Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
W
wechat
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
wechat
Commits
9159a942
Commit
9159a942
authored
Nov 09, 2019
by
zhiwei
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
将转临时链接添加白明天代理访问使用
parent
eec30e53
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
50 additions
and
97 deletions
+50
-97
pom.xml
+1
-1
src/main/java/com/zhiwei/wechat/search/WechatReal.java
+34
-6
src/test/java/com/zhiwei/wechat/example/WechatSearchExample.java
+15
-90
No files found.
pom.xml
View file @
9159a942
...
...
@@ -3,7 +3,7 @@
<modelVersion>
4.0.0
</modelVersion>
<groupId>
com.zhiwei
</groupId>
<artifactId>
wechat
</artifactId>
<version>
1.
2.9
-SNAPSHOT
</version>
<version>
1.
3.0
-SNAPSHOT
</version>
<description>
知微微信采集程序,包含
1.微信历史文章采集
...
...
src/main/java/com/zhiwei/wechat/search/WechatReal.java
View file @
9159a942
...
...
@@ -26,6 +26,31 @@ public class WechatReal {
*/
public
static
String
getRealLink
(
String
originalUrl
)
throws
Exception
{
Proxy
proxy
=
ProxyHolder
.
NAT_HEAVY_PROXY
.
getProxy
();
originalUrl
=
getOriginalUrl
(
originalUrl
);
String
realUrl
=
getFinalUrl
(
originalUrl
,
proxy
);
return
realUrl
;
}
/**
* 通过白名单代理ip获取真实链接
* @param originalUrl
* @param proxy
* @return
* @throws Exception
*/
public
static
String
getRealLink
(
String
originalUrl
,
Proxy
proxy
)
throws
Exception
{
originalUrl
=
getOriginalUrl
(
originalUrl
);
String
realUrl
=
getFinalUrl
(
originalUrl
,
proxy
);
return
realUrl
;
}
/**
* 获取转链接的中间跳转链接
* @param originalUrl
* @return
*/
private
static
String
getOriginalUrl
(
String
originalUrl
){
int
b
=
(
int
)
(
Math
.
floor
(
100
*
Math
.
random
())
+
1
);
int
a
=
originalUrl
.
indexOf
(
"url="
);
int
c
=
originalUrl
.
indexOf
(
"&k="
);
...
...
@@ -34,13 +59,17 @@ public class WechatReal {
d
=
originalUrl
.
substring
(
a
+
25
+
b
,
a
+
26
+
b
);
}
originalUrl
+=
"&k="
+
b
+
"&h="
+
d
;
String
realUrl
=
getFinalUrl
(
originalUrl
,
proxy
);
return
realUrl
;
return
originalUrl
;
}
/**
* 通过普通代理获取临时链接
* @param originalUrl
* @param proxy
* @return
* @throws Exception
*/
private
static
String
getFinalUrl
(
String
originalUrl
,
Proxy
proxy
)
throws
Exception
{
Map
<
String
,
String
>
headerMap
=
new
HashMap
<>();
headerMap
.
put
(
"Sec-Fetch-Mode"
,
"navigate"
);
...
...
@@ -66,8 +95,7 @@ public class WechatReal {
}
return
furl
.
toString
();
}
else
{
throw
new
NullPointerException
(
"获取临时链接失败"
);
throw
new
NullPointerException
(
"获取临时链接失败
, 出现输入验证码
"
);
}
}
}
src/test/java/com/zhiwei/wechat/example/WechatSearchExample.java
View file @
9159a942
...
...
@@ -42,26 +42,25 @@ public class WechatSearchExample{
public
static
void
main
(
String
[]
args
)
{
ProxyFactory
.
init
(
registry
,
group
,
GroupType
.
PROVIDER
,
10000018
);
Proxy
proxy
=
ProxyHolder
.
SOUGOU_INNER_PROXY
.
getProxy
();
// String url = "https://weixin.sogou.com/link?url=dn9a_-gY295K0Rci_xozVXfdMkSQTLW6cwJThYulHEtVjXrGTiVgSzcttWBfUfRyBteZJZKwOQZcZaXkLh7iD1qXa8Fplpd9OIASmEBDDgpc-DopMAxHDRa5rMUETB5W4jcmy1RslCj6dRdWlI71gTiuwjp2qvcTJ8ryfwJWyrd9awnq8kg4J-jH9rgNij43NIxLSEyMEC0OFckdi_fmA1TpUaYEJzIlQ9H-i95UM3h5UwmbSJx95X6FkyXmgknK9g_68U3LLV9hlgeRt7bSzA..&type=2&query=%E4%BA%BA%E6%B0%91%E6%97%A5%E6%8A%A5";
// try {
//// String cookie = getRealUrlCookie(url, proxy);
//// System.out.println("cookie==================="+cookie);
//
// String realUrl = getRealLink(url, proxy);
//
// System.out.println("realUrl==================="+realUrl);
// } catch (Exception e) {
// e.printStackTrace();
// }
try
{
WechatAritcleSearch
.
wechatKeywordSearch
(
"京东"
,
5
,
null
,
"2019-10-01"
,
"2019-10-01"
,
proxy
,
10
);
Proxy
proxy
=
ProxyHolder
.
NAT_HEAVY_PROXY
.
getProxy
();
String
url
=
"https://weixin.sogou.com/link?url=dn9a_-gY295K0Rci_xozVXfdMkSQTLW6cwJThYulHEtVjXrGTiVgSzcttWBfUfRyBteZJZKwOQZcZaXkLh7iD1qXa8Fplpd9OIASmEBDDgpc-DopMAxHDRa5rMUETB5W4jcmy1RslCj6dRdWlI71gTiuwjp2qvcTJ8ryfwJWyrd9awnq8kg4J-jH9rgNij43NIxLSEyMEC0OFckdi_fmA1TpUaYEJzIlQ9H-i95UM3h5UwmbSJx95X6FkyXmgknK9g_68U3LLV9hlgeRt7bSzA..&type=2&query=%E4%BA%BA%E6%B0%91%E6%97%A5%E6%8A%A5"
;
try
{
// String cookie = getRealUrlCookie(url, proxy);
// System.out.println("cookie==================="+cookie);
}
catch
(
Exception
e
){
String
realUrl
=
getRealLink
(
url
,
proxy
);
System
.
out
.
println
(
"realUrl==================="
+
realUrl
);
}
catch
(
Exception
e
)
{
e
.
printStackTrace
();
}
// try{
// WechatAritcleSearch.wechatKeywordSearch("京东", 5, null, "2019-10-01", "2019-10-01", proxy, 10);
//
// }catch (Exception e){
// e.printStackTrace();
// }
}
...
...
@@ -130,80 +129,6 @@ public class WechatSearchExample{
}
public
static
String
getRealUrlCookie
(
String
originalUrl
,
Proxy
proxy
)
throws
Exception
{
String
word
=
originalUrl
.
split
(
"query="
)[
1
];
String
searchUrl
=
"https://weixin.sogou.com/weixin?type=2&s_from=input&query="
+
word
+
"&ie=utf8&_sug_=n&_sug_type_=&page=1"
;
Map
<
String
,
String
>
headerMap
=
HeaderTool
.
getCommonHead
();
headerMap
.
put
(
"Host"
,
"weixin.sogou.com"
);
headerMap
.
put
(
"Referer"
,
searchUrl
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36"
);
String
htmlBody
=
httpBoot
.
syncCall
(
RequestUtils
.
wrapGet
(
searchUrl
,
headerMap
),
proxy
,
false
).
body
().
string
();
if
(
StringUtils
.
isNotBlank
(
htmlBody
)
&&
htmlBody
.
contains
(
"snuid"
)){
Matcher
matcher
=
Pattern
.
compile
(
"var uigs_para = [\\s\\S]+?;"
).
matcher
(
htmlBody
);
matcher
.
find
();
String
str
=
matcher
.
group
().
replaceAll
(
"var uigs_para = |;"
,
""
);
try
{
str
=
str
.
toString
().
replaceAll
(
" passportUserId \\? \"1\" \\:"
,
""
);
JSONObject
data
=
JSONObject
.
parseObject
(
str
);
str
=
str
.
replaceAll
(
"\\s"
,
""
).
replaceAll
(
"\":\""
,
"="
).
replaceAll
(
"\",\""
,
"&"
).
replaceAll
(
"\\{\"|\"\\}"
,
""
);
String
ac
=
URLCodeUtil
.
getURLEncode
(
str
,
"utf-8"
);
String
cookieUrl
=
"https://pb.sogou.com/cl.gif?uigs_cl=article_title_6&href="
+
originalUrl
+
"&uigs_refer=https://weixin.sogou.com/&uigs_t="
+
ac
+
"&right=right0_0&exp_id=null_0-null_1-null_2-null_3-null_4-null_5-null_6-null_7-null_8-null_9"
;
headerMap
.
put
(
"Host"
,
"pb.sogou.com"
);
headerMap
.
put
(
"Referer"
,
searchUrl
);
headerMap
.
put
(
"User-Agent"
,
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36"
);
Response
response
=
httpBoot
.
syncCall
(
RequestUtils
.
wrapGet
(
cookieUrl
,
headerMap
),
proxy
,
false
);
if
(
Objects
.
nonNull
(
response
)){
String
cookie
=
""
;
List
<
String
>
headersResponse
=
response
.
headers
(
"Set-Cookie"
);
for
(
String
header
:
headersResponse
)
{
System
.
out
.
println
(
"head======"
+
header
);
cookie
+=
header
.
split
(
";"
)[
0
];
}
return
"uuid="
+
data
.
getString
(
"uuid"
)+
";snuid="
+
data
.
getString
(
"snuid"
)+
";"
+
cookie
+
"IPLOC=CN3302; sct=1;weixinIndexVisited=1"
;
}
}
catch
(
Exception
e
){
e
.
printStackTrace
();
}
}
else
{
System
.
out
.
println
(
"-----------------"
+
htmlBody
);
}
return
null
;
}
public
static
String
getCookie
(
String
htmlBody
)
throws
Exception
{
String
cookie
=
""
;
if
(
StringUtils
.
isNotBlank
(
htmlBody
)
&&
htmlBody
.
contains
(
"snuid"
)){
StringBuilder
furl
=
new
StringBuilder
();
Pattern
pa1
=
Pattern
.
compile
(
"\"snuid\" : \"(.*?)\","
);
Matcher
ma1
=
pa1
.
matcher
(
htmlBody
);
while
(
ma1
.
find
())
{
furl
.
append
(
ma1
.
group
(
1
));
}
return
"SNUID="
+
furl
.
toString
();
}
return
null
;
}
public
static
void
wechatSearchExample
()
throws
UnknownHostException
{
List
<
String
>
wordList
=
new
ArrayList
<
String
>();
...
...
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