$USER_HOME$/.rvm/rubies/ruby-2.4.1/lib/ruby/2.4.0/webrick/compat.rb">
|
45
49
|
<provider selected="true" editor-type-id="text-editor">
|
46
|
-
<state relative-caret-position="
|
50
|
+
<state relative-caret-position="378">
|
47
51
|
<caret line="18" column="1" selection-start-line="18" selection-start-column="1" selection-end-line="18" selection-end-column="1" />
|
48
52
|
</state>
|
49
53
|
</provider>
|
@@ -52,7 +56,7 @@
|
|
52
56
|
<file leaf-file-name="errno.rb" pinned="false" current-in-tab="false">
|
53
57
|
<entry file="file://$APPLICATION_HOME_DIR$/rubystubs24/errno.rb">
|
54
58
|
<provider selected="true" editor-type-id="text-editor">
|
55
|
-
<state relative-caret-position="
|
59
|
+
<state relative-caret-position="672">
|
56
60
|
<caret line="32" column="7" selection-start-line="32" selection-start-column="7" selection-end-line="32" selection-end-column="7" />
|
57
61
|
</state>
|
58
62
|
</provider>
|
@@ -61,7 +65,7 @@
|
|
61
65
|
<file leaf-file-name="common.rb" pinned="false" current-in-tab="false">
|
62
66
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common.rb">
|
63
67
|
<provider selected="true" editor-type-id="text-editor">
|
64
|
-
<state relative-caret-position="
|
68
|
+
<state relative-caret-position="42">
|
65
69
|
<caret line="2" selection-start-line="2" selection-end-line="2" />
|
66
70
|
</state>
|
67
71
|
</provider>
|
@@ -70,7 +74,7 @@
|
|
70
74
|
<file leaf-file-name="proxy.rb" pinned="false" current-in-tab="false">
|
71
75
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/proxy.rb">
|
72
76
|
<provider selected="true" editor-type-id="text-editor">
|
73
|
-
<state relative-caret-position="
|
77
|
+
<state relative-caret-position="441">
|
74
78
|
<caret line="21" selection-start-line="21" selection-end-line="21" />
|
75
79
|
</state>
|
76
80
|
</provider>
|
@@ -79,7 +83,7 @@
|
|
79
83
|
<file leaf-file-name="client.rb" pinned="false" current-in-tab="false">
|
80
84
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/baidu/client.rb">
|
81
85
|
<provider selected="true" editor-type-id="text-editor">
|
82
|
-
<state relative-caret-position="
|
86
|
+
<state relative-caret-position="21">
|
83
87
|
<caret line="1" column="18" selection-start-line="1" selection-start-column="7" selection-end-line="1" selection-end-column="18" />
|
84
88
|
</state>
|
85
89
|
</provider>
|
@@ -88,7 +92,7 @@
|
|
88
92
|
<file leaf-file-name="Gemfile" pinned="false" current-in-tab="false">
|
89
93
|
<entry file="file://$PROJECT_DIR$/Gemfile">
|
90
94
|
<provider selected="true" editor-type-id="text-editor">
|
91
|
-
<state relative-caret-position="
|
95
|
+
<state relative-caret-position="168">
|
92
96
|
<caret line="8" column="23" selection-start-line="8" selection-start-column="23" selection-end-line="8" selection-end-column="23" />
|
93
97
|
</state>
|
94
98
|
</provider>
|
@@ -247,17 +251,18 @@
|
|
247
251
|
<workItem from="1546240992243" duration="719000" />
|
248
252
|
<workItem from="1546291493927" duration="464000" />
|
249
253
|
<workItem from="1546436457874" duration="2443000" />
|
254
|
+
<workItem from="1549964225949" duration="5000" />
|
250
255
|
</task>
|
251
256
|
<servers />
|
252
257
|
</component>
|
253
258
|
<component name="TimeTrackingManager">
|
254
|
-
<option name="totallyTimeSpent" value="
|
259
|
+
