Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
S
searchhotcrawler
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
zhiwei
searchhotcrawler
Commits
7546fbb8
Commit
7546fbb8
authored
Jul 12, 2021
by
chenweitao
Browse files
Options
Browse Files
Download
Plain Diff
Merge branch 'working' into 'master'
Working See merge request
!99
parents
e3740064
3d271f76
Hide whitespace changes
Inline
Side-by-side
Showing
19 changed files
with
847 additions
and
494 deletions
+847
-494
searchhotcrawler.iml
+6
-2
src/main/java/com/zhiwei/searchhotcrawler/bean/HotSearchType.java
+26
-25
src/main/java/com/zhiwei/searchhotcrawler/bean/WeiBoUser.java
+11
-1
src/main/java/com/zhiwei/searchhotcrawler/crawler/BaiDuHotSearchCrawler.java
+0
-2
src/main/java/com/zhiwei/searchhotcrawler/crawler/MaiMaiHotSearchCrawler.java
+4
-1
src/main/java/com/zhiwei/searchhotcrawler/crawler/WeiboHotSearchCrawler.java
+548
-429
src/main/java/com/zhiwei/searchhotcrawler/dao/HotSearchCacheDAO.java
+19
-1
src/main/java/com/zhiwei/searchhotcrawler/dao/WeiBoUserDao.java
+11
-2
src/main/java/com/zhiwei/searchhotcrawler/run/HotSearchRun.java
+1
-0
src/main/java/com/zhiwei/searchhotcrawler/test/HotSearch36KrCrawlerTest.java
+0
-6
src/main/java/com/zhiwei/searchhotcrawler/test/HotSearchRunTest.java
+5
-0
src/main/java/com/zhiwei/searchhotcrawler/test/TaoBaoHotSearchCrawlerTest.java
+85
-0
src/main/java/com/zhiwei/searchhotcrawler/timer/BaiduHotSearchRun.java
+13
-12
src/main/java/com/zhiwei/searchhotcrawler/timer/WeiboHotSearchRun.java
+0
-2
src/main/java/com/zhiwei/searchhotcrawler/util/MD5Util.java
+54
-0
src/main/java/com/zhiwei/searchhotcrawler/util/TaoBaoUtils.java
+38
-0
src/main/resources/redis.properties
+2
-0
src/test/java/ObjectTest.java
+2
-2
src/test/java/hotSaerchTest/HotSearchTest.java
+22
-9
No files found.
searchhotcrawler.iml
View file @
7546fbb8
<?xml version="1.0" encoding="UTF-8"?>
<module
org.jetbrains.idea.maven.project.MavenProjectsManager.isMavenModule=
"true"
type=
"JAVA_MODULE"
version=
"4"
>
<module
org.jetbrains.idea.maven.project.MavenProjectsManager.isMavenModule=
"true"
version=
"4"
>
<component
name=
"FacetManager"
>
<facet
type=
"Spring"
name=
"Spring"
>
<configuration
/>
...
...
@@ -10,8 +10,8 @@
<output-test
url=
"file://$MODULE_DIR$/target/test-classes"
/>
<content
url=
"file://$MODULE_DIR$"
>
<sourceFolder
url=
"file://$MODULE_DIR$/src/main/java"
isTestSource=
"false"
/>
<sourceFolder
url=
"file://$MODULE_DIR$/src/main/resources"
type=
"java-resource"
/>
<sourceFolder
url=
"file://$MODULE_DIR$/src/test/java"
isTestSource=
"true"
/>
<sourceFolder
url=
"file://$MODULE_DIR$/src/main/resources"
type=
"java-resource"
/>
<excludeFolder
url=
"file://$MODULE_DIR$/target"
/>
</content>
<orderEntry
type=
"inheritedJdk"
/>
...
...
@@ -77,5 +77,8 @@
<orderEntry
type=
"library"
name=
"Maven: org.apache.commons:commons-pool2:2.4.2"
level=
"project"
/>
<orderEntry
type=
"library"
scope=
"TEST"
name=
"Maven: junit:junit:4.12"
level=
"project"
/>
<orderEntry
type=
"library"
scope=
"TEST"
name=
"Maven: org.hamcrest:hamcrest-core:1.3"
level=
"project"
/>
<orderEntry
type=
"library"
name=
"Maven: org.apache.httpcomponents:httpclient:4.5.6"
level=
"project"
/>
<orderEntry
type=
"library"
name=
"Maven: org.apache.httpcomponents:httpcore:4.4.10"
level=
"project"
/>
<orderEntry
type=
"library"
name=
"Maven: commons-codec:commons-codec:1.10"
level=
"project"
/>
</component>
</module>
\ No newline at end of file
src/main/java/com/zhiwei/searchhotcrawler/bean/HotSearchType.java
View file @
7546fbb8
package
com
.
zhiwei
.
searchhotcrawler
.
bean
;
public
enum
HotSearchType
{
百度热搜
,
微博热搜
,
知乎热搜
,
抖音热搜
,
搜狗微信热搜
,
搜狗微信客户端热搜
,
微博话题
,
今日头条热搜
,
知乎热搜榜单
,
腾讯新闻
,
新浪热榜
,
新浪热点
,
搜狐话题
,
凤凰新闻热榜
,
凤凰新闻热搜
,
网易热榜
,
网易跟帖热议
,
微博预热榜
,
腾讯较真榜
,
脉脉热榜
,
B
站排行榜
,
B
站热搜
,
人气榜
36
氪
,
虎嗅热文推荐
,
快手热榜
,
百度热搜
,
微博热搜
,
知乎热搜
,
抖音热搜
,
搜狗微信热搜
,
搜狗微信客户端热搜
,
微博话题
,
今日头条热搜
,
知乎热搜榜单
,
腾讯新闻
,
新浪热榜
,
新浪热点
,
搜狐话题
,
凤凰新闻热榜
,
凤凰新闻热搜
,
网易热榜
,
网易跟帖热议
,
微博预热榜
,
腾讯较真榜
,
脉脉热榜
,
B
站排行榜
,
B
站热搜
,
人气榜
36
氪
,
虎嗅热文推荐
,
快手热榜
,
淘宝热搜
,
}
src/main/java/com/zhiwei/searchhotcrawler/bean/WeiBoUser.java
View file @
7546fbb8
...
...
@@ -53,6 +53,11 @@ public class WeiBoUser implements Serializable {
* 头像地址
*/
private
String
profileImageUrl
;
/**
* 类型
*/
private
String
type
;
public
WeiBoUser
()
{
}
...
...
@@ -66,6 +71,11 @@ public class WeiBoUser implements Serializable {
this
.
time
=
time
;
this
.
followerCount
=
followerCount
;
this
.
profileImageUrl
=
profileImageUrl
;
}
public
WeiBoUser
(
String
userId
,
String
userName
,
String
topic
,
Date
time
)
{
this
.
userId
=
userId
;
this
.
userName
=
userName
;
this
.
topic
=
topic
;
this
.
time
=
time
;
}
}
src/main/java/com/zhiwei/searchhotcrawler/crawler/BaiDuHotSearchCrawler.java
View file @
7546fbb8
...
...
@@ -14,8 +14,6 @@ import org.jsoup.Jsoup;
import
org.jsoup.nodes.Document
;
import
org.jsoup.nodes.Element
;
import
org.jsoup.select.Elements
;
import
org.slf4j.Logger
;
import
org.slf4j.LoggerFactory
;
import
com.zhiwei.crawler.core.HttpBoot
;
import
com.zhiwei.searchhotcrawler.bean.HotSearchList
;
...
...
src/main/java/com/zhiwei/searchhotcrawler/crawler/MaiMaiHotSearchCrawler.java
View file @
7546fbb8
...
...
@@ -45,7 +45,10 @@ public class MaiMaiHotSearchCrawler {
JSONObject
jsonObject
=
jsonArray
.
getJSONObject
(
i
).
getJSONObject
(
"style35"
);
if
(
jsonObject
!=
null
)
{
String
name
=
jsonObject
.
getString
(
"text"
);
log
.
info
(
name
);
if
(
name
.
length
()>
750
){
name
=
name
.
substring
(
0
,
750
);
}
// log.info(name);
String
maimaiUrl
=
jsonObject
.
getString
(
"share_url"
);
String
icon
=
null
;
if
(
jsonObject
.
containsKey
(
"hot_type_card"
))
{
...
...
src/main/java/com/zhiwei/searchhotcrawler/crawler/WeiboHotSearchCrawler.java
View file @
7546fbb8
package
com
.
zhiwei
.
searchhotcrawler
.
crawler
;
import
java.io.IOException
;
import
java.io.UnsupportedEncodingException
;
import
java.net.URLEncoder
;
import
java.text.ParseException
;
import
java.text.SimpleDateFormat
;
import
java.util.*
;
import
java.util.stream.Collectors
;
import
com.alibaba.fastjson.JSON
;
import
com.mongodb.client.result.UpdateResult
;
import
com.zhiwei.searchhotcrawler.bean.*
;
import
com.zhiwei.searchhotcrawler.config.RedisConfig
;
import
com.zhiwei.searchhotcrawler.dao.RedisDao
;
...
...
@@ -17,6 +20,12 @@ import lombok.extern.log4j.Log4j2;
import
okhttp3.Request
;
import
okhttp3.Response
;
import
org.apache.commons.lang3.StringUtils
;
import
org.apache.http.HttpEntity
;
import
org.apache.http.client.methods.CloseableHttpResponse
;
import
org.apache.http.client.methods.HttpGet
;
import
org.apache.http.impl.client.CloseableHttpClient
;
import
org.apache.http.impl.client.HttpClients
;
import
org.apache.http.util.EntityUtils
;
import
org.bson.Document
;
import
org.checkerframework.checker.units.qual.C
;
import
org.jsoup.Jsoup
;
...
...
@@ -37,6 +46,7 @@ import org.springframework.beans.factory.annotation.Autowired;
import
static
java
.
util
.
Objects
.
nonNull
;
/**
* @author hero
* @ClassName: WeiboHotSearch
* @Description: 微博实时热搜采集
* @author hero
...
...
