673eb0245a
注册漏洞修复，增强用户认证系统安全性
2025-03-06 08:14:16 +08:00
f85298c021
Spider System Performance & Stability Enhancement
2025-03-04 10:45:37 +08:00
e0719583fc
Optimize database connection management in spider module, fix WebSocket handling and parameter validation.
2025-02-25 10:27:41 +08:00
930046fd5c
Add AI-powered Spider Configuration Assistant.
2025-02-24 17:10:23 +08:00
1180f285a0
Add a visual control panel for the crawler, supporting customization of topics and parameter configuration.
2025-02-23 23:30:54 +08:00
20a5be7aeb
Add options for selecting large models and prioritize using DeepSeek for analysis.
2025-02-16 01:16:35 +08:00
017f43a9c3
Deleted some unused documentation files.
2025-02-13 18:44:09 +08:00
f5b2bf5061
Delete the BCAT frontend page.
2025-02-13 16:13:25 +08:00
dfe1a833f9
Modify naming conventions that may cause confusion and consolidate code files.
2025-02-13 15:56:34 +08:00
9106d8ed3d
Add DeepSeek model selection UI support.
2025-02-12 18:21:27 +08:00
82089852c9
Supports integration of two models from DeepSeek for analysis!
2025-02-12 01:45:45 +08:00
12a8732bd2
More model support, including OpenAI and Claude, with corresponding updates to the README documentation.
2025-02-11 22:41:09 +08:00
a60a0f3296
A more comprehensive large model analysis setup, front-end interface optimization.
2025-02-11 22:30:52 +08:00
8ec05efe27
Integrating the OpenAI API for in-depth comment analysis, with usability to be debugged.
2025-02-10 00:10:14 +08:00
8249ec0048
Implement a two-level caching system (memory + disk) to optimize topic switch response speed, support asynchronous writing, and automatically clean up expired data.
2025-02-09 22:06:46 +08:00
607db7317e
Optimize model loading and prediction performance, implement the singleton pattern, and provide comprehensive error handling and error messages, along with confidence level display.
2025-02-08 23:00:11 +08:00
1707c2c3de
Added a feature to select the emotion analysis model, supporting switching between the basic and improved models.
2025-02-04 21:06:33 +08:00
826de6184d
The old emotion recognition model has been replaced with the new model_pro, and the results have been integrated into the project.
2025-02-04 21:03:45 +08:00
a9108a909c
Merge branch 'main' of https://github.com/666ghj/Weibo_PublicOpinion_AnalysisSystem
2025-01-27 18:09:59 +08:00
c62f2b2a8e
Added a logging utility class and supplemented, standardized the logging output for all modules.
2025-01-27 18:09:30 +08:00
766d45dec9
Update README-CN.md
2025-01-17 21:50:07 +08:00
03a70e6413
Update README.md
2025-01-17 21:32:56 +08:00
0a224289ef
Update README.md
2025-01-17 21:31:45 +08:00
6bbebde3d8
Merge pull request #15 from zhaisang111/main
...
Optimized the getEchartsData.py script, improving code efficiency and…
2025-01-15 15:37:25 +08:00
fea1f778b4
Optimized the getEchartsData.py script, improving code efficiency and readability.
2025-01-13 21:03:44 +08:00
1288b5f0be
Unimportant changes
2025-01-12 19:54:56 +08:00
4bee58b73a
Merge pull request #14 from tianjy12/main
...
Removed unnecessary introduction and optimized the word cloud generation component. Added dynamic scheduling functionality to adjust crawler execution intervals based on crawl duration and data volume.
2025-01-12 19:49:00 +08:00
45324ee19b
Added dynamic scheduling functionality to adjust crawler execution intervals based on crawl duration and data volume.
2025-01-12 18:34:09 +08:00
3d253b11fb
Optimize word cloud generation script by adding logging and exception handling.
2025-01-12 04:06:18 -06:00
06e6060b7a
Delete some unnecessary introductions
2025-01-12 03:18:25 -06:00
e58f105761
More convenient project initialization, with database initialization added to app.py.
2025-01-09 23:30:15 +08:00
a30773715e
Modify the database hardcoding to switch to command-line interactive database connection.
2025-01-09 23:08:55 +08:00
ba56f3b0d4
Merge pull request #12 from lintsinghua/main
...
Optimized the web scraping functionality to support multi-account crawling and enhance performance.
2024-12-14 23:33:30 +08:00
8c4f3e9b52
Update spiderContent.py
2024-12-14 20:07:14 +08:00
a7472b4287
Update spiderComments.py
2024-12-14 20:06:39 +08:00
babb9d54a9
Update spiderNav.py
2024-12-14 20:05:58 +08:00
82be6f864f
Merge pull request #11 from craiemer/main
...
添加日志输出
2024-12-14 19:26:21 +08:00
057e02e943
Merge pull request #10 from qqqlsm666/main
...
优化 topicDefine.py 主题标签处理逻辑，提升性能与稳定性
2024-12-14 19:16:27 +08:00
ad3a20018d
添加日志输出
2024-12-14 19:11:51 +08:00
9e3c72e3ae
Create CODE_OF_CONDUCT.md
2024-12-14 18:41:49 +08:00
7583ef2c9a
优化 topicDefine.py 主题标签处理逻辑，提升性能与稳定性
...
主要针对 topicDefine.py 程序进行了优化，提升了其在处理文章和评论主题标签时的性能与稳定性。
2024-12-14 18:29:11 +08:00
f4ea9b9b6d
Merge pull request #7 from wjhgq/main
...
The new practice sequence model to complete the public opinion prediction function.
2024-12-12 16:59:11 +08:00
03ec500e17
Merge pull request #5 from lycoriskang/main
...
Strengthen login security and prevent SQL injection issues
2024-12-12 16:16:15 +08:00
d908e4c82d
Update yuqingpredict.py
2024-12-12 13:25:21 +08:00
3fab33a8d4
Update predict.py. The prediction model is optimized to a time series model, which significantly improves the modeling fitness.
...
In the original method, only linear regression is used to perform simple trend extrapolation, which leads to insufficient prediction accuracy. This optimization adopts time series model, and uses the auto_arima method of pmdarima to automatically select appropriate model parameters (including p, d, q and seasonal parameters) according to historical data. It significantly improves the suitability of the model in time series modeling. In this way, the model can better capture the trend and periodicity of the data, and predict the future heat more reasonable and accurate.
2024-12-12 13:24:50 +08:00
f480ceeb21
Update README.md
2024-12-10 23:23:17 +08:00
d9d1b7136c
Update README.md
2024-12-10 23:00:49 +08:00
ff41fa8310
Update README.md
2024-12-10 22:33:44 +08:00
e87a13df09
Update README-CN.md
2024-12-10 22:21:46 +08:00
c6568b366e
Fix broken link
2024-12-10 22:18:05 +08:00
多多