http_crawler 0.3.1.18 → 0.3.1.19
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.idea/.rakeTasks +1 -1
- data/.idea/http_crawler.iml +2 -13
- data/.idea/workspace.xml +124 -121
- data/lib/http_crawler.rb +0 -1
- data/lib/http_crawler/common/integer.rb +1 -1
- data/lib/http_crawler/common/object.rb +1 -1
- data/lib/http_crawler/common/string.rb +18 -5
- data/lib/http_crawler/decryption.rb +0 -2
- data/lib/http_crawler/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: d0e50899bd853cd086eabd2be247b40fa74f6f2d0c5a50f7e5a04e6f4fba7f90
|
4
|
+
data.tar.gz: b77db25f63506a1182fafd7741d83b04fea6ec9d339e8147390332937fb6f7da
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d3251a089a02bd55a1dc1a4f6fc92ded5f631e59d7e81f9d6f756a36dca09c37694b7414c61595aec900c2e2255458ebf3e7104839eba782b903a62494694fa7
|
7
|
+
data.tar.gz: c8945774aa2e60f58685e78e4ba7a67aab0a8866636ee9ec4d442d5fe178530e2c3ff927d37078de8cee0056b168c5fe5b92d749056fa906f68f5dfe3eca2071
|
data/.idea/.rakeTasks
CHANGED
@@ -4,4 +4,4 @@ You are allowed to:
|
|
4
4
|
1. Remove rake task
|
5
5
|
2. Add existing rake tasks
|
6
6
|
To add existing rake tasks automatically delete this file and reload the project.
|
7
|
-
--><RakeGroup description="" fullCmd="" taksId="rake"
|
7
|
+
--><RakeGroup description="" fullCmd="" taksId="rake" /></Settings>
|
data/.idea/http_crawler.iml
CHANGED
@@ -5,19 +5,8 @@
|
|
5
5
|
</component>
|
6
6
|
<component name="NewModuleRootManager">
|
7
7
|
<content url="file://$MODULE_DIR$" />
|
8
|
-
<orderEntry type="
|
8
|
+
<orderEntry type="inheritedJdk" />
|
9
9
|
<orderEntry type="sourceFolder" forTests="false" />
|
10
|
-
<orderEntry type="library" scope="PROVIDED" name="
|
11
|
-
<orderEntry type="library" scope="PROVIDED" name="bundler (v1.16.6, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
12
|
-
<orderEntry type="library" scope="PROVIDED" name="diff-lcs (v1.3, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
13
|
-
<orderEntry type="library" scope="PROVIDED" name="guess_html_encoding (v0.0.11, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
14
|
-
<orderEntry type="library" scope="PROVIDED" name="mini_portile2 (v2.4.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
15
|
-
<orderEntry type="library" scope="PROVIDED" name="nokogiri (v1.10.1, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
16
|
-
<orderEntry type="library" scope="PROVIDED" name="rchardet (v1.8.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
17
|
-
<orderEntry type="library" scope="PROVIDED" name="rspec (v3.8.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
18
|
-
<orderEntry type="library" scope="PROVIDED" name="rspec-core (v3.8.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
19
|
-
<orderEntry type="library" scope="PROVIDED" name="rspec-mocks (v3.8.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
20
|
-
<orderEntry type="library" scope="PROVIDED" name="rspec-support (v3.8.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
21
|
-
<orderEntry type="library" scope="PROVIDED" name="ruby-readability (v0.7.0, RVM: ruby-2.4.1 [rails5.1.6]) [gem]" level="application" />
|
10
|
+
<orderEntry type="library" scope="PROVIDED" name="bundler (v1.16.6, RVM: ruby-2.4.1) [gem]" level="application" />
|
22
11
|
</component>
|
23
12
|
</module>
|
data/.idea/workspace.xml
CHANGED
@@ -2,11 +2,9 @@
|
|
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 afterPath="$PROJECT_DIR$/.idea
|
6
|
-
<change beforePath="$PROJECT_DIR$/.idea/http_crawler.iml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/http_crawler.iml" afterDir="false" />
|
5
|
+
<change beforePath="$PROJECT_DIR$/.idea/.rakeTasks" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/.rakeTasks" afterDir="false" />
|
7
6
|