<option name="totallyTimeSpent" value="23113000" />
|
255
260
|
</component>
|
256
261
|
<component name="ToolWindowManager">
|
257
|
-
<frame x="0" y="0" width="
|
262
|
+
<frame x="0" y="0" width="1680" height="1050" extended-state="0" />
|
258
263
|
<editor active="true" />
|
259
264
|
<layout>
|
260
|
-
<window_info
|
265
|
+
<window_info content_ui="combo" id="Project" order="0" visible="true" weight="0.34188035" />
|
261
266
|
<window_info anchor="bottom" id="TODO" order="6" />
|
262
267
|
<window_info anchor="bottom" id="Docker" order="7" show_stripe_button="false" />
|
263
268
|
<window_info anchor="bottom" id="Event Log" order="7" side_tool="true" />
|
@@ -265,7 +270,7 @@
|
|
265
270
|
<window_info anchor="bottom" id="Database Changes" order="7" show_stripe_button="false" />
|
266
271
|
<window_info anchor="bottom" id="Version Control" order="7" />
|
267
272
|
<window_info id="Structure" order="1" side_tool="true" weight="0.25" />
|
268
|
-
<window_info anchor="bottom" id="Terminal" order="7" visible="true" weight="0.
|
273
|
+
<window_info active="true" anchor="bottom" id="Terminal" order="7" visible="true" weight="0.45725647" />
|
269
274
|
<window_info id="Favorites" order="2" side_tool="true" />
|
270
275
|
<window_info anchor="right" content_ui="combo" id="Hierarchy" order="2" weight="0.25" />
|
271
276
|
<window_info anchor="bottom" id="Inspection" order="5" weight="0.4" />
|
@@ -554,50 +559,50 @@
|
|
554
559
|
</entry>
|
555
560
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common.rb">
|
556
561
|
<provider selected="true" editor-type-id="text-editor">
|
557
|
-
<state relative-caret-position="
|
562
|
+
<state relative-caret-position="42">
|
558
563
|
<caret line="2" selection-start-line="2" selection-end-line="2" />
|
559
564
|
</state>
|
560
565
|
</provider>
|
561
566
|
</entry>
|
562
567
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/proxy.rb">
|
563
568
|
<provider selected="true" editor-type-id="text-editor">
|
564
|
-
<state relative-caret-position="
|
569
|
+
<state relative-caret-position="441">
|
565
570
|
<caret line="21" selection-start-line="21" selection-end-line="21" />
|
566
571
|
</state>
|
567
572
|
</provider>
|
568
573
|
</entry>
|
569
574
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web.rb">
|
570
575
|
<provider selected="true" editor-type-id="text-editor">
|
571
|
-
<state relative-caret-position="
|
576
|
+
<state relative-caret-position="126">
|
572
577
|
<caret line="6" selection-start-line="6" selection-end-line="6" />
|
573
578
|
</state>
|
574
579
|
</provider>
|
575
580
|
</entry>
|
576
581
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/baidu/client.rb">
|
577
582
|
<provider selected="true" editor-type-id="text-editor">
|
578
|
-
<state relative-caret-position="
|
583
|
+
<state relative-caret-position="21">
|
579
584
|
<caret line="1" column="18" selection-start-line="1" selection-start-column="7" selection-end-line="1" selection-end-column="18" />
|
580
585
|
</state>
|
581
586
|
</provider>
|
582
587
|
</entry>
|
583
588
|
<entry file="file://$PROJECT_DIR$/Gemfile">
|
584
589
|
<provider selected="true" editor-type-id="text-editor">
|
585
|
-
<state relative-caret-position="
|
590
|
+
<state relative-caret-position="168">
|
586
591
|