@@ -113,444 +123,553 @@ public class WeiboHotSearchCrawler {
// }
/**
* @Title: weiboHotSearchByPhoneTest
* @author hero
* @Description: TODO(手机端Iphone 微博热搜采集)
* @return void 返回类型
*/
public
static
List
<
HotSearchList
>
weiboHotSearchByPhone
(
Date
date
){
String
url
=
"https://m.weibo.cn/api/container/getIndex?containerid=106003type%3D25%26t%3D3%26disable_hot%3D1%26filter_type%3Drealtimehot&title=%E5%BE%AE%E5%8D%9A%E7%83%AD%E6%90%9C&extparam=pos%3D0_0%26mi_cid%3D100103%26cate%3D10103%26filter_type%3Drealtimehot%26c_type%3D30&luicode=10000011&lfid=231583"
;
Map
<
String
,
String
>
headerMap
=
new
HashMap
<>();
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
);
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
,
headerMap
);
for
(
int
count
=
0
;
count
<=
5
;
count
++){
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博时热搜时出现连接失败"
,
e
);
}
List
<
HotSearchList
>
result
=
new
ArrayList
<
HotSearchList
>();
if
(
StringUtils
.
isNotBlank
(
htmlBody
)
&&
htmlBody
.
contains
(
"cards"
))
{
try
{
JSONObject
json
=
JSONObject
.
parseObject
(
htmlBody
).
getJSONObject
(
"data"
);
JSONArray
cards
=
json
.
getJSONArray
(
"cards"
);
int
rank
=
0
;
/**
* @return void 返回类型
* @Title: weiboHotSearchByPhoneTest
* @author hero
* @Description: TODO(手机端Iphone 微博热搜采集)
*/
public
static
List
<
HotSearchList
>
weiboHotSearchByPhone
(
Date
date
)
{
String
url
=
"https://m.weibo.cn/api/container/getIndex?containerid=106003type%3D25%26t%3D3%26disable_hot%3D1%26filter_type%3Drealtimehot&title=%E5%BE%AE%E5%8D%9A%E7%83%AD%E6%90%9C&extparam=pos%3D0_0%26mi_cid%3D100103%26cate%3D10103%26filter_type%3Drealtimehot%26c_type%3D30&luicode=10000011&lfid=231583"
;
Map
<
String
,
String
>
headerMap
=
new
HashMap
<>();
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
);
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
,
headerMap
);
for
(
int
count
=
0
;
count
<=
5
;
count
++)
{
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博时热搜时出现连接失败"
,
e
);
}
List
<
HotSearchList
>
result
=
new
ArrayList
<
HotSearchList
>();
if
(
StringUtils
.
isNotBlank
(
htmlBody
)
&&
htmlBody
.
contains
(
"cards"
))
{
try
{
JSONObject
json
=
JSONObject
.
parseObject
(
htmlBody
).
getJSONObject
(
"data"
);
JSONArray
cards
=
json
.
getJSONArray
(
"cards"
);
int
rank
=
0
;
// for (int i = 0; i < cards.size(); i++) {
try
{
JSONObject
card
=
cards
.
getJSONObject
(
0
);
JSONArray
cardGroup
=
card
.
getJSONArray
(
"card_group"
);
JSONObject
topCard
=
cardGroup
.
getJSONObject
(
0
);
if
(!
topCard
.
containsKey
(
"pic"
))
{
rank
=
1
;
}
if
(
Objects
.
nonNull
(
cardGroup
)
&&
!
cardGroup
.
isEmpty
())
{
try
{
JSONObject
card
=
cards
.
getJSONObject
(
0
);
JSONArray
cardGroup
=
card
.
getJSONArray
(
"card_group"
);
JSONObject
topCard
=
cardGroup
.
getJSONObject
(
0
);
if
(!
topCard
.
containsKey
(
"pic"
))
{
rank
=
1
;
}
if
(
Objects
.
nonNull
(
cardGroup
)
&&
!
cardGroup
.
isEmpty
())
{
// String title = card.getString("title");
boolean
hot
=
true
;
boolean
hot
=
true
;
// if (Objects.nonNull(title) && title.contains("实时上升热点")) {
// hot = false;
// rank = 51;
// }
for
(
int
j
=
0
;
j
<
cardGroup
.
size
();
j
++)
{
JSONObject
cardInfo
=
cardGroup
.
getJSONObject
(
j
);
String
name
=
cardInfo
.
getString
(
"desc"
);
long
hotCount
=
cardInfo
.
getLongValue
(
"desc_extr"
);
String
icon
=
cardInfo
.
getString
(
"icon"
);
if
(
StringUtils
.
isNotBlank
(
icon
))
{
icon
=
icon
.
split
(
"_"
)[
1
].
split
(
".png"
)[
0
];
}
String
rankPic
=
cardInfo
.
getString
(
"pic"
);
for
(
int
j
=
0
;
j
<
cardGroup
.
size
();
j
++)
{
JSONObject
cardInfo
=
cardGroup
.
getJSONObject
(
j
);
String
name
=
cardInfo
.
getString
(
"desc"
);
long
hotCount
=
cardInfo
.
getLongValue
(
"desc_extr"
);
String
icon
=
cardInfo
.
getString
(
"icon"
);
if
(
StringUtils
.
isNotBlank
(
icon
))
{
icon
=
icon
.
split
(
"_"
)[
1
].
split
(
".png"
)[
0
];
}
// String id = "http://s.weibo.com/weibo/" + URLCodeUtil.getURLEncode(name, "utf-8") + "&Refer=top";
String
urlScheme
=
cardInfo
.
getString
(
"scheme"
);
HotSearchList
hotSearch
=
new
HotSearchList
(
urlScheme
,
name
,
hotCount
,
hot
,
rank
,
HotSearchType
.
微博热搜
.
name
(),
icon
,
date
);
hotSearch
.
setRankPic
(
rankPic
);
result
.
add
(
hotSearch
);
rank
++;
redisDao
.
addDataToSet
(
RedisConfig
.
WEIBO_HOTSEARCHIDS
,
name
+
"_微博热搜"
);
}
}
else
{
log
.
info
(
"card 数据结构为:{}"
,
card
);
}
}
catch
(
Exception
e
)
{
log
.
error
(
"解析微博时热搜时出现解析错误"
,
e
);
continue
;
}
String
id
=
cardInfo
.
getString
(
"scheme"
);
HotSearchList
hotSearch
=
new
HotSearchList
(
id
,
name
,
hotCount
,
hot
,
rank
,
HotSearchType
.
微博热搜
.
name
(),
icon
,
date
);
result
.
add
(
hotSearch
);
rank
++;
redisDao
.
addDataToSet
(
RedisConfig
.
WEIBO_HOTSEARCHIDS
,
name
+
"_微博热搜"
);
}
}
else
{
log
.
info
(
"card 数据结构为:{}"
,
card
);
}
}
catch
(
Exception
e
)
{
log
.
error
(
"解析微博时热搜时出现解析错误"
,
e
);
continue
;
}
// }
return
result
;
}
catch
(
Exception
e
)
{
log
.
error
(
"解析微博时热搜时出现解析错误,数据不是json结构"
,
e
);
}
}
else
{
log
.
info
(
"解析微博时热搜时出现解析错误,页面结构有问题"
);
}
}
return
Collections
.
emptyList
();
}
/**
* 微博预热榜(实时上升热点采集)
* @param date
* @return
*/
public
static
List
<
HotSearchList
>
weiboPreheatSearch
(
Date
date
){
String
url
=
"https://api.weibo.cn/2/guest/page?c=android&s=3d477777&from=10A8395010&gsid=_2AkMoFNQvf8NhqwJRm_gWy2rkbo1_yA7EieKeSCX0JRM3HRl-wT9kqkIltRV6A-gElEGNj31RgrfclQ31YPAf7UBZPBx2&containerid=106003type%3D25%26t%3D3%26disable_hot%3D1%26filter_type%3Drealtimehot"
;
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
);
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博热搜时出现连接失败"
,
e
);
}
List
<
HotSearchList
>
result
=
new
ArrayList
<>();
if
(
StringUtils
.
isNotBlank
(
htmlBody
)
&&
htmlBody
.
contains
(
"cards"
)){
JSONArray
cardArray
=
JSON
.
parseObject
(
htmlBody
).
getJSONArray
(
"cards"
);
if
(
cardArray
.
size
()
>
1
)
{
JSONObject
jsonObject
=
cardArray
.
getJSONObject
(
1
);
if
(
"实时上升热点"
.
equals
(
jsonObject
.
getString
(
"title"
))
&&
jsonObject
.
containsKey
(
"card_group"
))
{
JSONArray
jsonArray
=
jsonObject
.
getJSONArray
(
"card_group"
);
for
(
int
i
=
0
;
i
<
jsonArray
.
size
();
i
++){
JSONObject
cardInfo
=
jsonArray
.
getJSONObject
(
i
);
String
name
=
cardInfo
.
getString
(
"desc"
);
long
hotCount
=
cardInfo
.
getIntValue
(
"desc_extr"
);
String
weiboUrl
=
"http://s.weibo.com/weibo/"
+
URLCodeUtil
.
getURLEncode
(
name
,
"utf-8"
)
+
"&Refer=top"
;
HotSearchList
hotSearchList
=
new
HotSearchList
(
weiboUrl
,
name
,
hotCount
,
null
,
HotSearchType
.
微博预热榜
.
name
(),
date
);
result
.
add
(
hotSearchList
);
}
//根据热度排序,赋值排名
result
=
result
.
stream
().
sorted
(
Comparator
.
comparing
(
HotSearchList:
:
getCount
).
reversed
()).
collect
(
Collectors
.
toList
());
int
rank
=
1
;
for
(
HotSearchList
hotSearchList
:
result
){
hotSearchList
.
setRank
(
rank
);
rank
++;
}
}
}
}
return
result
;
}
/**
* 微博热搜数据更新导语,阅读量,讨论量
* @param document
* @return
*/
public
static
Document
weiboUpdate
(
Document
document
)
{
log
.
info
(
"更新微博热搜{}导语阅读量和讨论量"
,
document
.
getString
(
"name"
));
String
url
=
"https://m.weibo.cn/api/container/getIndex?"
+
document
.
getString
(
"url"
).
substring
(
document
.
getString
(
"url"
).
indexOf
(
"?"
)+
1
,
document
.
getString
(
"url"
).
indexOf
(
"&"
));
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
);
for
(
int
count
=
0
;
count
<=
5
;
count
++)
{
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博热搜详情页面时出现连接失败"
,
e
);
}
if
(
htmlBody
!=
null
&&
htmlBody
.
contains
(
"data"
))
{
JSONObject
json
=
JSONObject
.
parseObject
(
htmlBody
).
getJSONObject
(
"data"
).
getJSONObject
(
"cardlistInfo"
);
List
<
JSONObject
>
cardsJsons
=
(
List
<
JSONObject
>)
JSONObject
.
parseObject
(
htmlBody
).
getJSONObject
(
"data"
).
get
(
"cards"
);
if
(
json
.
containsKey
(
"desc"
)){
String
topicLead
=
json
.
getString
(
"desc"
);
if
(!