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
8
|
-
<change beforePath="$PROJECT_DIR$/lib/http_crawler/
|
9
|
-
<change beforePath="$PROJECT_DIR$/lib/http_crawler/net/response.rb" beforeDir="false" afterPath="$PROJECT_DIR$/lib/http_crawler/net/response.rb" afterDir="false" />
|
7
|
+
<change beforePath="$PROJECT_DIR$/lib/http_crawler/decryption/node.rb" beforeDir="false" afterPath="$PROJECT_DIR$/lib/http_crawler/decryption/node.rb" afterDir="false" />
|
10
8
|
<change beforePath="$PROJECT_DIR$/lib/http_crawler/version.rb" beforeDir="false" afterPath="$PROJECT_DIR$/lib/http_crawler/version.rb" afterDir="false" />
|
11
9
|
</list>
|
12
10
|
<option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
|
@@ -18,47 +16,76 @@
|
|
18
16
|
</component>
|
19
17
|
<component name="FileEditorManager">
|
20
18
|
<leaf SIDE_TABS_SIZE_LIMIT_KEY="300">
|
21
|
-
<file leaf-file-name="
|
22
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
19
|
+
<file leaf-file-name="common.rb" pinned="false" current-in-tab="false">
|
20
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common.rb">
|
23
21
|
<provider selected="true" editor-type-id="text-editor">
|
24
|
-
<state relative-caret-position="
|
25
|
-
<caret line="
|
22
|
+
<state relative-caret-position="36">
|
23
|
+
<caret line="2" selection-start-line="2" selection-end-line="2" />
|
26
24
|
</state>
|
27
25
|
</provider>
|
28
26
|
</entry>
|
29
27
|
</file>
|
30
|
-
<file leaf-file-name="
|
31
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
28
|
+
<file leaf-file-name="version.rb" pinned="false" current-in-tab="false">
|
29
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/version.rb">
|
32
30
|
<provider selected="true" editor-type-id="text-editor">
|
33
|
-
<state relative-caret-position="
|
34
|
-
<caret line="
|
31
|
+
<state relative-caret-position="54">
|
32
|
+
<caret line="3" lean-forward="true" selection-start-line="3" selection-end-line="3" />
|
35
33
|
</state>
|
36
34
|
</provider>
|
37
35
|
</entry>
|
38
36
|
</file>
|
37
|
+
<file leaf-file-name="response.rb" pinned="false" current-in-tab="false">
|
38
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http/response.rb">
|
39
|
+
<provider selected="true" editor-type-id="text-editor" />
|
40
|
+
</entry>
|
41
|
+
</file>
|
39
42
|
<file leaf-file-name="client.rb" pinned="false" current-in-tab="false">
|
40
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/client.rb">
|
43
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/client.rb">
|
41
44
|
<provider selected="true" editor-type-id="text-editor">
|
42
|
-
<state relative-caret-position="
|
43
|
-
<caret line="
|
45
|
+
<state relative-caret-position="180">
|
46
|
+
<caret line="10" column="48" selection-start-line="10" selection-start-column="48" selection-end-line="10" selection-end-column="48" />
|
44
47
|
</state>
|
45
48
|
</provider>
|
46
49
|
</entry>
|
47
50
|
</file>
|
51
|
+
<file leaf-file-name="node.rb" pinned="false" current-in-tab="true">
|
52
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/decryption/node.rb">
|
53
|
+
<provider selected="true" editor-type-id="text-editor">
|
54
|
+
<state relative-caret-position="342">
|
55
|
+
<caret line="19" column="7" lean-forward="true" selection-start-line="19" selection-start-column="7" selection-end-line="19" selection-end-column="7" />
|
56
|
+
</state>
|
57
|
+
</provider>
|
58
|
+
</entry>
|
59
|
+
</file>
|
60
|
+
<file leaf-file-name="string.rb" pinned="false" current-in-tab="false">
|
61
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/string.rb">
|
62
|
+
<provider selected="true" editor-type-id="text-editor" />
|
63
|
+
</entry>
|
64
|
+
</file>
|
65
|
+
<file leaf-file-name="integer.rb" pinned="false" current-in-tab="false">
|
66
