Skip to content
项目
群组
代码片段
帮助
当前项目
正在载入...
登录 / 注册
切换导航面板
Z
zzsn_spider
概览
概览
详情
活动
周期分析
版本库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
统计图
问题
0
议题
0
列表
看板
标记
里程碑
合并请求
1
合并请求
1
CI / CD
CI / CD
流水线
作业
日程表
图表
维基
Wiki
代码片段
代码片段
成员
成员
折叠边栏
关闭边栏
活动
图像
聊天
创建新问题
作业
提交
问题看板
Open sidebar
丁双波
zzsn_spider
Commits
a7245fb1
提交
a7245fb1
authored
11月 14, 2023
作者:
薛凌堃
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
天眼查token修改
上级
3ad4e1eb
隐藏空白字符变更
内嵌
并排
正在显示
5 个修改的文件
包含
30 行增加
和
17 行删除
+30
-17
getTycId.py
comData/Tyc/getTycId.py
+1
-1
newsbucai.py
comData/Tyc/newsbucai.py
+3
-2
newsbucai1.py
comData/Tyc/newsbucai1.py
+3
-2
tyc_qydt_add.py
comData/Tyc/tyc_qydt_add.py
+19
-11
采集说明.md
comData/Tyc/采集说明.md
+4
-1
没有找到文件。
comData/Tyc/getTycId.py
浏览文件 @
a7245fb1
...
...
@@ -28,7 +28,7 @@ headers = {
'Sec-Fetch-Mode'
:
'cors'
,
'Sec-Fetch-Site'
:
'same-site'
,
'User-Agent'
:
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5
NzE5MDMwMywiZXhwIjoxNjk5NzgyMzAzfQ.awXuS-59RzK35r0aUJq4Rj83JzyAOvsdUfL_ojp66CVQMjlLv_ZDD9g5gCoZKE21LN1JYRMLNZhuWsHhxapROw
'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5
OTkyNTk5NywiZXhwIjoxNzAyNTE3OTk3fQ.9iXmxFEiBdu2WYa7RwdU0xKKx7v_wBe9-QipH0TNKp9Dzk_2cZK1ESsmO1o8ICrddb5sx2cl5pjOBoaaf_9Qsg
'
,
'X-TYCID'
:
'6f6298905d3011ee96146793e725899d'
,
'sec-ch-ua'
:
'"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"'
,
'sec-ch-ua-mobile'
:
'?0'
,
...
...
comData/Tyc/newsbucai.py
浏览文件 @
a7245fb1
...
...
@@ -42,7 +42,7 @@ headers = {
'Sec-Fetch-Mode'
:
'cors'
,
'Sec-Fetch-Site'
:
'same-site'
,
'User-Agent'
:
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5
NzE5MDMwMywiZXhwIjoxNjk5NzgyMzAzfQ.awXuS-59RzK35r0aUJq4Rj83JzyAOvsdUfL_ojp66CVQMjlLv_ZDD9g5gCoZKE21LN1JYRMLNZhuWsHhxapROw
'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5
OTkyNTk5NywiZXhwIjoxNzAyNTE3OTk3fQ.9iXmxFEiBdu2WYa7RwdU0xKKx7v_wBe9-QipH0TNKp9Dzk_2cZK1ESsmO1o8ICrddb5sx2cl5pjOBoaaf_9Qsg
'
,
'X-TYCID'
:
'6f6298905d3011ee96146793e725899d'
,
'sec-ch-ua'
:
'"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"'
,
'sec-ch-ua-mobile'
:
'?0'
,
...
...
@@ -181,7 +181,8 @@ def beinWork(tyc_code, social_code,start_time):
retData
[
'up_okCount'
]
=
up_okCount
retData
[
'up_errorCount'
]
=
up_errorCount
retData
[
'up_repetCount'
]
=
up_repetCount
return
retData
# return retData
continue
try
:
time_struct
=
time
.
localtime
(
int
(
info_page
[
'rtm'
]
/
1000
))
# 首先把时间戳转换为结构化时间
time_format
=
time
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
,
time_struct
)
# 把结构化时间转换为格式化时间
...
...
comData/Tyc/newsbucai1.py
浏览文件 @
a7245fb1
...
...
@@ -42,7 +42,7 @@ headers = {
'Sec-Fetch-Mode'
:
'cors'
,
'Sec-Fetch-Site'
:
'same-site'
,
'User-Agent'
:
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5
NzE5MDMwMywiZXhwIjoxNjk5NzgyMzAzfQ.awXuS-59RzK35r0aUJq4Rj83JzyAOvsdUfL_ojp66CVQMjlLv_ZDD9g5gCoZKE21LN1JYRMLNZhuWsHhxapROw
'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5
OTkyNTk5NywiZXhwIjoxNzAyNTE3OTk3fQ.9iXmxFEiBdu2WYa7RwdU0xKKx7v_wBe9-QipH0TNKp9Dzk_2cZK1ESsmO1o8ICrddb5sx2cl5pjOBoaaf_9Qsg
'
,
'X-TYCID'
:
'6f6298905d3011ee96146793e725899d'
,
'sec-ch-ua'
:
'"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"'
,
'sec-ch-ua-mobile'
:
'?0'
,
...
...
@@ -181,7 +181,8 @@ def beinWork(tyc_code, social_code,start_time):
retData
[
'up_okCount'
]
=
up_okCount
retData
[
'up_errorCount'
]
=
up_errorCount
retData
[
'up_repetCount'
]
=
up_repetCount
return
retData
# return retData
continue
try
:
time_struct
=
time
.
localtime
(
int
(
info_page
[
'rtm'
]
/
1000
))
# 首先把时间戳转换为结构化时间
time_format
=
time
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
,
time_struct
)
# 把结构化时间转换为格式化时间
...