""
.
equals
(
topicLead
))
{
document
.
put
(
"topicLead"
,
topicLead
);
}
}
if
(
json
.
containsKey
(
"cardlist_head_cards"
)){
JSONObject
readJson
=
json
.
getJSONArray
(
"cardlist_head_cards"
).
getJSONObject
(
0
);
if
(
readJson
.
containsKey
(
"head_data"
))
{
String
midText
=
readJson
.
getJSONObject
(
"head_data"
).
getString
(
"midtext"
);
String
read
=
midText
.
replaceAll
(
"阅读"
,
""
).
replaceAll
(
"讨论.*"
,
""
).
trim
();
String
discussCount
=
midText
.
replaceAll
(
".*讨论"
,
""
).
replaceAll
(
"详情.*"
,
""
).
trim
();
String
pictureUrl
=
readJson
.
getJSONObject
(
"head_data"
).
getString
(
"portrait_url"
);
document
.
put
(
"readCount"
,
TipsUtils
.
getHotCount
(
read
));
document
.
put
(
"discussCount"
,
TipsUtils
.
getHotCount
(
discussCount
));
document
.
put
(
"pictureUrl"
,
pictureUrl
);
if
(
readJson
.
getJSONObject
(
"head_data"
).
containsKey
(
"downtext"
)){
String
downtext
=
readJson
.
getJSONObject
(
"head_data"
).
getString
(
"downtext"
);
if
(!
""
.
equals
(
downtext
))
{
document
.
put
(
"downtext"
,
downtext
.
replaceAll
(
"主持人:"
,
""
));
}
}
}
}
try
{
//解析cards,获取热门微博、人物
if
(
Objects
.
isNull
(
weiBoMassageDao
)){
weiBoMassageDao
=
new
WeiBoMassageDao
();
}
if
(
Objects
.
isNull
(
weiBoUserDao
)){
weiBoUserDao
=
new
WeiBoUserDao
();
}
for
(
JSONObject
jsonObject
:
cardsJsons
)
{
if
(
nonNull
(
jsonObject
)
&&
!
jsonObject
.
isEmpty
())
{
if
(
jsonObject
.
containsKey
(
"mblog"
))
{
if
(
jsonObject
.
getJSONObject
(
"mblog"
).
containsKey
(
"title"
))
{
WeiBoMassage
weiBoMassage
=
analysisWeiboMBlog
(
jsonObject
,
document
.
getString
(
"name"
));
if
(
Objects
.
nonNull
(
weiBoMassage
))
{
weiBoMassageDao
.
addWeiBoMassage
(
weiBoMassage
);
}
}
}
else
if
(
jsonObject
.
containsKey
(
"card_group"
))
{
JSONArray
cardGroup
=
jsonObject
.
getJSONArray
(
"card_group"
);
WeiBoMassage
weiBoMassage
=
analysisWeiboMassage
(
cardGroup
,
document
.
getString
(
"name"
));
if
(
Objects
.
nonNull
(
weiBoMassage
))
{
weiBoMassageDao
.
addWeiBoMassage
(
weiBoMassage
);
}
List
<
WeiBoUser
>
weiBoUserList
=
analysisWeiBoUsers
(
cardGroup
,
document
.
getString
(
"name"
));
if
(!
weiBoUserList
.
isEmpty
()){
for
(
int
i
=
0
;
i
<
weiBoUserList
.
size
();
i
++)
{
weiBoUserDao
.
addWeiBoUser
(
weiBoUserList
.
get
(
i
));
}
}
}
}
}
}
catch
(
Exception
e
)
{
log
.
error
(
"解析cards失败,未获得热门微博,人物信息"
,
e
);
}
return
document
;
}
}
return
null
;
}
/**
* 解析微博信息
*
* @param cardGroup
* @param topic
* @return
*/
public
static
WeiBoMassage
analysisWeiboMassage
(
JSONArray
cardGroup
,
String
topic
)
{
for
(
int
i
=
0
;
i
<
cardGroup
.
size
();
i
++)
{
if
(
cardGroup
.
getJSONObject
(
i
).
containsKey
(
"mblog"
))
{
if
(
cardGroup
.
getJSONObject
(
i
).
getJSONObject
(
"mblog"
).
containsKey
(
"title"
))
{
WeiBoMassage
weiBoMassage
=
analysisWeiboMBlog
(
cardGroup
.
getJSONObject
(
i
),
topic
);
return
weiBoMassage
;
}
}
}
return
null
;
}
/**
* 解析用户信息
*
* @param cardGroup
* @param topic
* @return
*/
public
static
List
<
WeiBoUser
>
analysisWeiBoUsers
(
JSONArray
cardGroup
,
String
topic
)
{
List
<
WeiBoUser
>
weiBoUserList
=
new
ArrayList
();
//解析weibo人物信息
Date
date
=
new
Date
();
for
(
int
i
=
0
;
i
<
cardGroup
.
size
();
i
++)
{
if
(
3
==
Integer
.
valueOf
(
cardGroup
.
getJSONObject
(
i
).
getString
(
"card_type"
)))
{
if
(
cardGroup
.
getJSONObject
(
i
).
containsKey
(
"users"
)){
JSONArray
users
=
cardGroup
.
getJSONObject
(
i
).
getJSONArray
(
"users"
);
for
(
int
i1
=
0
;
i1
<
users
.
size
();
i1
++)
{
//获取用户id
String
userId
=
users
.
getJSONObject
(
i1
).
getString
(
"id"
);
//获取用户名
String
userName
=
users
.
getJSONObject
(
i1
).
getString
(
"screen_name"
);
//获取认证信息
String
attestationMassage
=
users
.
getJSONObject
(
i1
).
getString
(
"verified_reason"
);
//获取粉丝数量
String
followers_count
=
users
.
getJSONObject
(
i1
).
getString
(
"followers_count"
);
Long
followerCount
=
null
;
if
(!
followers_count
.
contains
(
"万"
)){
followerCount
=
Long
.
valueOf
(
followers_count
);
}
else
{
String
[]
split
=
followers_count
.
split
(
"万"
);
followerCount
=
Long
.
valueOf
(
split
[
0
])*
10000
;
}
//用户头像地址
String
profileImageUrl
=
users
.
getJSONObject
(
i1
).
getString
(
"profile_image_url"
);
WeiBoUser
weiBoUser
=
new
WeiBoUser
(
userId
,
attestationMassage
,
userName
,
topic
,
date
,
followerCount
,
profileImageUrl
);
weiBoUserList
.
add
(
weiBoUser
);
}
}
return
weiBoUserList
;
}
else
if
(
10
==
Integer
.
valueOf
(
cardGroup
.
getJSONObject
(
i
).
getString
(
"card_type"
)))
{
if
(
cardGroup
.
getJSONObject
(
i
).
containsKey
(
"user"
)){
JSONObject
user
=
cardGroup
.
getJSONObject
(
i
).
getJSONObject
(
"user"
);
//获取用户id
String
userId
=
user
.
getString
(
"id"
);
//获取用户名
String
userName
=
user
.
getString
(
"screen_name"
);
//获取认证信息
String
attestationMassage
=
user
.
getString
(
"verified_reason"
);
//获取粉丝数
String
followers_count
=
user
.
getString
(
"followers_count"
);
Long
followerCount
=
null
;
if
(
followers_count
.
contains
(
"万"
)){
String
[]
split
=
followers_count
.
split
(
"万"
);
followerCount
=
Long
.
valueOf
(
split
[
0
])*
10000
;
}
else
{
followerCount
=
Long
.
valueOf
(
followers_count
);
}
//用户头像地址
String
profileImageUrl
=
user
.
getString
(
"profile_image_url"
);
WeiBoUser
weiBoUser
=
new
WeiBoUser
(
userId
,
attestationMassage
,
userName
,
topic
,
date
,
followerCount
,
profileImageUrl
);
weiBoUserList
.
add
(
weiBoUser
);
}
return
weiBoUserList
;
}
}
return
Collections
.
emptyList
();
}
/**
* 解析微博类型
*
* @param jsonObject
* @param topic
* @return
*/
public
static
WeiBoMassage
analysisWeiboMBlog
(
JSONObject
jsonObject
,
String
topic
)
{
JSONObject
mblog
=
jsonObject
.
getJSONObject
(
"mblog"
);
String
type
=
mblog
.
getJSONObject
(
"title"
).
getString
(
"text"
);
String
card_type
=
jsonObject
.
getString
(
"card_type"
);
Integer
cardType
=
Integer
.
valueOf
(
card_type
);
String
show_type
=
jsonObject
.
getString
(
"show_type"
);
Integer
showType
=
Integer
.
valueOf
(
show_type
);
//点赞数
String
attitudes_count
=
mblog
.
getString
(
"attitudes_count"
);
Long
attitudeCount
=
null
;
if
(
attitudes_count
.
contains
(
"万"
))
{
String
[]
split
=
attitudes_count
.
split
(
"万"
);
attitudeCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
attitudeCount
=
Long
.
valueOf
(
attitudes_count
);
}
//评论数
String
comments_count
=
mblog
.
getString
(
"comments_count"
);
Long
commentCount
=
null
;
if
(
comments_count
.
contains
(
"万"
))
{
String
[]
split
=
comments_count
.
split
(
"万"
);
commentCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
commentCount
=
Long
.
valueOf
(
comments_count
);
}
//转发数
String
reposts_count
=
mblog
.
getString
(
"reposts_count"
);
Long
repostCount
=
null
;
if
(
reposts_count
.
contains
(
"万"
)){
String
[]
split
=
reposts_count
.
split
(
"万"
);
repostCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
repostCount
=
Long
.
valueOf
(
reposts_count
);
}
Date
createTime
=
null
;
Date
editTime
=
null
;
try
{
SimpleDateFormat
simpleDateFormat
=
new
SimpleDateFormat
(
"EEE MMM dd HH:mm:ss z yyyy"
,
java
.
util
.
Locale
.
US
);
//创建时间
String
created_at
=
mblog
.
getString
(
"created_at"
);
createTime
=
simpleDateFormat
.
parse
(
created_at
);
//编辑时间
if
(
mblog
.
containsKey
(
"edit_at"
)){
String
edit_at
=
mblog
.
getString
(
"edit_at"
);
editTime
=
simpleDateFormat
.
parse
(
edit_at
);
}
}
catch
(
ParseException
e
)
{
log
.
error
(
"创建时间和编辑时间解析异常"
,
e
);
}
String
mid
=
mblog
.
getString
(
"mid"
);
//用户id
String
userId
=
mblog
.
getJSONObject
(
"user"
).
getString
(
"id"
);
//用户名
String
userName
=
mblog
.
getJSONObject
(
"user"
).
getString
(
"screen_name"
);
//来源
String
source
=
mblog
.
getString
(
"source"
);
//用户头像地址
String
profileImageUrl
=
mblog
.
getJSONObject
(
"user"
).
getString
(
"profile_image_url"
);
//内容
String
content
=
null
;
if
(
mblog
.
getString
(
"text"
).
contains
(
"<"
))
{
String
text
=
mblog
.
getString
(
"text"
);
org
.
jsoup
.
nodes
.