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/integer.rb">
|
67
|
+
<provider selected="true" editor-type-id="text-editor" />
|
68
|
+
</entry>
|
69
|
+
</file>
|
70
|
+
<file leaf-file-name="object.rb" pinned="false" current-in-tab="false">
|
71
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/object.rb">
|
72
|
+
<provider selected="true" editor-type-id="text-editor" />
|
73
|
+
</entry>
|
74
|
+
</file>
|
48
75
|
<file leaf-file-name="client.rb" pinned="false" current-in-tab="false">
|
49
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
76
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/client.rb">
|
50
77
|
<provider selected="true" editor-type-id="text-editor">
|
51
|
-
<state relative-caret-position="
|
52
|
-
<caret line="
|
78
|
+
<state relative-caret-position="414">
|
79
|
+
<caret line="23" selection-start-line="23" selection-end-line="23" />
|
53
80
|
</state>
|
54
81
|
</provider>
|
55
82
|
</entry>
|
56
83
|
</file>
|
57
|
-
<file leaf-file-name="
|
58
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
84
|
+
<file leaf-file-name="client.rb" pinned="false" current-in-tab="false">
|
85
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/baidu/client.rb">
|
59
86
|
<provider selected="true" editor-type-id="text-editor">
|
60
|
-
<state relative-caret-position="
|
61
|
-
<caret line="
|
87
|
+
<state relative-caret-position="90">
|
88
|
+
<caret line="5" selection-start-line="5" selection-end-line="5" />
|
62
89
|
</state>
|
63
90
|
</provider>
|
64
91
|
</entry>
|
@@ -110,8 +137,9 @@
|
|
110
137
|
<option value="$PROJECT_DIR$/lib/http_crawler/web/baidu/client.rb" />
|
111
138
|
<option value="$PROJECT_DIR$/lib/http_crawler/proxy.rb" />
|
112
139
|
<option value="$PROJECT_DIR$/lib/http_crawler/web.rb" />
|
113
|
-
<option value="$PROJECT_DIR$/lib/http_crawler/version.rb" />
|
114
140
|
<option value="$PROJECT_DIR$/lib/http_crawler/http.rb" />
|
141
|
+
<option value="$PROJECT_DIR$/lib/http_crawler/version.rb" />
|
142
|
+
<option value="$PROJECT_DIR$/lib/http_crawler/decryption/node.rb" />
|
115
143
|
</list>
|
116
144
|
</option>
|
117
145
|
</component>
|
@@ -124,7 +152,7 @@
|
|
124
152
|
<component name="NodePackageJsonFileManager">
|
125
153
|
<packageJsonPaths />
|
126
154
|
</component>
|
127
|
-
<component name="ProjectFrameBounds" fullScreen="true">
|
155
|
+
<component name="ProjectFrameBounds" extendedState="6" fullScreen="true">
|
128
156
|
<option name="y" value="23" />
|
129
157
|
<option name="width" value="1280" />
|
130
158
|
<option name="height" value="777" />
|
@@ -157,7 +185,28 @@
|
|
157
185
|
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
158
186
|
<item name="lib" type="462c0819:PsiDirectoryNode" />
|
159
187
|
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
160
|
-
<item name="
|
188
|
+
<item name="common" type="462c0819:PsiDirectoryNode" />
|
189
|
+
</path>
|
190
|
+
<path>
|
191
|
+
<item name="http_crawler" type="b2602c69:ProjectViewProjectNode" />
|
192
|
+
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
193
|
+
<item name="lib" type="462c0819:PsiDirectoryNode" />
|
194
|
+
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
195
|
+
<item name="decryption" type="462c0819:PsiDirectoryNode" />
|
196
|
+
</path>
|
197
|
+
<path>
|
198
|
+
<item name="http_crawler" type="b2602c69:ProjectViewProjectNode" />
|
199
|
+
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
200
|
+
<item name="lib" type="462c0819:PsiDirectoryNode" />
|
201
|
+
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
202
|
+
<item name="http" type="462c0819:PsiDirectoryNode" />
|
203
|
+
</path>
|
204
|
+
<path>
|
205
|
+
<item name="http_crawler" type="b2602c69:ProjectViewProjectNode" />
|
206
|
+
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