<caret line="8" column="23" selection-start-line="8" selection-start-column="23" selection-end-line="8" selection-end-column="23" />
|
587
592
|
</state>
|
588
593
|
</provider>
|
589
594
|
</entry>
|
590
595
|
<entry file="file://$APPLICATION_HOME_DIR$/rubystubs24/errno.rb">
|
591
596
|
<provider selected="true" editor-type-id="text-editor">
|
592
|
-
<state relative-caret-position="
|
597
|
+
<state relative-caret-position="672">
|
593
598
|
<caret line="32" column="7" selection-start-line="32" selection-start-column="7" selection-end-line="32" selection-end-column="7" />
|
594
599
|
</state>
|
595
600
|
</provider>
|
596
601
|
</entry>
|
597
602
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http.rb">
|
598
603
|
<provider selected="true" editor-type-id="text-editor">
|
599
|
-
<state relative-caret-position="
|
600
|
-
<caret line="210" column="
|
604
|
+
<state relative-caret-position="4410">
|
605
|
+
<caret line="210" column="11" lean-forward="true" selection-start-line="210" selection-start-column="11" selection-end-line="210" selection-end-column="11" />
|
601
606
|
</state>
|
602
607
|
</provider>
|
603
608
|
</entry>
|
@@ -610,15 +615,15 @@
|
|
610
615
|
</entry>
|
611
616
|
<entry file="file://$USER_HOME$/.rvm/rubies/ruby-2.4.1/lib/ruby/2.4.0/webrick/compat.rb">
|
612
617
|
<provider selected="true" editor-type-id="text-editor">
|
613
|
-
<state relative-caret-position="
|
618
|
+
<state relative-caret-position="378">
|
614
619
|
<caret line="18" column="1" selection-start-line="18" selection-start-column="1" selection-end-line="18" selection-end-column="1" />
|
615
620
|
</state>
|
616
621
|
</provider>
|
617
622
|
</entry>
|
618
623
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/version.rb">
|
619
624
|
<provider selected="true" editor-type-id="text-editor">
|
620
|
-
<state relative-caret-position="
|
621
|
-
<caret line="
|
625
|
+
<state relative-caret-position="21">
|
626
|
+
<caret line="1" column="21" selection-start-line="1" selection-start-column="21" selection-end-line="1" selection-end-column="21" />
|
622
627
|
</state>
|
623
628
|
</provider>
|
624
629
|
</entry>
|
data/lib/http_crawler/http.rb
CHANGED
@@ -5,6 +5,11 @@ module HttpCrawler
|
|
5
5
|
attr_accessor :auto_proxy
|
6
6
|
# 代理API的别名 主要关联 HttpCrawler::Proxy中维护的代理API
|
7
7
|
attr_accessor :proxy_api
|
8
|
+
|
9
|
+
def proxy_api
|
10
|
+
@proxy_api ||= "my"
|
11
|
+
end
|
12
|
+
|
8
13
|
# 调用自己的代理池所需要的主键 key
|
9
14
|
attr_accessor :proxy_key
|
10
15
|
# 请求错误后的重复最大请求次数
|
@@ -28,9 +33,6 @@ module HttpCrawler
|
|
28
33
|
sleep(3)
|
29
34
|
end
|
30
35
|
|
31
|
-
def proxy_api
|
32
|
-
@proxy_api ||= "my"
|
33
|
-
end
|
34
36
|
|
35
37
|
@@proxy_list = []
|
36
38
|
# 为 @http 重设代理
|
data/lib/http_crawler/version.rb
CHANGED
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: 0.2.3.
|
4
|
+
version: 0.2.3.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- jagger
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-
|
11
|
+
date: 2019-02-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rspec
|
@@ -175,7 +175,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
175
175
|
version: '0'
|
176
176
|
requirements: []
|
177
177
|
rubyforge_project:
|
178
|
-
rubygems_version: 2.
|
178
|
+
rubygems_version: 2.7.8
|
179
179
|
signing_key:
|
180
180
|
specification_version: 4
|
181
181
|
summary: http 爬虫。
|