Document
parse
=
Jsoup
.
parse
(
text
);
content
=
parse
.
text
();
}
else
{
content
=
mblog
.
getString
(
"text"
);
}
WeiBoMassage
weiBoMassage
=
new
WeiBoMassage
(
userId
,
content
,
userName
,
mid
,
createTime
,
editTime
,
cardType
,
showType
,
repostCount
,
commentCount
,
attitudeCount
,
source
,
type
,
topic
,
profileImageUrl
);
//默认不转发为0
weiBoMassage
.
setForward
(
0
);
JSONObject
weiboJson
=
null
;
//微博实体 是否转发
if
(
mblog
.
containsKey
(
"retweeted_status"
))
{
weiboJson
=
mblog
.
getJSONObject
(
"retweeted_status"
);
//处理转发特有的
//weiBoMassage.set
//源mid
String
rootMid
=
weiboJson
.
getString
(
"mid"
);
//源来源
String
rootSource
=
weiboJson
.
getString
(
"source"
);
//源text
String
text
=
weiboJson
.
getString
(
"text"
);
//解析
org
.
jsoup
.
nodes
.
Document
parse
=
Jsoup
.
parse
(
text
);
String
rootText
=
parse
.
text
();
//源用户id
String
rootId
=
weiboJson
.
getJSONObject
(
"user"
).
getString
(
"id"
);
//源用户名
String
rootName
=
weiboJson
.
getJSONObject
(
"user"
).
getString
(
"screen_name"
);
//数据保存到对象中
weiBoMassage
.
setRoot_mid
(
rootMid
);
weiBoMassage
.
setRoot_id
(
rootId
);
weiBoMassage
.
setRoot_source
(
rootSource
);
weiBoMassage
.
setRoot_text
(
rootText
);
weiBoMassage
.
setRoot_name
(
rootName
);
//转发为1
weiBoMassage
.
setForward
(
1
);
}
else
{
weiboJson
=
mblog
;
}
List
<
String
>
pictureUrlList
=
new
ArrayList
();
Long
playCount
=
null
;
//获取播放量和图片链接
if
(
weiboJson
.
getJSONArray
(
"pic_ids"
).
size
()
>
0
)
{
JSONArray
jsonArray
=
weiboJson
.
getJSONArray
(
"pics"
);
for
(
int
i
=
0
;
i
<
jsonArray
.
size
();
i
++)
{
String
picUrl
=
jsonArray
.
getJSONObject
(
i
).
getString
(
"url"
);
pictureUrlList
.
add
(
picUrl
);
}
}
else
if
(
weiboJson
.
containsKey
(
"page_info"
))
{
if
(
weiboJson
.
getJSONObject
(
"page_info"
).
containsKey
(
"play_count"
)){
String
play
=
weiboJson
.
getJSONObject
(
"page_info"
).
getString
(
"play_count"
);
if
(
play
.
contains
(
"万"
))
{
String
[]
split
=
play
.
split
(
"万"
);
playCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
if
(
play
.
contains
(
"次"
)){
String
[]
split
=
play
.
split
(
"次"
);
playCount
=
Long
.
valueOf
(
split
[
0
]);
}
}
}
weiBoMassage
.
setPlayCount
(
playCount
);
weiBoMassage
.
setPictureUrlList
(
pictureUrlList
);
return
weiBoMassage
;
}
return
result
;
}
catch
(
Exception
e
)
{
log
.
error
(
"解析微博时热搜时出现解析错误,数据不是json结构"
,
e
);
}
}
else
{
log
.
info
(
"解析微博时热搜时出现解析错误,页面结构有问题"
);
}
}
return
Collections
.
emptyList
();
}
/**
* 微博预热榜(实时上升热点采集)
*
* @param date
* @return
*/
public
static
List
<
HotSearchList
>
weiboPreheatSearch
(
Date
date
)
{
String
url
=
"https://api.weibo.cn/2/guest/page?c=android&s=3d477777&from=10A8395010&gsid=_2AkMoFNQvf8NhqwJRm_gWy2rkbo1_yA7EieKeSCX0JRM3HRl-wT9kqkIltRV6A-gElEGNj31RgrfclQ31YPAf7UBZPBx2&containerid=106003type%3D25%26t%3D3%26disable_hot%3D1%26filter_type%3Drealtimehot"
;
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
);
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博热搜时出现连接失败"
,
e
);
}
List
<
HotSearchList
>
result
=
new
ArrayList
<>();
if
(
StringUtils
.
isNotBlank
(
htmlBody
)
&&
htmlBody
.
contains
(
"cards"
))
{
JSONArray
cardArray
=
JSON
.
parseObject
(
htmlBody
).
getJSONArray
(
"cards"
);
if
(
cardArray
.
size
()
>
1
)
{
JSONObject
jsonObject
=
cardArray
.
getJSONObject
(
1
);
if
(
"实时上升热点"
.
equals
(
jsonObject
.
getString
(
"title"
))
&&
jsonObject
.
containsKey
(
"card_group"
))
{
JSONArray
jsonArray
=
jsonObject
.
getJSONArray
(
"card_group"
);
for
(
int
i
=
0
;
i
<
jsonArray
.
size
();
i
++)
{
JSONObject
cardInfo
=
jsonArray
.
getJSONObject
(
i
);
String
name
=
cardInfo
.
getString
(
"desc"
);
long
hotCount
=
cardInfo
.
getIntValue
(
"desc_extr"
);
String
weiboUrl
=
"http://s.weibo.com/weibo/"
+
URLCodeUtil
.
getURLEncode
(
name
,
"utf-8"
)
+
"&Refer=top"
;
HotSearchList
hotSearchList
=
new
HotSearchList
(
weiboUrl
,
name
,
hotCount
,
null
,
HotSearchType
.
微博预热榜
.
name
(),
date
);
result
.
add
(
hotSearchList
);
}
//根据热度排序,赋值排名
result
=
result
.
stream
().
sorted
(
Comparator
.
comparing
(
HotSearchList:
:
getCount
).
reversed
()).
collect
(
Collectors
.
toList
());
int
rank
=
1
;
for
(
HotSearchList
hotSearchList
:
result
)
{
hotSearchList
.
setRank
(
rank
);
rank
++;
}
}
}
}
return
result
;
}
/**
* 微博热搜数据更新导语,阅读量,讨论量
*
* @param document
* @return
*/
public
static
Document
weiboUpdate
(
Document
document
)
{
log
.
info
(
"更新微博热搜{}导语阅读量和讨论量"
,
document
.
getString
(
"name"
));
String
url
=
"https://m.weibo.cn/api/container/getIndex?"
+
document
.
getString
(
"url"
).
substring
(
document
.
getString
(
"url"
).
indexOf
(
"?"
)
+
1
,
document
.
getString
(
"url"
).
indexOf
(
"&"
));
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
);
for
(
int
count
=
0
;
count
<=
5
;
count
++)
{
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博热搜详情页面时出现连接失败"
,
e
);
}
if
(
htmlBody
!=
null
&&
htmlBody
.
contains
(
"data"
))
{
JSONObject
json
=
JSONObject
.
parseObject
(
htmlBody
).
getJSONObject
(
"data"
).
getJSONObject
(
"cardlistInfo"
);
List
<
JSONObject
>
cardsJsons
=
(
List
<
JSONObject
>)
JSONObject
.
parseObject
(
htmlBody
).
getJSONObject
(
"data"
).
get
(
"cards"
);
if
(
json
.
containsKey
(
"desc"
))
{
String
topicLead
=
json
.
getString
(
"desc"
);
if
(!
""
.
equals
(
topicLead
))
{
document
.
put
(
"topicLead"
,
topicLead
);
}
}
if
(
json
.
containsKey
(
"cardlist_head_cards"
))
{
JSONObject
readJson
=
json
.
getJSONArray
(
"cardlist_head_cards"
).
getJSONObject
(
0
);
if
(
readJson
.
containsKey
(
"head_data"
))
{
String
midText
=
readJson
.
getJSONObject
(
"head_data"
).
getString
(
"midtext"
);
String
read
=
midText
.
replaceAll
(
"阅读"
,
""
).
replaceAll
(
"讨论.*"
,
""
).
trim
();
String
discussCount
=
midText
.
replaceAll
(
".*讨论"
,
""
).
replaceAll
(
"详情.*"
,
""
).
trim
();
String
pictureUrl
=
readJson
.
getJSONObject
(
"head_data"
).
getString
(
"portrait_url"
);
document
.
put
(
"readCount"
,
TipsUtils
.
getHotCount
(
read
));
document
.
put
(
"discussCount"
,
TipsUtils
.
getHotCount
(
discussCount
));
document
.
put
(
"pictureUrl"
,
pictureUrl
);
if
(
readJson
.
getJSONObject
(
"head_data"
).
containsKey
(
"downtext"
))
{
String
downtext
=
readJson
.
getJSONObject
(
"head_data"
).
getString
(
"downtext"
);
if
(!
""
.
equals
(
downtext
))
{
document
.
put
(
"downtext"
,
downtext
.
replaceAll
(
"主持人:"
,
""
));
}
}
}
}
try
{
//解析cards,获取热门微博、人物
if
(
Objects
.
isNull
(
weiBoMassageDao
))
{
weiBoMassageDao
=
new
WeiBoMassageDao
();
}
if
(
Objects
.
isNull
(
weiBoUserDao
))
{
weiBoUserDao
=
new
WeiBoUserDao
();
}
for
(
JSONObject
jsonObject
:
cardsJsons
)
{
if
(
nonNull
(
jsonObject
)
&&
!
jsonObject
.
isEmpty
())
{
if
(
jsonObject
.
containsKey
(
"mblog"
))
{
if
(
jsonObject
.
getJSONObject
(
"mblog"
).
containsKey
(
"title"
))
{
WeiBoMassage
weiBoMassage
=
analysisWeiboMBlog
(
jsonObject
,
document
.
getString
(
"name"
));
if
(
Objects
.
nonNull
(
weiBoMassage
))
{
weiBoMassageDao
.
addWeiBoMassage
(
weiBoMassage
);
}
}
}
else
if
(
jsonObject
.
containsKey
(
"card_group"
))
{
JSONArray
cardGroup
=
jsonObject
.
getJSONArray
(
"card_group"
);
WeiBoMassage
weiBoMassage
=
analysisWeiboMassage
(
cardGroup
,
document
.
getString
(
"name"
));
if
(
Objects
.
nonNull
(
weiBoMassage
))
{
weiBoMassageDao
.
addWeiBoMassage
(
weiBoMassage
);
}
List
<
WeiBoUser
>
weiBoUserList
=
analysisWeiBoUsers
(
cardGroup
,
document
.
getString
(
"name"
));
if
(!
weiBoUserList
.
isEmpty
())
{
for
(
int
i
=
0
;
i
<
weiBoUserList
.
size
();
i
++)
{
weiBoUserDao
.
addWeiBoUser
(
weiBoUserList
.
get
(
i
));
}
}
}
}
}
}
catch
(
Exception
e
)
{
log
.
error
(
"解析cards失败,未获得热门微博,人物信息"
,
e
);
}
return
document
;
}
}
return
null
;
}
/**
* 微博热搜数据更新话题贡献者排行,关于
*
* @param document
* @return
*/
public
static
Document
weiboUpdatePC
(
Document
document
)
{
document
.
getString
(
"name"
);
String
topic
=
document
.
getString
(
"name"
);
String
gb
=
"#"
+
topic
+
"#"
;
String
encode
=
null
;
try
{
encode
=
URLEncoder
.
encode
(
gb
,
"utf-8"
);
}
catch
(
UnsupportedEncodingException
e
)
{
log
.
error
(
"字符解析成URl模式异常"
,
e
);
}
String
url
=
"https://s.weibo.com/weibo?q="
+
encode
;
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
);
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
}
catch
(
IOException
e
)
{
log
.
error
(
"解析微博时热搜时出现连接失败"
,
e
);
}
if
(
htmlBody
!=
null
&&
htmlBody
.
contains
(
"m-main"
))
{
Document
docm
=
new
Document
();
try
{
org
.
jsoup
.
nodes
.
Document
documen
=
Jsoup
.
parse
(
htmlBody
);
//获取贡献者信息
try
{
Elements
cardUser
=
documen
.
select
(
"div.card-user"
);
for
(
Element
element
:
cardUser
)
{
if
(!
element
.
select
(
"div.card-head"
).
text
().
isEmpty
())
{
Elements
li
=
element
.
select
(
"ul.card-user-list-a"
).
select
(
"li"
);
if
(
Objects
.
nonNull
(
li
))
{
//循环获取话题贡献者相关信息
for
(
Element
eleme
:
li
)
{
String
type
=
"话题贡献者"
;
writeUser
(
eleme
,
type
,
topic
);
}
}
}
else
{
Elements
li
=
element
.
select
(
"ul.card-user-list-a"
).
select
(
"li"
);
if
(
Objects
.
nonNull
(
li
))
{
//循环获取话题贡献者相关信息
for
(
Element
eleme
:
li
)
{
String
type
=
"当事人"
;
writeUser
(
eleme
,
type
,
topic
);
}
}
}
}
}
catch
(
Exception
e
)
{
log
.
error
(
"话题贡献者排行采集异常"
,
e
);
}
Elements
dt
=
documen
.
select
(
"div.card-about"
).
select
(
"dt"
);
if
(
Objects
.
nonNull
(
dt
))
{
//获取微博关于的相关信息
Elements
dd
=
documen
.
select
(
"div.card-about"
).
select
(
"dd"
);
Document
dtDocument
=
new
Document
();
Document
ddDocument
=
new
Document
();
for
(
int
i
=
0
;
i
<
dt
.
size
();
i
++)
{
String
dtText
=
dt
.
get
(
i
).
text
().
replaceAll
(
":"
,
""
).
trim
();
dtDocument
.
put
(
String
.
valueOf
(
i
),
dtText
);
}
for
(
int
i1
=
0
;
i1
<
dd
.
size
();
i1
++)
{
Elements
a
=
dd
.
get
(
i1
).
select
(
"a"
);
List
<
String
>
str
=
new
ArrayList
<>();
for
(
int
b
=
0
;
b
<
a
.
size
();
b
++)
{
String
text1
=
a
.
get
(
b
).
text
();
str
.
add
(
text1
);
}
ddDocument
.
put
(
String
.
valueOf
(
i1
),
str
);
}
for
(
int
a
=
0
;
a
<
dt
.
size
();
a
++)
{
docm
.
put
(
dtDocument
.
getString
(
String
.
valueOf
(
a
)),
ddDocument
.
get
(
String
.
valueOf
(
a
)));
}
}
return
docm
;
}
catch
(
Exception
e
)
{
log
.
error
(
"解析微博话题时出现解析错误"
,
e
);
}
}
return
document
;
}
/**
* 写入user数据
*
* @param eleme
* @param type
*/
private
static
void
writeUser
(
Element
eleme
,
String
type
,
String
topic
)
{
Date
date
=
new
Date
();
if
(
Objects
.
isNull
(
weiBoUserDao
))
{
weiBoUserDao
=
new
WeiBoUserDao
();
}
//获取用户名
String
userName
=
eleme
.
select
(
"a.name"
).
text
();
String
attr
=
eleme
.
select
(
"span.avator"
).
select
(
"a"
).
first
().
attr
(
"href"
);
//获取用户id
String
userId
=
attr
.
substring
(
14
);
String
id
=
userId
+
"_"
+
type
+
"_"
+
topic
;
WeiBoUser
weiBoUser
=
new
WeiBoUser
(
userName
,
userId
,
topic
,
date
);
weiBoUser
.
setType
(
type
);
weiBoUser
.
setId
(
id
);
weiBoUserDao
.
addWeiBoUser
(
weiBoUser
);
}
/**
* 解析微博信息
*
* @param cardGroup
* @param topic
* @return
*/
public
static
WeiBoMassage
analysisWeiboMassage
(
JSONArray
cardGroup
,
String
topic
)
{
for
(
int
i
=
0
;
i
<
cardGroup
.
size
();
i
++)
{
if
(
cardGroup
.
getJSONObject
(
i
).
containsKey
(
"mblog"
))
{
if
(
cardGroup
.
getJSONObject
(
i
).
getJSONObject
(
"mblog"
).
containsKey
(
"title"
))
{
WeiBoMassage
weiBoMassage
=
analysisWeiboMBlog
(
cardGroup
.
getJSONObject
(
i
),
topic
);
return
weiBoMassage
;
}
}
}
return
null
;
}
/**
* 解析用户信息
*
* @param cardGroup
* @param topic
* @return
*/
public
static
List
<
WeiBoUser
>
analysisWeiBoUsers
(
JSONArray
cardGroup
,
String
topic
)
{
List
<
WeiBoUser
>
weiBoUserList
=
new
ArrayList
();
//解析weibo人物信息
Date
date
=
new
Date
();
for
(
int
i
=
0
;
i
<
cardGroup
.
size
();
i
++)
{
if
(
3
==
Integer
.
valueOf
(
cardGroup
.
getJSONObject
(
i
).
getString
(
"card_type"
)))
{
if
(
cardGroup
.
getJSONObject
(
i
).
containsKey
(
"users"
))
{
JSONArray
users
=
cardGroup
.
getJSONObject
(
i
).
getJSONArray
(
"users"
);
for
(
int
i1
=
0
;
i1
<
users
.
size
();
i1
++)
{
//获取用户id
String
userId
=
users
.
getJSONObject
(
i1
).
getString
(
"id"
);
//获取用户名
String
userName
=
users
.
getJSONObject
(
i1
).
getString
(
"screen_name"
);
//获取认证信息
String
attestationMassage
=
users
.
getJSONObject
(
i1
).
getString
(
"verified_reason"
);
//获取粉丝数量
String
followers_count
=
users
.
getJSONObject
(
i1
).
getString
(
"followers_count"
);
Long
followerCount
=
null
;
if
(!
followers_count
.
contains
(
"万"
))
{
followerCount
=
Long
.
valueOf
(
followers_count
);
}
else
{
String
[]
split
=
followers_count
.
split
(
"万"
);
followerCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
//用户头像地址
String
profileImageUrl
=
users
.
getJSONObject
(
i1
).
getString
(
"profile_image_url"
);
WeiBoUser
weiBoUser
=
new
WeiBoUser
(
userId
,
attestationMassage
,
userName
,
topic
,
date
,
followerCount
,
profileImageUrl
);
weiBoUserList
.
add
(
weiBoUser
);
}
}
return
weiBoUserList
;
}
else
if
(
10
==
Integer
.
valueOf
(
cardGroup
.
getJSONObject
(
i
).
getString
(
"card_type"
)))
{
if
(
cardGroup
.
getJSONObject
(
i
).
containsKey
(
"user"
))
{
JSONObject
user
=
cardGroup
.
getJSONObject
(
i
).
getJSONObject
(
"user"
);
//获取用户id
String
userId
=
user
.
getString
(
"id"
);
//获取用户名
String
userName
=
user
.
getString
(
"screen_name"
);
//获取认证信息
String
attestationMassage
=
user
.
getString
(
"verified_reason"
);
//获取粉丝数
String
followers_count
=
user
.
getString
(
"followers_count"
);
Long
followerCount
=
null
;
if
(
followers_count
.
contains
(
"万"
))
{
String
[]
split
=
followers_count
.
split
(
"万"
);
followerCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
followerCount
=
Long
.
valueOf
(
followers_count
);
}
//用户头像地址
String
profileImageUrl
=
user
.
getString
(
"profile_image_url"
);
WeiBoUser
weiBoUser
=
new
WeiBoUser
(
userId
,
attestationMassage
,
userName
,
topic
,
date
,
followerCount
,
profileImageUrl
);
weiBoUserList
.
add
(
weiBoUser
);
}
return
weiBoUserList
;
}
}
return
Collections
.
emptyList
();
}
/**
* 解析微博类型
*
* @param jsonObject
* @param topic
* @return
*/
public
static
WeiBoMassage
analysisWeiboMBlog
(
JSONObject
jsonObject
,
String
topic
)
{
JSONObject
mblog
=
jsonObject
.
getJSONObject
(
"mblog"
);
String
type
=
mblog
.
getJSONObject
(
"title"
).
getString
(
"text"
);
String
card_type
=
jsonObject
.
getString
(
"card_type"
);
Integer
cardType
=
Integer
.
valueOf
(
card_type
);
String
show_type
=
jsonObject
.
getString
(
"show_type"
);
Integer
showType
=
Integer
.
valueOf
(
show_type
);
//点赞数
String
attitudes_count
=
mblog
.
getString
(
"attitudes_count"
);
Long
attitudeCount
=
null
;
if
(
attitudes_count
.
contains
(
"万"
))
{
String
[]
split
=
attitudes_count
.
split
(
"万"
);
attitudeCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
attitudeCount
=
Long
.
valueOf
(
attitudes_count
);
}
//评论数
String
comments_count
=
mblog
.
getString
(
"comments_count"
);
Long
commentCount
=
null
;
if
(
comments_count
.
contains
(
"万"
))
{
String
[]
split
=
comments_count
.
split
(
"万"
);
commentCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
commentCount
=
Long
.
valueOf
(
comments_count
);
}
//转发数
String
reposts_count
=
mblog
.
getString
(
"reposts_count"
);
Long
repostCount
=
null
;
if
(
reposts_count
.
contains
(
"万"
))
{
String
[]
split
=
reposts_count
.
split
(
"万"
);
repostCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
{
repostCount
=
Long
.
valueOf
(
reposts_count
);
}
Date
createTime
=
null
;
Date
editTime
=
null
;
try
{
SimpleDateFormat
simpleDateFormat
=
new
SimpleDateFormat
(
"EEE MMM dd HH:mm:ss z yyyy"
,
java
.
util
.
Locale
.
US
);
//创建时间
String
created_at
=
mblog
.
getString
(
"created_at"
);
createTime
=
simpleDateFormat
.
parse
(
created_at
);
//编辑时间
if
(
mblog
.
containsKey
(
"edit_at"
))
{
String
edit_at
=
mblog
.
getString
(
"edit_at"
);
editTime
=
simpleDateFormat
.
parse
(
edit_at
);
}
}
catch
(
ParseException
e
)
{
log
.
error
(
"创建时间和编辑时间解析异常"
,
e
);
}
String
mid
=
mblog
.
getString
(
"mid"
);
//用户id
String
userId
=
mblog
.
getJSONObject
(
"user"
).
getString
(
"id"
);
//用户名
String
userName
=
mblog
.
getJSONObject
(
"user"
).
getString
(
"screen_name"
);
//来源
String
source
=
mblog
.
getString
(
"source"
);
//用户头像地址
String
profileImageUrl
=
mblog
.
getJSONObject
(
"user"
).
getString
(
"profile_image_url"
);
//内容
String
content
=
null
;
if
(
mblog
.
getString
(
"text"
).
contains
(
"<"
))
{
String
text
=
mblog
.
getString
(
"text"
);
org
.
jsoup
.
nodes
.
Document
parse
=
Jsoup
.
parse
(
text
);
content
=
parse
.
text
();
}
else
{
content
=
mblog
.
getString
(
"text"
);
}
WeiBoMassage
weiBoMassage
=
new
WeiBoMassage
(
userId
,
content
,
userName
,
mid
,
createTime
,
editTime
,
cardType
,
showType
,
repostCount
,
commentCount
,
attitudeCount
,
source
,
type
,
topic
,
profileImageUrl
);
//默认不转发为0
weiBoMassage
.
setForward
(
0
);
JSONObject
weiboJson
=
null
;
//微博实体 是否转发
if
(
mblog
.
containsKey
(
"retweeted_status"
))
{
weiboJson
=
mblog
.
getJSONObject
(
"retweeted_status"
);
//处理转发特有的
//weiBoMassage.set
//源mid
String
rootMid
=
weiboJson
.
getString
(
"mid"
);
//源来源
String
rootSource
=
weiboJson
.
getString
(
"source"
);
//源text
String
text
=
weiboJson
.
getString
(
"text"
);
//解析
org
.
jsoup
.
nodes
.
Document
parse
=
Jsoup
.
parse
(
text
);
String
rootText
=
parse
.
text
();
//源用户id
String
rootId
=
weiboJson
.
getJSONObject
(
"user"
).
getString
(
"id"
);
//源用户名
String
rootName
=
weiboJson
.
getJSONObject
(
"user"
).
getString
(
"screen_name"
);
//数据保存到对象中
weiBoMassage
.
setRoot_mid
(
rootMid
);
weiBoMassage
.
setRoot_id
(
rootId
);
weiBoMassage
.
setRoot_source
(
rootSource
);
weiBoMassage
.
setRoot_text
(
rootText
);
weiBoMassage
.
setRoot_name
(
rootName
);
//转发为1
weiBoMassage
.
setForward
(
1
);
}
else
{
weiboJson
=
mblog
;
}
List
<
String
>
pictureUrlList
=
new
ArrayList
();
Long
playCount
=
null
;
//获取播放量和图片链接
if
(
weiboJson
.
getJSONArray
(
"pic_ids"
).
size
()
>
0
)
{
JSONArray
jsonArray
=
weiboJson
.
getJSONArray
(
"pics"
);
for
(
int
i
=
0
;
i
<
jsonArray
.
size
();
i
++)
{
String
picUrl
=
jsonArray
.
getJSONObject
(
i
).
getString
(
"url"
);
pictureUrlList
.
add
(
picUrl
);
}
}
else
if
(
weiboJson
.
containsKey
(
"page_info"
))
{
if
(
weiboJson
.
getJSONObject
(
"page_info"
).
containsKey
(
"play_count"
))
{
String
play
=
weiboJson
.
getJSONObject
(
"page_info"
).
getString
(
"play_count"
);
if
(
play
.
contains
(
"万"
))
{
String
[]
split
=
play
.
split
(
"万"
);
playCount
=
Long
.
valueOf
(
split
[
0
])
*
10000
;
}
else
if
(
play
.
contains
(
"次"
))
{
String
[]
split
=
play
.
split
(
"次"
);
playCount
=
Long
.
valueOf
(
split
[
0
]);
}
}
}
weiBoMassage
.
setPlayCount
(
playCount
);
weiBoMassage
.
setPictureUrlList
(
pictureUrlList
);
return
weiBoMassage
;
}
// /**
// * 微博更新历史数据
...
...
src/main/java/com/zhiwei/searchhotcrawler/dao/HotSearchCacheDAO.java
View file @
7546fbb8
...
...
@@ -6,12 +6,14 @@ import com.zhiwei.searchhotcrawler.bean.HotSearchList;
import
com.zhiwei.searchhotcrawler.config.DBConfig
;
import
com.zhiwei.searchhotcrawler.crawler.WeiboHotSearchCrawler
;
import
com.zhiwei.searchhotcrawler.dbtemplate.MongoDBTemplate
;
import
com.zhiwei.searchhotcrawler.util.MD5Util
;
import
lombok.extern.log4j.Log4j2
;
import
org.apache.logging.log4j.util.Strings
;
import
org.bson.Document
;
import
java.util.*
;
import
static
java
.
util
.
Objects
.
isNull
;
import
static
java
.
util
.
Objects
.
nonNull
;
/**
...
...
@@ -97,7 +99,12 @@ public class HotSearchCacheDAO {
String
url
=
document
.
getString
(
"url"
)!=
null
?
document
.
getString
(
"url"
):
null
;
String
topicResult
=
document
.
getString
(
"topic_result"
)!=
null
?
document
.
getString
(
"topic_result"
):
null
;
String
pictureUrl
=
document
.
getString
(
"pictureUrl"
)!=
null
?
document
.
getString
(
"pictureUrl"
):
null
;
String
id
=
name
+
"_"
+
type
;
String
id
=
document
.
getString
(
"_id"
);
if
(
isNull
(
id
)){
id
=
name
+
"_"
+
type
;
}
boolean
recommend
=
false
;
// Integer readCount = document.getInteger("comment_count");
if
(
"微博热搜"
.
equals
(
type
)){
...
...
@@ -208,6 +215,17 @@ public class HotSearchCacheDAO {
}
if
(
"微博热搜"
.
equals
(
type
)){
nowDoc
=
WeiboHotSearchCrawler
.
weiboUpdate
(
nowDoc
);
//更新微博话题贡献者,关于功能
Document
documentPC
=
WeiboHotSearchCrawler
.
weiboUpdatePC
(
nowDoc
);
if
(
documentPC
.
containsKey
(
"分类"
))
{
nowDoc
.
put
(
"classify"
,
documentPC
.
get
(
"分类"
));
}
if
(
documentPC
.
containsKey
(
"地区"
))
{
nowDoc
.
put
(
"region"
,
documentPC
.
get
(
"地区"
));
}
if
(
documentPC
.
containsKey
(
"标签"
))
{
nowDoc
.
put
(
"label"
,
documentPC
.
get
(
"标签"
));
}
if
(
nowDoc
.
containsKey
(
"topicLead"
)){
nowDoc
.
put
(
"topicLead"
,
nowDoc
.
getString
(
"topicLead"
));
}
...
...
src/main/java/com/zhiwei/searchhotcrawler/dao/WeiBoUserDao.java
View file @
7546fbb8
...
...
@@ -42,8 +42,17 @@ public class WeiBoUserDao {
document
.
put
(
"userName"
,
weiBoUser
.
getUserName
());
document
.
put
(
"topic"
,
weiBoUser
.
getTopic
());
document
.
put
(
"time"
,
weiBoUser
.
getTime
());
document
.
put
(
"followerCount"
,
weiBoUser
.
getFollowerCount
());
document
.
put
(
"profileImageUrl"
,
weiBoUser
.
getProfileImageUrl
());
if
(
Objects
.
nonNull
(
weiBoUser
.
getType
())){
document
.
put
(
"type"
,
weiBoUser
.
getType
());
}
if
(
Objects
.
nonNull
(
weiBoUser
.
getFollowerCount
())){
document
.
put
(
"followerCount"
,
weiBoUser
.
getFollowerCount
());
}
if
(
Objects
.
nonNull
(
weiBoUser
.
getProfileImageUrl
())){
document
.
put
(
"profileImageUrl"
,
weiBoUser
.
getProfileImageUrl
());
}
try
{
mongoCollection
.
insertOne
(
document
);
}
catch
(
Exception
e
)
{
...
...
src/main/java/com/zhiwei/searchhotcrawler/run/HotSearchRun.java
View file @
7546fbb8
...
...
@@ -9,6 +9,7 @@ import com.zhiwei.tools.tools.ZhiWeiTools;
import
org.springframework.context.ApplicationContext
;
import
org.springframework.context.support.ClassPathXmlApplicationContext
;
import
java.util.concurrent.Executors
;
import
java.util.concurrent.ScheduledExecutorService
;
import
java.util.concurrent.TimeUnit
;
...
...
src/main/java/com/zhiwei/searchhotcrawler/test/HotSearch36KrCrawlerTest.java
View file @
7546fbb8
...
...
@@ -9,12 +9,6 @@ import lombok.extern.log4j.Log4j2;
import
okhttp3.Request
;
import
okhttp3.Response
;
import
org.apache.commons.lang3.StringUtils
;
import
org.apache.http.HttpEntity
;
import
org.apache.http.client.methods.CloseableHttpResponse
;
import
org.apache.http.client.methods.HttpGet
;
import
org.apache.http.impl.client.CloseableHttpClient
;
import
org.apache.http.impl.client.HttpClients
;
import
org.apache.http.util.EntityUtils
;
import
org.jsoup.Jsoup
;
import
org.jsoup.nodes.Document
;
import
org.jsoup.nodes.Element
;
...
...
src/main/java/com/zhiwei/searchhotcrawler/test/HotSearchRunTest.java
View file @
7546fbb8
...
...
@@ -4,6 +4,9 @@ package com.zhiwei.searchhotcrawler.test;
import
com.zhiwei.crawler.core.proxy.ProxyFactory
;
import
com.zhiwei.proxy.config.SimpleConfig
;
import
com.zhiwei.searchhotcrawler.config.ProxyConfig
;
import
com.zhiwei.searchhotcrawler.timer.BaiduHotSearchRun
;
import
com.zhiwei.searchhotcrawler.timer.WeiboHotSearchRun
;
import
java.text.ParseException
;
public
class
HotSearchRunTest
{
...
...
@@ -17,5 +20,7 @@ public class HotSearchRunTest {
// new WeiboHotSearchRun().start();
//快手热榜开始采集
// new KuaiShouHotSearchRun().start();
//百度热搜
new
BaiduHotSearchRun
().
run
();
}
}
src/main/java/com/zhiwei/searchhotcrawler/test/TaoBaoHotSearchCrawlerTest.java
0 → 100644
View file @
7546fbb8
package
com
.
zhiwei
.
searchhotcrawler
.
test
;
import
com.alibaba.fastjson.JSONArray
;
import
com.alibaba.fastjson.JSONObject
;
import
com.zhiwei.crawler.core.HttpBoot
;
import
com.zhiwei.crawler.core.proxy.ProxyHolder
;
import
com.zhiwei.crawler.core.utils.RequestUtils
;
import
com.zhiwei.searchhotcrawler.bean.HotSearchList
;
import
com.zhiwei.searchhotcrawler.bean.HotSearchType
;
import
com.zhiwei.searchhotcrawler.util.TaoBaoUtils
;
import
lombok.extern.log4j.Log4j2
;
import
okhttp3.Request
;
import
okhttp3.Response
;
import
java.io.IOException
;
import
java.time.Duration
;
import
java.util.*
;
/**
* @author ll
* @ClassName:TaoBaoHotSearchCrawler
* @Description:
* @date 2021年6月18日 下午16:33:31
*/
@Log4j2
public
class
TaoBaoHotSearchCrawlerTest
{
private
static
HttpBoot
httpBoot
=
new
HttpBoot
.
Builder
().
throwException
(
false
).
retryTimes
(
3
).
connectTimeout
(
Duration
.
ofSeconds
(
60
)).
build
();
public
static
List
<
HotSearchList
>
taoBaoHotSearch
(
Date
date
)
{
long
time
=
new
Date
().
getTime
();
String
signs
=
"undefined&"
+
time
+
"&12574478&{\"appId\":\"10211\",\"params\":\"{\\\"multi_hintq_show\\\":\\\"on\\\",\\\"src\\\":\\\"c2c\\\",\\\"area\\\":\\\"active_page\\\",\\\"sversion\\\":\\\"7.5\\\",\\\"bangdan_src\\\":\\\"list\\\"}\"}"
;
//String signs="undefined&1624862377708&12574478&{\"appId\":\"10211\",\"params\":\"{\\\"multi_hintq_show\\\":\\\"on\\\",\\\"src\\\":\\\"c2c\\\",\\\"area\\\":\\\"active_page\\\",\\\"sversion\\\":\\\"7.5\\\",\\\"bangdan_src\\\":\\\"list\\\"}\"}";
String
sign
=
TaoBaoUtils
.
parsJSFunction
(
signs
);
//String url = "https://acs.m.taobao.com/h5/mtop.relationrecommend.wirelessrecommend.recommend/2.0/?appKey=12574478&t="+time+"&sign="+sign+"&api=mtop.relationrecommend.WirelessRecommend.recommend&v=2.0&type=jsonp&dataType=jsonp&callback=mtopjsonp1&data=%7B%22appId%22%3A%2210211%22%2C%22params%22%3A%22%7B%5C%22multi_hintq_show%5C%22%3A%5C%22on%5C%22%2C%5C%22src%5C%22%3A%5C%22c2c%5C%22%2C%5C%22area%5C%22%3A%5C%22active_page%5C%22%2C%5C%22sversion%5C%22%3A%5C%227.5%5C%22%2C%5C%22bangdan_src%5C%22%3A%5C%22list%5C%22%7D%22%7D";
String
url
=
"https://acs.m.taobao.com/h5/mtop.relationrecommend.wirelessrecommend.recommend/2.0/?appKey=12574478&t=1624929605260&sign=ada01d783dc9772d2f84124d293bac26&api=mtop.relationrecommend.WirelessRecommend.recommend&v=2.0&type=jsonp&dataType=jsonp&callback=mtopjsonp1&data=%7B%22appId%22%3A%2210211%22%2C%22params%22%3A%22%7B%5C%22multi_hintq_show%5C%22%3A%5C%22on%5C%22%2C%5C%22src%5C%22%3A%5C%22c2c%5C%22%2C%5C%22area%5C%22%3A%5C%22active_page%5C%22%2C%5C%22sversion%5C%22%3A%5C%227.5%5C%22%2C%5C%22bangdan_src%5C%22%3A%5C%22list%5C%22%7D%22%7D"
;
Map
<
String
,
String
>
headerMap
=
new
HashMap
<>();
headerMap
.
put
(
"cookie"
,
"_m_h5_tk=975fb07b671f12a689d4ec36cf2e9047_1624937028814; _m_h5_tk_enc=ffb83d60b283eee5992d5e32429c2597;"
);
String
htmlBody
=
null
;
Request
request
=
RequestUtils
.
wrapGet
(
url
,
headerMap
);
try
(
Response
response
=
httpBoot
.
syncCall
(
request
,
ProxyHolder
.
NAT_HEAVY_PROXY
))
{
htmlBody
=
response
.
body
().
string
();
System
.
out
.
println
(
htmlBody
);
}
catch
(
Exception
e
)
{
log
.
error
(
"解析淘宝热搜时出现解析错误,页面结构有问题"
,
e
);
}
if
(
htmlBody
!=
null
&&
htmlBody
.
contains
(
"data"
))
{
return
ansysData
(
htmlBody
,
date
);
}
else
{
log
.
info
(
"解析淘宝热搜时出现解析错误,页面结构有问题"
);
}
return
Collections
.
emptyList
();
}
private
static
List
<
HotSearchList
>
ansysData
(
String
htmlBody
,
Date
date
)
{
List
<
HotSearchList
>
list
=
new
ArrayList
<>();
try
{
String
sub
=
htmlBody
.
substring
(
htmlBody
.
indexOf
(
"searchdoor"
),
htmlBody
.
indexOf
(
"searchdoorFrom"
));
String
substring
=
sub
.
substring
(
sub
.
indexOf
(
"showReminder"
)
+
27
,
sub
.
indexOf
(
"multi_bangdan_flag"
)
-
2
).
trim
();
JSONArray
objects
=
JSONObject
.
parseArray
(
substring
);
JSONArray
jsonArray
=
objects
.
getJSONObject
(
0
).
getJSONObject
(
"result"
).
getJSONArray
(
"text"
);
for
(
int
i
=
0
;
i
<
jsonArray
.
size
();
i
++)
{
try
{
JSONObject
jsonObject
=
jsonArray
.
getJSONObject
(
i
);
String
name
=
jsonObject
.
getString
(
"showtext"
);
String
showmark
=
jsonObject
.
getString
(
"showmark"
);
Integer
rank
=
Integer
.
valueOf
(
showmark
);
String
searchtext
=
jsonObject
.
getString
(
"searchtext"
);
String
url
=
"https://s.m.taobao.com/h5?q="
+
searchtext
;
String
tagText
=
jsonObject
.
getString
(
"tagText"
);
Long
count
=
0L
;
HotSearchList
hotSearchList
=
new
HotSearchList
(
url
,
name
,
count
,
true
,
rank
,
HotSearchType
.
淘宝热搜
.
name
(),
tagText
,
date
);
list
.
add
(
hotSearchList
);
}
catch
(
Exception
e
)
{
log
.
error
(
"解析淘宝热搜时出现解析错误"
,
e
);
}
}
System
.
out
.
println
(
jsonArray
.
size
());
}
catch
(
Exception
e
)
{
log
.
error
(
"解析淘宝热搜时出现解析错误,数据不是json结构"
,
e
);
}
return
list
;
}
}
src/main/java/com/zhiwei/searchhotcrawler/timer/BaiduHotSearchRun.java
View file @
7546fbb8
...
...
@@ -56,18 +56,18 @@ public class BaiduHotSearchRun extends Thread{
// }
TipsUtils
.
addHotList
(
"百度热搜"
,
baiduList
);
log
.
info
(
"百度风云榜采集结束........"
);
ZhiWeiTools
.
sleep
(
2000L
);
log
.
info
(
"搜狗微信采集开始........"
);
List
<
HotSearchList
>
sougouList
=
SougoHotSearchCrawler
.
sougoHotSearch
(
new
Date
());
log
.
info
(
"{}, 此轮采集到的数据量为:{}"
,
new
Date
(),
Integer
.
valueOf
(
sougouList
!=
null
?
sougouList
.
size
()
:
0
));
TipsUtils
.
addHotList
(
"搜狗微信热搜"
,
sougouList
);
log
.
info
(
"搜狗微信采集结束........"
);
ZhiWeiTools
.
sleep
(
2000L
);
log
.
info
(
"知乎话题采集开始........"
);
List
<
HotSearchList
>
zhihuList
=
ZhihuHotSearchCrawler
.
getMobileZhihuHotList
(
new
Date
());
log
.
info
(
"{}, 知乎此轮采集到的数据量为:{}"
,
new
Date
(),
Integer
.
valueOf
(
zhihuList
!=
null
?
zhihuList
.
size
()
:
0
));
TipsUtils
.
addHotList
(
"知乎热搜"
,
zhihuList
);
log
.
info
(
"知乎话题采集结束........"
);
//
ZhiWeiTools.sleep(2000L);
//
log.info("搜狗微信采集开始........");
//
List<HotSearchList> sougouList = SougoHotSearchCrawler.sougoHotSearch(new Date());
//
log.info("{}, 此轮采集到的数据量为:{}", new Date(), Integer.valueOf(sougouList != null ? sougouList.size() : 0));
//
TipsUtils.addHotList("搜狗微信热搜",sougouList);
//
log.info("搜狗微信采集结束........");
//
ZhiWeiTools.sleep(2000L);
//
log.info("知乎话题采集开始........");
//
List<HotSearchList> zhihuList = ZhihuHotSearchCrawler.getMobileZhihuHotList(new Date());
//
log.info("{}, 知乎此轮采集到的数据量为:{}", new Date(), Integer.valueOf(zhihuList != null ? zhihuList.size() : 0));
//
TipsUtils.addHotList("知乎热搜",zhihuList);
//
log.info("知乎话题采集结束........");
}
}
\ No newline at end of file
src/main/java/com/zhiwei/searchhotcrawler/timer/WeiboHotSearchRun.java
View file @
7546fbb8
package
com
.
zhiwei
.
searchhotcrawler
.
timer
;
import
java.util.ArrayList
;
import
java.util.Date
;
import
java.util.List
;
import
java.util.concurrent.TimeUnit
;
import
com.zhiwei.searchhotcrawler.dao.HotSearchCacheDAO
;
import
com.zhiwei.searchhotcrawler.util.TipsUtils
;
import
lombok.extern.log4j.Log4j2
;
...
