Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
A
articlenewscrawler
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
chenweiyang
articlenewscrawler
Commits
0709d18e
Commit
0709d18e
authored
Nov 16, 2018
by
yangchen
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
新增 部分网站评论采集 验证版
parent
41208eb5
Show whitespace changes
Inline
Side-by-side
Showing
7 changed files
with
10 additions
and
6 deletions
+10
-6
src/main/java/com/zhiwei/parse/QicheHome.java
+1
-1
src/main/java/com/zhiwei/parse/analysis/FenghuangCommentAnalysis.java
+2
-2
src/main/java/com/zhiwei/parse/analysis/PcautoCommentAnalysis.java
+2
-0
src/main/java/com/zhiwei/parse/analysis/QicheHomeKwyWordAnalysis.java
+1
-0
src/main/java/com/zhiwei/parse/analysis/SinaKejiCommentAnalysis.java
+1
-0
src/main/java/com/zhiwei/parse/analysis/WangyiCommentAnalysis.java
+3
-3
src/test/java/com/zhiwei/keyword/QicheComment.java
+0
-0
No files found.
src/main/java/com/zhiwei/parse/QicheHome.java
View file @
0709d18e
...
@@ -35,12 +35,12 @@ public class QicheHome {
...
@@ -35,12 +35,12 @@ public class QicheHome {
count
=
qicheHomeKwyWordAnalysis
.
getCount
(
result
);
count
=
qicheHomeKwyWordAnalysis
.
getCount
(
result
);
}
}
bodyList
.
addAll
(
qicheHomeKwyWordAnalysis
.
getData
(
result
));
bodyList
.
addAll
(
qicheHomeKwyWordAnalysis
.
getData
(
result
));
page
++;
logger
.
info
(
"采集 articleid {} 总页数 {} 第 {} 页 , 采集总数 {}"
,
articleid
,
count
,
page
,
bodyList
.
size
());
logger
.
info
(
"采集 articleid {} 总页数 {} 第 {} 页 , 采集总数 {}"
,
articleid
,
count
,
page
,
bodyList
.
size
());
ZhiWeiTools
.
sleep
(
3000
);
ZhiWeiTools
.
sleep
(
3000
);
if
(
page
>
count
)
{
if
(
page
>
count
)
{
break
;
break
;
}
}
page
++;
}
catch
(
IOException
e
)
{
}
catch
(
IOException
e
)
{
e
.
printStackTrace
();
e
.
printStackTrace
();
n
++;
n
++;
...
...
src/main/java/com/zhiwei/parse/analysis/FenghuangCommentAnalysis.java
View file @
0709d18e
...
@@ -130,9 +130,9 @@ public class FenghuangCommentAnalysis {
...
@@ -130,9 +130,9 @@ public class FenghuangCommentAnalysis {
private
Map
<
String
,
Object
>
getcommentData2
(
JSONObject
json
)
{
private
Map
<
String
,
Object
>
getcommentData2
(
JSONObject
json
)
{
Map
<
String
,
Object
>
map
=
new
HashMap
<>();
Map
<
String
,
Object
>
map
=
new
HashMap
<>();
try
{
try
{
map
.
put
(
"
nicknam
e"
,
json
.
getString
(
"uname"
));
map
.
put
(
"
sourc
e"
,
json
.
getString
(
"uname"
));
map
.
put
(
"content"
,
json
.
getString
(
"comment_contents"
).
replaceAll
(
"""
,
""
));
map
.
put
(
"content"
,
json
.
getString
(
"comment_contents"
).
replaceAll
(
"""
,
""
));
map
.
put
(
"id"
,
json
.
getString
(
"
article_
id"
));
map
.
put
(
"id"
,
json
.
getString
(
"
comment_tem
id"
));
map
.
put
(
"like"
,
json
.
getString
(
"uptimes"
));
map
.
put
(
"like"
,
json
.
getString
(
"uptimes"
));
map
.
put
(
"from"
,
json
.
getString
(
"ip_from"
));
map
.
put
(
"from"
,
json
.
getString
(
"ip_from"
));
map
.
put
(
"time"
,
TimeParse
.
stringFormartDate
(
json
.
getString
(
"comment_date"
)));
map
.
put
(
"time"
,
TimeParse
.
stringFormartDate
(
json
.
getString
(
"comment_date"
)));
...
...
src/main/java/com/zhiwei/parse/analysis/PcautoCommentAnalysis.java
View file @
0709d18e
...
@@ -33,7 +33,9 @@ public class PcautoCommentAnalysis {
...
@@ -33,7 +33,9 @@ public class PcautoCommentAnalysis {
String
time
=
element
.
select
(
"div.cmtMain > div > div.thTB > span.cmtTime"
).
text
();
String
time
=
element
.
select
(
"div.cmtMain > div > div.thTB > span.cmtTime"
).
text
();
map
.
put
(
"time"
,
TimeParse
.
stringFormartDate
(
time
));
map
.
put
(
"time"
,
TimeParse
.
stringFormartDate
(
time
));
String
like
=
element
.
select
(
"span.cmtSupportNum"
).
text
();
String
like
=
element
.
select
(
"span.cmtSupportNum"
).
text
();
String
id
=
element
.
select
(
"a.cmtVote"
).
attr
(
"data-id"
);
map
.
put
(
"like"
,
like
);
map
.
put
(
"like"
,
like
);
map
.
put
(
"id"
,
id
);
dataList
.
add
(
map
);
dataList
.
add
(
map
);
}
}
boolean
next
=
false
;
boolean
next
=
false
;
...