207
|
+
<item name="lib" type="462c0819:PsiDirectoryNode" />
|
208
|
+
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
209
|
+
<item name="web" type="462c0819:PsiDirectoryNode" />
|
161
210
|
</path>
|
162
211
|
<path>
|
163
212
|
<item name="http_crawler" type="b2602c69:ProjectViewProjectNode" />
|
@@ -165,6 +214,7 @@
|
|
165
214
|
<item name="lib" type="462c0819:PsiDirectoryNode" />
|
166
215
|
<item name="http_crawler" type="462c0819:PsiDirectoryNode" />
|
167
216
|
<item name="web" type="462c0819:PsiDirectoryNode" />
|
217
|
+
<item name="baidu" type="462c0819:PsiDirectoryNode" />
|
168
218
|
</path>
|
169
219
|
</expand>
|
170
220
|
<select />
|
@@ -220,31 +270,34 @@
|
|
220
270
|
<workItem from="1549964225949" duration="1209000" />
|
221
271
|
<workItem from="1550132724592" duration="3006000" />
|
222
272
|
<workItem from="1550208979012" duration="304000" />
|
273
|
+
<workItem from="1556176614736" duration="951000" />
|
223
274
|
</task>
|
224
275
|
<servers />
|
225
276
|
</component>
|
226
277
|
<component name="TimeTrackingManager">
|
227
|
-
<option name="totallyTimeSpent" value="
|
278
|
+
<option name="totallyTimeSpent" value="28578000" />
|
228
279
|
</component>
|
229
280
|
<component name="ToolWindowManager">
|
230
|
-
<frame x="0" y="0" width="1680" height="1050" extended-state="
|
281
|
+
<frame x="0" y="0" width="1680" height="1050" extended-state="6" />
|
282
|
+
<editor active="true" />
|
231
283
|
<layout>
|
232
|
-
<window_info active="true" content_ui="combo" id="Project" order="0" visible="true" weight="0.35042736" />
|
233
284
|
<window_info anchor="bottom" id="TODO" order="6" />
|
234
|
-
<window_info anchor="bottom" id="
|
285
|
+
<window_info anchor="bottom" id="Messages" weight="0.22974358" />
|
235
286
|
<window_info anchor="bottom" id="Event Log" order="7" side_tool="true" />
|
236
|
-
<window_info anchor="right" id="Database" order="3" />
|
237
287
|
<window_info anchor="bottom" id="Database Changes" order="7" show_stripe_button="false" />
|
288
|
+
<window_info anchor="bottom" id="Run" order="2" />
|
238
289
|
<window_info anchor="bottom" id="Version Control" order="7" />
|
239
|
-
<window_info id="Structure" order="1" side_tool="true" weight="0.25" />
|
240
290
|
<window_info anchor="bottom" id="Terminal" order="7" weight="0.45725647" />
|
291
|
+
<window_info active="true" content_ui="combo" id="Project" order="0" visible="true" weight="0.26923078" />
|
292
|
+
<window_info anchor="bottom" id="Docker" order="7" show_stripe_button="false" />
|
293
|
+
<window_info anchor="right" id="Database" order="3" />
|
294
|
+
<window_info id="Structure" order="1" side_tool="true" weight="0.25" />
|
295
|
+
<window_info anchor="bottom" id="Debug" order="3" weight="0.4" />
|
241
296
|
<window_info id="Favorites" order="2" side_tool="true" />
|
242
297
|
<window_info anchor="right" content_ui="combo" id="Hierarchy" order="2" weight="0.25" />
|
243
298
|
<window_info anchor="bottom" id="Inspection" order="5" weight="0.4" />
|
244
299
|
<window_info anchor="right" id="Commander" order="0" weight="0.4" />
|
245
300
|
<window_info anchor="right" id="Ant Build" order="1" weight="0.25" />
|
246
|
-
<window_info anchor="bottom" id="Run" order="2" />
|
247
|
-
<window_info anchor="bottom" id="Debug" order="3" weight="0.4" />
|
248
301
|
<window_info anchor="bottom" id="Message" order="0" />
|
249
302
|
<window_info anchor="bottom" id="Cvs" order="4" weight="0.25" />
|
250
303
|
<window_info anchor="bottom" id="Find" order="1" />
|
@@ -257,27 +310,6 @@
|
|
257
310
|
<option name="myLimit" value="2678400000" />
|
258
311
|
</component>
|
259
312
|
<component name="editorHistoryManager">
|
260
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/client.rb">
|
261
|
-
<provider selected="true" editor-type-id="text-editor">
|
262
|
-
<state relative-caret-position="90">
|
263
|
-
<caret line="6" column="36" selection-start-line="6" selection-start-column="36" selection-end-line="6" selection-end-column="36" />
|
264
|
-
</state>
|
265
|
-
</provider>
|
266
|
-
</entry>
|
267
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/proxy.rb">
|
268
|
-
<provider selected="true" editor-type-id="text-editor">
|
269
|
-
<state relative-caret-position="315">
|
270
|
-
<caret line="21" selection-start-line="21" selection-end-line="21" />
|
271
|
-
</state>
|
272
|
-
</provider>
|
273
|
-
</entry>
|
274
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/client.rb">
|
275
|
-
<provider selected="true" editor-type-id="text-editor">
|
276
|
-
<state relative-caret-position="150">
|
277
|
-
<caret line="10" column="48" selection-start-line="10" selection-start-column="48" selection-end-line="10" selection-end-column="48" />
|
278
|
-
</state>
|
279
|
-
</provider>
|
280
|
-
</entry>
|
281
313
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/baidu/client.rb">
|
282
314
|
<provider selected="true" editor-type-id="text-editor">
|
283
315
|
<state relative-caret-position="15">
|
@@ -292,13 +324,7 @@
|
|
292
324
|
</state>
|
293
325
|
</provider>
|
294
326
|
</entry>
|
295
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/version.rb"
|
296
|
-
<provider selected="true" editor-type-id="text-editor">
|
297
|
-
<state relative-caret-position="45">
|
298
|
-
<caret line="3" lean-forward="true" selection-start-line="3" selection-end-line="3" />
|
299
|
-
</state>
|
300
|
-
</provider>
|
301
|
-
</entry>
|
327
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/version.rb" />
|
302
328
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/proxy/client.rb">
|
303
329
|
<provider selected="true" editor-type-id="text-editor">
|
304
330
|
<state relative-caret-position="30">
|
@@ -306,20 +332,8 @@
|
|
306
332
|
</state>
|
307
333
|
</provider>
|
308
334
|
</entry>
|
309
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler.rb"
|
310
|
-
|
311
|
-
<state relative-caret-position="120">
|
312
|
-
<caret line="8" lean-forward="true" selection-start-line="8" selection-end-line="8" />
|
313
|
-
</state>
|
314
|
-
</provider>
|
315
|
-
</entry>
|
316
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http.rb">
|
317
|
-
<provider selected="true" editor-type-id="text-editor">
|
318
|
-
<state>
|
319
|
-
<caret column="4" selection-start-column="4" selection-end-column="4" />
|
320
|
-
</state>
|
321
|
-
</provider>
|
322
|
-
</entry>
|
335
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler.rb" />
|
336
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http.rb" />
|
323
337
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common.rb">
|
324
338
|
<provider selected="true" editor-type-id="text-editor">
|
325
339
|
<state relative-caret-position="45">
|
@@ -366,12 +380,6 @@
|
|
366
380
|
</state>
|
367
381
|
</provider>
|
368
382
|
</entry>
|
369
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/string.rb">
|
370
|
-
<provider selected="true" editor-type-id="text-editor" />
|
371
|
-
</entry>
|
372
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/object.rb">
|
373
|
-
<provider selected="true" editor-type-id="text-editor" />
|
374
|
-
</entry>
|
375
383
|
<entry file="file://$PROJECT_DIR$/README.md">
|
376
384
|
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
|
377
385
|
<state split_layout="SPLIT">
|
@@ -468,20 +476,8 @@
|
|
468
476
|
</state>
|
469
477
|
</provider>
|
470
478
|
</entry>
|
471
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/net/http.rb"
|
472
|
-
|
473
|
-
<state relative-caret-position="30">
|
474
|
-
<caret line="2" lean-forward="true" selection-start-line="2" selection-end-line="2" />
|
475
|
-
</state>
|
476
|
-
</provider>
|
477
|
-
</entry>
|
478
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler.rb">
|
479
|
-
<provider selected="true" editor-type-id="text-editor">
|
480
|
-
<state relative-caret-position="120">
|
481
|
-
<caret line="8" column="22" lean-forward="true" selection-start-line="8" selection-start-column="22" selection-end-line="8" selection-end-column="22" />
|
482
|
-
</state>
|
483
|
-
</provider>
|
484
|
-
</entry>
|
479
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/net/http.rb" />
|
480
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler.rb" />
|
485
481
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/baidu/response/index.rb">
|
486
482
|
<provider selected="true" editor-type-id="text-editor">
|
487
483
|
<state relative-caret-position="240">
|
@@ -503,16 +499,9 @@
|
|
503
499
|
</state>
|
504
500
|
</provider>
|
505
501
|
</entry>
|
506
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/client.rb">
|
507
|
-
<provider selected="true" editor-type-id="text-editor">
|
508
|
-
<state relative-caret-position="150">
|
509
|
-
<caret line="10" column="48" selection-start-line="10" selection-start-column="48" selection-end-line="10" selection-end-column="48" />
|
510
|
-
</state>
|
511
|
-
</provider>
|
512
|
-
</entry>
|
513
502
|
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common.rb">
|
514
503
|
<provider selected="true" editor-type-id="text-editor">
|
515
|
-
<state relative-caret-position="
|
504
|
+
<state relative-caret-position="36">
|
516
505
|
<caret line="2" selection-start-line="2" selection-end-line="2" />
|
517
506
|
</state>
|
518
507
|
</provider>
|
@@ -552,45 +541,59 @@
|
|
552
541
|
</state>
|
553
542
|
</provider>
|
554
543
|
</entry>
|
555
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
544
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/proxy.rb">
|
556
545
|
<provider selected="true" editor-type-id="text-editor">
|
557
|
-
<state relative-caret-position="
|
558
|
-
<caret line="
|
546
|
+
<state relative-caret-position="441">
|
547
|
+
<caret line="21" selection-start-line="21" selection-end-line="21" />
|
559
548
|
</state>
|
560
549
|
</provider>
|
561
550
|
</entry>
|
562
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
551
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/baidu/client.rb">
|
563
552
|
<provider selected="true" editor-type-id="text-editor">
|
564
|
-
<state relative-caret-position="
|
565
|
-
<caret line="
|
553
|
+
<state relative-caret-position="90">
|
554
|
+
<caret line="5" selection-start-line="5" selection-end-line="5" />
|
566
555
|
</state>
|
567
556
|
</provider>
|
568
557
|
</entry>
|
569
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
558
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http.rb" />
|
559
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/net/response.rb" />
|
560
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/version.rb">
|
570
561
|
<provider selected="true" editor-type-id="text-editor">
|
571
|
-
<state relative-caret-position="
|
572
|
-
<caret line="
|
562
|
+
<state relative-caret-position="54">
|
563
|
+
<caret line="3" lean-forward="true" selection-start-line="3" selection-end-line="3" />
|
573
564
|
</state>
|
574
565
|
</provider>
|
575
566
|
</entry>
|
576
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
567
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/integer.rb">
|
568
|
+
<provider selected="true" editor-type-id="text-editor" />
|
569
|
+
</entry>
|
570
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/object.rb">
|
571
|
+
<provider selected="true" editor-type-id="text-editor" />
|
572
|
+
</entry>
|
573
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/common/string.rb">
|
574
|
+
<provider selected="true" editor-type-id="text-editor" />
|
575
|
+
</entry>
|
576
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/http/response.rb">
|
577
|
+
<provider selected="true" editor-type-id="text-editor" />
|
578
|
+
</entry>
|
579
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/web/client.rb">
|
577
580
|
<provider selected="true" editor-type-id="text-editor">
|
578
|
-
<state relative-caret-position="
|
579
|
-
<caret line="
|
581
|
+
<state relative-caret-position="180">
|
582
|
+
<caret line="10" column="48" selection-start-line="10" selection-start-column="48" selection-end-line="10" selection-end-column="48" />
|
580
583
|
</state>
|
581
584
|
</provider>
|
582
585
|
</entry>
|
583
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
586
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/client.rb">
|
584
587
|
<provider selected="true" editor-type-id="text-editor">
|
585
|
-
<state relative-caret-position="
|
586
|
-
<caret line="
|
588
|
+
<state relative-caret-position="414">
|
589
|
+
<caret line="23" selection-start-line="23" selection-end-line="23" />
|
587
590
|
</state>
|
588
591
|
</provider>
|
589
592
|
</entry>
|
590
|
-
<entry file="file://$PROJECT_DIR$/lib/http_crawler/
|
593
|
+
<entry file="file://$PROJECT_DIR$/lib/http_crawler/decryption/node.rb">
|
591
594
|
<provider selected="true" editor-type-id="text-editor">
|
592
|
-
<state relative-caret-position="
|
593
|
-
<caret line="
|
595
|
+
<state relative-caret-position="342">
|
596
|
+
<caret line="19" column="7" lean-forward="true" selection-start-line="19" selection-start-column="7" selection-end-line="19" selection-end-column="7" />
|
594
597
|
</state>
|
595
598
|
</provider>
|
596
599
|
</entry>
|
data/lib/http_crawler.rb
CHANGED
@@ -21,7 +21,6 @@ require_dependency 'http_crawler/common.rb'
|
|
21
21
|
require_dependency 'http_crawler/client.rb'
|
22
22
|
require_dependency 'http_crawler/web.rb'
|
23
23
|
require_dependency 'http_crawler/proxy.rb'
|
24
|
-
require_dependency 'http_crawler/decryption.rb'
|
25
24
|
|
26
25
|
module HttpCrawler
|
27
26
|
# Your code goes here...
|
@@ -2,14 +2,14 @@ class String
|
|
2
2
|
# 清除干扰数据
|
3
3
|
# 清除包含: 空格,回车
|
4
4
|
#
|
5
|
-
def
|
5
|
+
def jagger_del_inter
|
6
6
|
self.gsub(/(?:\n|\t|\r| | )/, "")
|
7
7
|
end
|
8
8
|
|
9
9
|
# 转换成时间格式
|
10
|
-
def
|
10
|
+
def jagger_to_time
|
11
11
|
|
12
|
-
#
|
12
|
+
# 然后先遍历所有格式
|
13
13
|
[
|
14
14
|
"%Y年%m月%d日%H:%M:%S",
|
15
15
|
"%Y年%m月%d日 %H:%M:%S",
|
@@ -25,10 +25,23 @@ class String
|
|
25
25
|
"%Y年%m月%d日",
|
26
26
|
"%Y%m%d",
|
27
27
|
|
28
|
+
"%m月%d日",
|
29
|
+
|
30
|
+
"%m月%d日 %H%M",
|
31
|
+
"%m月%d日 %H%M%S",
|
32
|
+
"%m月%d日%H%M",
|
33
|
+
"%m月%d日%H%M%S",
|
34
|
+
|
35
|
+
"%m月%d日 %H:%M",
|
36
|
+
"%m月%d日 %H:%M:%S",
|
37
|
+
"%m月%d日%H:%M",
|
38
|
+
"%m月%d日%H:%M:%S",
|
39
|
+
|
28
40
|
"%Y%m%d%H%M%S",
|
29
41
|
"%Y%m%d%H%M",
|
30
42
|
|
31
43
|
].each do |v|
|
44
|
+
Rails.logger.debug v
|
32
45
|
begin
|
33
46
|
return Time.strptime(self, v)
|
34
47
|
rescue => error
|
@@ -36,8 +49,8 @@ class String
|
|
36
49
|
end
|
37
50
|
end
|
38
51
|
|
39
|
-
Time.at(self.to_i / 1000.0) if self.length == 13
|
40
|
-
Time.at(self.to_i) if self.length == 10
|
52
|
+
return Time.at(self.to_i / 1000.0) if self.length == 13
|
53
|
+
return Time.at(self.to_i) if self.length == 10
|
41
54
|
|
42
55
|
# 最后用 Time通用类型尝试
|
43
56
|
return Time.parse(self)
|
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: 0.3.1.
|
4
|
+
version: 0.3.1.19
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- jagger
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-04-
|
11
|
+
date: 2019-04-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rspec
|