...
src/main/java/com/zhiwei/searchhotcrawler/util/MD5Util.java
0 → 100644
View file @
7546fbb8
package
com
.
zhiwei
.
searchhotcrawler
.
util
;
import
java.security.MessageDigest
;
public
class
MD5Util
{
private
MD5Util
()
{
throw
new
IllegalStateException
(
"Utility class"
);
}
/**
* @Title: MD5
* @Description: MD5后的字符串
* @param pwd
* @param @return
* 设定文件
* @return String 返回类型
*/
public
static
String
getMD5
(
String
pwd
)
{
return
getString
(
pwd
);
}
private
static
String
getString
(
String
pwd
)
{
char
[]
md5String
=
{
'0'
,
'1'
,
'2'
,
'3'
,
'4'
,
'5'
,
'6'
,
'7'
,
'8'
,
'9'
,
'A'
,
'B'
,
'C'
,
'D'
,
'E'
,
'F'
};
try
{
// 使用平台的默认字符集将此 String 编码为 byte序列,并将结果存储到一个新的 byte数组中
byte
[]
btInput
=
pwd
.
getBytes
();
// 信息摘要是安全的单向哈希函数,它接收任意大小的数据,并输出固定长度的哈希值。
MessageDigest
mdInst
=
MessageDigest
.
getInstance
(
"MD5"
);
// MessageDigest对象通过使用 update方法处理数据, 使用指定的byte数组更新摘要
mdInst
.
update
(
btInput
);
// 摘要更新之后,通过调用digest()执行哈希计算,获得密文
byte
[]
md
=
mdInst
.
digest
();
// 把密文转换成十六进制的字符串形式
int
j
=
md
.
length
;
char
str
[]
=
new
char
[
j
*
2
];
int
k
=
0
;
for
(
int
i
=
0
;
i
<
j
;
i
++)
{
// i = 0
byte
byte0
=
md
[
i
];
// 95
str
[
k
++]
=
md5String
[
byte0
>>>
4
&
0xf
];
// 5
str
[
k
++]
=
md5String
[
byte0
&
0xf
];
// F
}
// 返回经过加密后的字符串
return
new
String
(
str
);
}
catch
(
Exception
e
)
{
e
.
printStackTrace
();
return
null
;
}
}
}
src/main/java/com/zhiwei/searchhotcrawler/util/TaoBaoUtils.java
0 → 100644
View file @
7546fbb8
package
com
.
zhiwei
.
searchhotcrawler
.
util
;
import
lombok.extern.log4j.Log4j2
;
import
org.springframework.core.io.ClassPathResource
;
import
org.springframework.core.io.Resource
;
import
javax.script.Invocable
;
import
javax.script.ScriptEngine
;
import
javax.script.ScriptEngineManager
;
import
java.io.FileReader
;
@Log4j2
public
class
TaoBaoUtils
{
public
static
String
parsJSFunction
(
String
sign
)
{
String
scriptResult
=
""
;
//脚本的执行结果
ScriptEngine
engine
=
new
ScriptEngineManager
().
getEngineByName
(
"JavaScript"
);
//1.得到脚本引擎
//ScriptEngine engine = new ScriptEngineManager().getEngineByName("nashorn");//1.得到脚本引擎
try
{
//2.引擎读取 脚本字符串
//engine.eval(new StringReader(routeScript));
//如果js存在文件里
Resource
aesJs
=
new
ClassPathResource
(
"taobao.js"
);
engine
.
eval
(
new
FileReader
(
aesJs
.
getFile
()));
//3.将引擎转换为Invocable,这样才可以掉用js的方法
Invocable
invocable
=
(
Invocable
)
engine
;
//4.使用 invocable.invokeFunction掉用js脚本里的方法,第一個参数为方法名,后面的参数为被调用的js方法的入参
scriptResult
=
(
String
)
invocable
.
invokeFunction
(
"h"
,
sign
);
}
catch
(
Exception
e
){
log
.
error
(
"Error executing script: "
,
e
.
getMessage
());
}
return
scriptResult
;
}
}
src/main/resources/redis.properties
View file @
7546fbb8
#redis.host=115.236.59.91
#redis.port=7382
#redis.host=127.0.0.1
#redis.port=6379
#redis.password=
#ÐÂÏßÉÏredis
#redis.host = 192.168.0.39
...
...
src/test/java/ObjectTest.java
View file @
7546fbb8
...
...
@@ -21,6 +21,6 @@ import org.springframework.test.context.junit4.SpringJUnit4ClassRunner;
@RunWith
(
SpringJUnit4ClassRunner
.
class
)
@ContextConfiguration
(
locations
=
{
"classpath:applicationContext.xml"
})
public
abstract
class
ObjectTest
extends
AbstractJUnit4SpringContextTests
{
public
abstract
class
ObjectTest
extends
AbstractJUnit4SpringContextTests
{
}
src/test/java/hotSaerchTest/HotSearchTest.java
View file @
7546fbb8
...
...
@@ -14,6 +14,7 @@ import com.zhiwei.searchhotcrawler.crawler.BaiDuHotSearchCrawler;
import
com.zhiwei.searchhotcrawler.dbtemplate.MongoDBTemplate
;
import
com.zhiwei.searchhotcrawler.test.KuaiShouHotSearchCrawlerTest
;
import
com.zhiwei.searchhotcrawler.test.TaoBaoHotSearchCrawlerTest
;
import
com.zhiwei.searchhotcrawler.util.TaoBaoUtils
;
import
com.zhiwei.searchhotcrawler.util.TipsUtils
;
import
lombok.extern.log4j.Log4j2
;
import
okhttp3.Request
;
...
...
@@ -103,27 +104,28 @@ public class HotSearchTest {
}
}
ad
(
document
);
ad
(
document
);
System
.
out
.
println
(
document
);
}
private
void
ad
(
Document
nowDoc
)
{
MongoCollection
collection
=
MongoDBTemplate
.
getCollection
(
DBConfig
.
dbName
,
DBConfig
.
searchCacheCollName
);
if
(
nowDoc
.
containsKey
(
"topicLead"
))
{
MongoCollection
collection
=
MongoDBTemplate
.
getCollection
(
DBConfig
.
dbName
,
DBConfig
.
searchCacheCollName
);
if
(
nowDoc
.
containsKey
(
"topicLead"
))
{
nowDoc
.
put
(
"topicLead"
,
nowDoc
.
getString
(
"topicLead"
));
}
if
(
nowDoc
.
containsKey
(
"readCount"
)
&&
nowDoc
.
containsKey
(
"discussCount"
))
{
nowDoc
.
put
(
"readCount"
,
nonNull
(
nowDoc
.
get
(
"readCount"
))?
Long
.
valueOf
(
nowDoc
.
get
(
"readCount"
).
toString
()):
null
);
nowDoc
.
put
(
"discussCount"
,
nonNull
(
nowDoc
.
get
(
"discussCount"
))?
Long
.
valueOf
(
nowDoc
.
get
(
"discussCount"
).
toString
()):
null
);
if
(
nowDoc
.
containsKey
(
"readCount"
)
&&
nowDoc
.
containsKey
(
"discussCount"
))
{
nowDoc
.
put
(
"readCount"
,
nonNull
(
nowDoc
.
get
(
"readCount"
))
?
Long
.
valueOf
(
nowDoc
.
get
(
"readCount"
).
toString
())
:
null
);
nowDoc
.
put
(
"discussCount"
,
nonNull
(
nowDoc
.
get
(
"discussCount"
))
?
Long
.
valueOf
(
nowDoc
.
get
(
"discussCount"
).
toString
())
:
null
);
}
if
(
nowDoc
.
containsKey
(
"pictureUrl"
))
{
nowDoc
.
put
(
"pictureUrl"
,
nowDoc
.
getString
(
"pictureUrl"
));
nowDoc
.
put
(
"pictureUrl"
,
nowDoc
.
getString
(
"pictureUrl"
));
}
if
(
nowDoc
.
containsKey
(
"downtext"
))
{
nowDoc
.
put
(
"downtext"
,
nowDoc
.
getString
(
"downtext"
));
nowDoc
.
put
(
"downtext"
,
nowDoc
.
getString
(
"downtext"
));
}
collection
.
insertOne
(
nowDoc
);
}
/**
* 测试淘宝热搜采集
*/
...
...
@@ -154,9 +156,20 @@ public class HotSearchTest {
List
<
HotSearchList
>
hotSearchLists
=
BaiDuHotSearchCrawler
.
baiduHotSearch
(
new
Date
());
System
.
out
.
println
(
hotSearchLists
);
System
.
out
.
println
(
hotSearchLists
.
size
());
}
/**
* 测试解析淘宝js文件
*/
@Test
public
void
taoBaoJSTest
()
throws
IOException
{
long
time
=
new
Date
().
getTime
();
String
signs
=
"undefined&1625624820156&12574478&{\"appId\":\"10211\",\"params\":\"{\\\"multi_hintq_show\\\":\\\"on\\\",\\\"src\\\":\\\"c2c\\\",\\\"area\\\":\\\"active_page\\\",\\\"sversion\\\":\\\"7.5\\\",\\\"bangdan_src\\\":\\\"list\\\"}\"}"
;
// https://acs.m.taobao.com/h5/mtop.relationrecommend.wirelessrecommend.recommend/2.0/?appKey=12574478&t=1624930984092&sign=acf994dbcee6c0c1d7a8a566a6b8ff0a&api=mtop.relationrecommend.WirelessRecommend.recommend&v=2.0&type=jsonp&dataType=jsonp&callback=mtopjsonp1&data=%7B%22appId%22%3A%2210211%22%2C%22params%22%3A%22%7B%5C%22multi_hintq_show%5C%22%3A%5C%22on%5C%22%2C%5C%22src%5C%22%3A%5C%22c2c%5C%22%2C%5C%22area%5C%22%3A%5C%22active_page%5C%22%2C%5C%22sversion%5C%22%3A%5C%227.5%5C%22%2C%5C%22bangdan_src%5C%22%3A%5C%22list%5C%22%7D%22%7D
String
s
=
TaoBaoUtils
.
parsJSFunction
(
signs
);
System
.
out
.
println
(
s
);
}
}
...
...
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