...
src/main/java/com/zhiwei/parse/analysis/QicheHomeKwyWordAnalysis.java
View file @
0709d18e
...
@@ -31,6 +31,7 @@ public class QicheHomeKwyWordAnalysis {
...
@@ -31,6 +31,7 @@ public class QicheHomeKwyWordAnalysis {
String
time
=
data
.
getString
(
"RReplyDate"
);
String
time
=
data
.
getString
(
"RReplyDate"
);
map
.
put
(
"time"
,
TimeParse
.
dateFormartString
(
TimeParse
.
stringFormartDate
(
time
.
split
(
"Date\\("
)[
1
].
split
(
"\\+"
)[
0
]),
"yyyy-MM-dd HH:mm:ss"
));
map
.
put
(
"time"
,
TimeParse
.
dateFormartString
(
TimeParse
.
stringFormartDate
(
time
.
split
(
"Date\\("
)[
1
].
split
(
"\\+"
)[
0
]),
"yyyy-MM-dd HH:mm:ss"
));
map
.
put
(
"like"
,
data
.
getInteger
(
"RUp"
));
map
.
put
(
"like"
,
data
.
getInteger
(
"RUp"
));
map
.
put
(
"id"
,
data
.
getString
(
"RMemberId"
));
bodyList
.
add
(
map
);
bodyList
.
add
(
map
);
}
}
return
bodyList
;
return
bodyList
;
...
...
src/main/java/com/zhiwei/parse/analysis/SinaKejiCommentAnalysis.java
View file @
0709d18e
...
@@ -29,6 +29,7 @@ public class SinaKejiCommentAnalysis {
...
@@ -29,6 +29,7 @@ public class SinaKejiCommentAnalysis {
map
.
put
(
"source"
,
data
.
getString
(
"nick"
));
map
.
put
(
"source"
,
data
.
getString
(
"nick"
));
map
.
put
(
"like"
,
data
.
getString
(
"agree"
));
map
.
put
(
"like"
,
data
.
getString
(
"agree"
));
map
.
put
(
"location"
,
data
.
getString
(
"area"
));
map
.
put
(
"location"
,
data
.
getString
(
"area"
));
map
.
put
(
"id"
,
data
.
getString
(
"status_cmnt_mid"
));
dataList
.
add
(
map
);
dataList
.
add
(
map
);
}
}
return
dataList
;
return
dataList
;
...
...
src/main/java/com/zhiwei/parse/analysis/WangyiCommentAnalysis.java
View file @
0709d18e
...
@@ -16,13 +16,13 @@ public class WangyiCommentAnalysis {
...
@@ -16,13 +16,13 @@ public class WangyiCommentAnalysis {
@SuppressWarnings
(
"unchecked"
)
@SuppressWarnings
(
"unchecked"
)
public
List
<
Map
<
String
,
Object
>>
getWangyiCommentData
(
String
result
,
List
<
String
>
idList
)
{
public
List
<
Map
<
String
,
Object
>>
getWangyiCommentData
(
String
result
,
List
<
String
>
idList
)
{
List
<
Map
<
String
,
Object
>>
dataList
=
new
ArrayList
<
Map
<
String
,
Object
>
>();
List
<
Map
<
String
,
Object
>>
dataList
=
new
ArrayList
<>();
try
{
try
{
JSONObject
json
=
JSONObject
.
parseObject
(
result
);
JSONObject
json
=
JSONObject
.
parseObject
(
result
);
Map
<
String
,
Object
>
dataMap
=
(
Map
<
String
,
Object
>)
json
.
get
(
"comments"
);
Map
<
String
,
Object
>
dataMap
=
(
Map
<
String
,
Object
>)
json
.
get
(
"comments"
);
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
dataMap
.
entrySet
())
{
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
dataMap
.
entrySet
())
{
JSONObject
data
=
JSONObject
.
parseObject
(
entry
.
getValue
().
toString
());
JSONObject
data
=
JSONObject
.
parseObject
(
entry
.
getValue
().
toString
());
Map
<
String
,
Object
>
map
=
new
HashMap
<
String
,
Object
>();
Map
<
String
,
Object
>
map
=
new
HashMap
<>();
String
id
=
data
.
getString
(
"postId"
);
String
id
=
data
.
getString
(
"postId"
);
if
(
idList
.
contains
(
id
))
{
if
(
idList
.
contains
(
id
))
{
continue
;
continue
;
...
@@ -38,7 +38,7 @@ public class WangyiCommentAnalysis {
...
@@ -38,7 +38,7 @@ public class WangyiCommentAnalysis {
}
}
return
dataList
;
return
dataList
;
}
catch
(
Exception
e
)
{
}
catch
(
Exception
e
)
{
logger
.
error
(
"解析出错
"
,
e
.
getMessage
()
);
logger
.
error
(
"解析出错
{}"
,
e
);
return
dataList
;
return
dataList
;
}
}
}
}
...
...
src/test/java/com/zhiwei/keyword/Qiche
KeyWord
.java
→
src/test/java/com/zhiwei/keyword/Qiche
Comment
.java
View file @
0709d18e
File moved
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment