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
f09aa1c9
Commit
f09aa1c9
authored
Dec 29, 2017
by
yangchen
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
增加大鱼的相关采集
parent
4c650e8d
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
187 additions
and
17 deletions
+187
-17
src/main/java/com/zhiwei/httpclient/HeadGet.java
+175
-10
src/main/java/com/zhiwei/parse/Dayu.java
+2
-1
src/main/java/com/zhiwei/parse/analysis/DayuCommentAnalysis.java
+2
-3
src/test/java/com/zhiwei/crawler/DayuCommentExample.java
+7
-2
src/test/java/com/zhiwei/crawler/YidainzixunByWordExample.java
+1
-1
No files found.
src/main/java/com/zhiwei/httpclient/HeadGet.java
View file @
f09aa1c9
...
...
@@ -7,6 +7,8 @@ import java.util.Map;
import
org.jsoup.Jsoup
;
import
org.jsoup.nodes.Document
;
import
com.alibaba.fastjson.JSONObject
;
public
class
HeadGet
{
/**
...
...
@@ -336,17 +338,180 @@ public class HeadGet {
return
headerMap
;
}
public
static
void
main
(
String
[]
args
)
{
String
url
=
"http://www.miaopai.com/show/H99oVYnsv47ejBqK8TMZXA__.htm"
;
String
cookie
=
"kg_udid=9E907CB26A8E3CC24F416CB5CF360E9F; sessionId=f771a3317da8040ace111d192f5e32df; udid=59B30CA793DBDCA2D400F41C8B3DDA78; aliyungf_tc=AQAAAEVz1U5hFwoA6tbnc5AZYZww6PRM"
;
Map
<
String
,
String
>
headerMap
=
HeadGet
.
getMiaoPaiByURlHeaderMap
(
null
);
String
result
=
HttpClient
.
executeHttpRequestGet
(
url
,
headerMap
);
Document
doc
=
Jsoup
.
parse
(
result
);
String
s
=
doc
.
select
(
"body > div.box885 > div.contentLeft.contentLeft_detail > div.videoList.video_detail > div.videoIntr > div > div.personalAbout > div.personalData > p.personalDataN > a"
).
text
();
System
.
out
.
println
(
s
);
/**
*
* @Description 爱奇艺关键词获取视频信息头信息
* @param cookie
* @return
*/
public
static
Map
<
String
,
String
>
getAiqiyiBywordHeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"so.iqiyi.com"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-CN,zh;q=0.9"
);
headerMap
.
put
(
"Accept"
,
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
/**
*
* @Description 爱奇艺链接视频信息头信息
* @param cookie
* @return
*/
public
static
Map
<
String
,
String
>
getAiqiyiHeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"www.iqiyi.com"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-CN,zh;q=0.9"
);
headerMap
.
put
(
"Accept"
,
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
/**
*
* @Description 爱奇艺获取播放数头信息
* @param cookie
* @return
*/
public
static
Map
<
String
,
String
>
getAiqiyiForCountHeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"cache.video.iqiyi.com"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-CN,zh;q=0.9"
);
headerMap
.
put
(
"Accept"
,
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
/**
*
* @Description 梨视频获取头信息
* @param cookie
* @return
*/
public
static
Map
<
String
,
String
>
getPearVideoByWordHeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"www.pearvideo.com"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-CN,zh;q=0.9"
);
headerMap
.
put
(
"Accept"
,
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
/**
*
* @Description 西瓜视频获取头信息
* @param cookie
* @return
*/
public
static
Map
<
String
,
String
>
getXiguaByWordHeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"www.ixigua.com"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-CN,zh;q=0.9"
);
headerMap
.
put
(
"Accept"
,
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
/**
*
* @Description 优酷视频获取头信息
* @param cookie
* @return
*/
public
static
Map
<
String
,
String
>
getSoKuByWordHeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"www.soku.com"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-CN,zh;q=0.9"
);
headerMap
.
put
(
"Accept"
,
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
public
static
Map
<
String
,
String
>
getJikeComment39HeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"app.jike.ruguoapp.com"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-cn"
);
headerMap
.
put
(
"Accept"
,
"*/*"
);
headerMap
.
put
(
"User-Agent"
,
"%E5%8D%B3%E5%88%BB/989 CFNetwork/811.5.4 Darwin/16.7.0"
);
headerMap
.
put
(
"App-BuildNo"
,
"989"
);
headerMap
.
put
(
"App-Version"
,
"3.9.1"
);
headerMap
.
put
(
"Content-Type"
,
"application/json"
);
headerMap
.
put
(
"Manufacturer"
,
"Apple"
);
headerMap
.
put
(
"Content-Length"
,
"39"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"OS-Version"
,
"Version 10.3.3 (Build 14G60)"
);
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
public
static
Map
<
String
,
String
>
getJikeComment94HeaderMap
(
String
cookie
)
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<
String
,
String
>();
headerMap
.
put
(
"Host"
,
"app.jike.ruguoapp.com"
);
headerMap
.
put
(
"Accept-Language"
,
"zh-cn"
);
headerMap
.
put
(
"Accept"
,
"*/*"
);
headerMap
.
put
(
"User-Agent"
,
"%E5%8D%B3%E5%88%BB/989 CFNetwork/811.5.4 Darwin/16.7.0"
);
headerMap
.
put
(
"App-BuildNo"
,
"989"
);
headerMap
.
put
(
"App-Version"
,
"3.9.1"
);
// headerMap.put("Content-Type", "application/json");
headerMap
.
put
(
"Manufacturer"
,
"Apple"
);
headerMap
.
put
(
"Content-Length"
,
"94"
);
headerMap
.
put
(
"Connection"
,
"keep-alive"
);
headerMap
.
put
(
"OS-Version"
,
"Version 10.3.3 (Build 14G60)"
);
// System.out.println(result);
// System.out.println(result.length());
if
(
cookie
!=
null
)
{
headerMap
.
put
(
"Cookie"
,
cookie
);
}
return
headerMap
;
}
public
static
Map
<
String
,
Object
>
getJikeCommentParamMap
(
String
targetId
,
String
time
)
{
Map
<
String
,
Object
>
paramMap
=
new
HashMap
<
String
,
Object
>();
JSONObject
json
=
new
JSONObject
();
if
(
time
!=
null
)
{
json
.
put
(
"createdAt"
,
time
);
paramMap
.
put
(
"loadMoreKey"
,
json
);
}
paramMap
.
put
(
"targetId"
,
targetId
);
return
paramMap
;
}
public
static
void
main
(
String
[]
args
)
{
String
url
=
"https://app.jike.ruguoapp.com/1.0/messageComments/listPrimary"
;
String
cookie
=
"jike:config:searchPlaceholderLastInfo=1514465731446#0; jike:sess=eyJfdWlkIjoiNWE0NGRmMTlmOWM4NWYwMDExODJhMjkwIiwiX3Nlc3Npb25Ub2tlbiI6InQ5cExKaEpiTFdVeDFsbUxKZW9vMUlKMEsifQ==; jike:sess.sig=HBuRKsTsMIIR9aMDUdkNV_mGH1E"
;
Map
<
String
,
String
>
headerMap
=
HeadGet
.
getJikeComment94HeaderMap
(
cookie
);
Map
<
String
,
Object
>
paramMap
=
HeadGet
.
getJikeCommentParamMap
(
"5a449a3d580d23001148412e"
,
"2017-12-28T10:17:50.601Z"
);
String
result
=
HttpClient
.
executeHttpRequestPost
(
url
,
headerMap
,
paramMap
);
System
.
out
.
println
(
result
);
System
.
out
.
println
(
result
.
length
());
}
}
src/main/java/com/zhiwei/parse/Dayu.java
View file @
f09aa1c9
...
...
@@ -74,7 +74,7 @@ public class Dayu {
dataList
.
addAll
(
lists
);
while
(
true
)
{
lists
.
clear
();
ZhiWeiTools
.
sleep
(
5
000
);
ZhiWeiTools
.
sleep
(
3
000
);
System
.
out
.
println
(
url
+
"&hotValue="
+
i
);
result
=
HttpClient
.
executeHttpRequestGet
(
url
+
"&hotValue="
+
i
,
headerMap
);
lists
=
dayuCommentAnalysis
.
getDayuCommentData
(
result
,
articleId
);
...
...
@@ -83,6 +83,7 @@ public class Dayu {
}
dataList
.
addAll
(
lists
);
i
-=
10
;
System
.
out
.
println
(
"=============已获取到的评论数"
+
dataList
.
size
());
}
return
dataList
;
}
catch
(
Exception
e
)
{
...
...
src/main/java/com/zhiwei/parse/analysis/DayuCommentAnalysis.java
View file @
f09aa1c9
...
...
@@ -45,7 +45,6 @@ public class DayuCommentAnalysis {
int
i
=
data
.
getInteger
(
"reply_cnt"
);
dataMap
.
put
(
"replay_count"
,
i
);
if
(
i
>
0
)
{
// System.out.println(dataMap.toString());
dataList
.
addAll
(
getReplayData
(
id
,
articleId
));
}
dataList
.
add
(
dataMap
);
...
...
@@ -71,7 +70,7 @@ public class DayuCommentAnalysis {
List
<
Map
<
String
,
Object
>>
data
=
new
ArrayList
<
Map
<
String
,
Object
>>();
List
<
String
>
timeList
=
new
ArrayList
<
String
>();
while
(
true
)
{
ZhiWeiTools
.
sleep
(
3
000
);
ZhiWeiTools
.
sleep
(
2
000
);
long
time
=
analysisReplayData
(
result
,
data
);
if
(
timeList
.
contains
(
String
.
valueOf
(
time
))){
break
;
...
...
@@ -82,7 +81,7 @@ public class DayuCommentAnalysis {
}
result
=
HttpClient
.
executeHttpRequestGet
(
url
+
time
,
headerMap
);
}
System
.
out
.
println
(
"====================="
+
data
.
size
());
System
.
out
.
println
(
"=====================
评论下回复获取数==
"
+
data
.
size
());
return
data
;
}
...
...
src/test/java/com/zhiwei/crawler/DayuCommentExample.java
View file @
f09aa1c9
...
...
@@ -18,7 +18,7 @@ public class DayuCommentExample {
//14180961224021425316 这个为此参数
PoiExcelUtil
poi
=
PoiExcelUtil
.
getInstance
();
Map
<
String
,
Object
>
map
=
poi
.
importExcel
(
"D://crawlerdata/UC评论采集.xlsx"
,
0
);
Map
<
String
,
Object
>
map
=
poi
.
importExcel
(
"D://crawlerdata/UC评论采集
-1
.xlsx"
,
0
);
List
<
Map
<
String
,
Object
>>
list
=
(
List
<
Map
<
String
,
Object
>>)
map
.
get
(
"body"
);
List
<
Map
<
String
,
Object
>>
bodyList
=
new
ArrayList
<
Map
<
String
,
Object
>>();
List
<
String
>
urlList
=
new
ArrayList
<
String
>();
...
...
@@ -26,7 +26,12 @@ public class DayuCommentExample {
String
url
=
""
;
try
{
url
=
map1
.
get
(
"url"
)+
""
;
String
articleId
=
url
.
split
(
"aid="
)[
1
].
split
(
"&"
)[
0
];
String
articleId
=
""
;
if
(
url
.
contains
(
"aid"
))
{
articleId
=
url
.
split
(
"aid="
)[
1
].
split
(
"&"
)[
0
];
}
else
{
articleId
=
url
;
}
List
<
Map
<
String
,
Object
>>
dataList
=
Dayu
.
getDayuCommentData
(
articleId
);
if
(
dataList
.
size
()
<=
0
)
{
urlList
.
add
(
url
);
...
...
src/test/java/com/zhiwei/crawler/YidainzixunByWordExample.java
View file @
f09aa1c9
...
...
@@ -35,7 +35,7 @@ public class YidainzixunByWordExample {
headList
.
add
(
"time"
);
headList
.
add
(
"url"
);
System
.
out
.
println
(
listAll
.
size
());
poi
.
exportExcel
(
"D://crawlerdata/一点资讯-美
林
.xlsx"
,
"asd"
,
headList
,
listAll
);
poi
.
exportExcel
(
"D://crawlerdata/一点资讯-美
食
.xlsx"
,
"asd"
,
headList
,
listAll
);
}
...
...
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