...
comData/Tyc/tyc_qydt_add.py
浏览文件 @
a7245fb1
...
...
@@ -26,17 +26,25 @@ cursor = cnx.cursor()
pageSize
=
10
headers
=
{
'Accept'
:
'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7'
,
'Accept-Encoding'
:
'gzip, deflate, br'
,
'Accept-Language'
:
'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6'
,
'Connection'
:
'keep-alive'
,
'Content-Type'
:
'application/json'
,
'Cookie'
:
'jsid=SEO-BAIDU-ALL-SY-000001; TYCID=77e997401d5f11ee9e91d5a0fd3c0b89; ssuid=6450041974; _ga=GA1.2.858826166.1688800641; _gid=GA1.2.2142449376.1689575510; tyc-user-info-save-time=1689764135027; sensorsdata2015jssdkcross=
%7
B
%22
distinct_id
%22%3
A
%22309757777%22%2
C
%22
first_id
%22%3
A
%22189345
cb10257d-0cfee05327f673-26031d51-1327104-189345cb10375b
%22%2
C
%22
props
%22%3
A
%7
B
%22%24
latest_traffic_source_type
%22%3
A
%22%
E8
%87%
AA
%
E7
%84%
B6
%
E6
%90%9
C
%
E7
%
B4
%
A2
%
E6
%
B5
%81%
E9
%87%8
F
%22%2
C
%22%24
latest_search_keyword
%22%3
A
%22%
E6
%9
C
%
AA
%
E5
%8
F
%96%
E5
%88%
B0
%
E5
%80%
BC
%22%2
C
%22%24
latest_referrer
%22%3
A
%22
https
%3
A
%2
F
%2
Fwww.baidu.com
%2
Flink
%22%7
D
%2
C
%22
identities
%22%3
A
%22
eyIkaWRlbnRpdHlfY29va2llX2lkIjoiMTg5MzQ1Y2IxMDI1N2QtMGNmZWUwNTMyN2Y2NzMtMjYwMzFkNTEtMTMyNzEwNC0xODkzNDVjYjEwMzc1YiIsIiRpZGVudGl0eV9sb2dpbl9pZCI6IjMwOTc1Nzc3NyJ9
%22%2
C
%22
history_login_id
%22%3
A
%7
B
%22
name
%22%3
A
%22%24
identity_login_id
%22%2
C
%22
value
%22%3
A
%22309757777%22%7
D
%2
C
%22%24
device_id
%22%3
A
%22189345
cb10257d-0cfee05327f673-26031d51-1327104-189345cb10375b
%22%7
D; bannerFlag=true; Hm_lvt_e92c8d65d92d534b0fc290df538b4758=1689752829,1689821665,1689831487,1689845884; searchSessionId=1689845917.81838207; HWWAFSESID=146bb1d25b1515339d3; HWWAFSESTIME=1689858023324; Hm_lpvt_e92c8d65d92d534b0fc290df538b4758=1689859758'
,
'Host'
:
'capi.tianyancha.com'
,
'Origin'
:
'https://www.tianyancha.com'
,
'Referer'
:
'https://www.tianyancha.com/'
,
'User-Agent'
:
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.51'
}
'Accept'
:
'application/json, text/plain, */*'
,
'Accept-Encoding'
:
'gzip, deflate, br'
,
'Accept-Language'
:
'zh-CN,zh;q=0.9'
,
'Connection'
:
'keep-alive'
,
'Content-Type'
:
'application/json'
,
'Host'
:
'capi.tianyancha.com'
,
'Origin'
:
'https://www.tianyancha.com'
,
'Referer'
:
'https://www.tianyancha.com/'
,
'Sec-Fetch-Dest'
:
'empty'
,
'Sec-Fetch-Mode'
:
'cors'
,
'Sec-Fetch-Site'
:
'same-site'
,
'User-Agent'
:
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
,
'X-AUTH-TOKEN'
:
'eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxODcwMzc1MjYwMCIsImlhdCI6MTY5OTkyNTk5NywiZXhwIjoxNzAyNTE3OTk3fQ.9iXmxFEiBdu2WYa7RwdU0xKKx7v_wBe9-QipH0TNKp9Dzk_2cZK1ESsmO1o8ICrddb5sx2cl5pjOBoaaf_9Qsg'
,
'X-TYCID'
:
'6f6298905d3011ee96146793e725899d'
,
'sec-ch-ua'
:
'"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"'
,
'sec-ch-ua-mobile'
:
'?0'
,
'sec-ch-ua-platform'
:
'"Windows"'
,
'version'
:
'TYC-Web'
}
#144数据库连接,使用连接池
cnx_
=
baseCore
.
pool_caiji
.
connection
()
cursor_
=
cnx_
.
cursor
()
...
...
comData/Tyc/采集说明.md
浏览文件 @
a7245fb1
天眼查企业
动态
天眼查企业
动态
...
...
@@ -18,3 +18,6 @@
`cnx_ = baseCore.pool_caiji.connection()
cursor_ = cnx_.cursor()`
!
[
img.png
](
img.png
)
11.
14 问题描述:天眼查token会过期,导致只能访问到第一页动态数据
(待解决)解决办法:设置登录存入数据库中,token从数据库中获取,判断过期的条件
编写
预览
Markdown
格式
0%
重试
或
添加新文件
添加附件
取消
您添加了
0
人
到此讨论。请谨慎行事。
请先完成此评论的编辑!
取消
请
注册
或者
登录
后发表评论