搜索关键字爬虫

This commit is contained in:
2025-11-12 16:10:34 +08:00
parent 7be02fe396
commit 675e6da7d7
37 changed files with 3382 additions and 572 deletions

View File

@@ -114,35 +114,49 @@ school-news:
crawler:
python:
path: F:\Environment\Conda\envs\shoolNewsCrewer
base:
path: F:/Project/schoolNews/schoolNewsCrawler
# Python 可执行文件路径Windows 建议指向 python.exe如已在 PATH可直接用 "python"
pythonPath: F:/Environment/Conda/envs/schoolNewsCrawler/python.exe
# 爬虫脚本根目录NewsCrawlerTask 的工作目录)
basePath: F:/Project/schoolNews/schoolNewsCrawler
crontab:
items: #可供前端选择的定时任务列表
- name: 人民日报新闻爬取
methods: #爬取方式
- name: 关键字搜索爬取
class: org.xyzh.crontab.task.newsTask.NewsCrawlerTask
clazz: newsCrewerTask
excuete_method: execute
path: crawler/RmrbSearch.py
params:
query: String #搜索关键字
total: Integer #总新闻数量
- name: query
description: 搜索关键字
type: String
value: ""
- name: total
description: 总新闻数量
type: Integer
value: 10
- name: 排行榜爬取
class: org.xyzh.crontab.task.newsTask.NewsCrawlerTask
clazz: newsCrewerTask
excuete_method: execute
path: crawler/RmrbHotPoint.py
- name: 往日精彩头条爬取
class: org.xyzh.crontab.task.newsTask.NewsCrawlerTask
clazz: newsCrewerTask
excuete_method: execute
path: crawler/RmrbTrending.py
params:
startDate: String #开始日期
endDate: String #结束日期
isYestoday: Boolean #是否是昨天
- name: startDate
description: 开始日期
type: String
value: ""
- name: endDate
description: 结束日期
type: String
value: ""
- name: yesterday
description: 是否是昨天
type: Boolean
value: true
# 文件存储配置
file: