Dedicated Crawler

Iš NAAS.
Jump to navigation Jump to search

Apie

Įrankis skirtas rinkti informaciją iš interneto puslapių.

Nuoroda į įrankį

Versijos

[1.0 (http://158.129.51.98/repo/NAAS/dedicated-crawler/src/master)]

Hakatonui

Versija skirta []

Konfigūravimas

 {
   "name": "baltnews",
   "url": "https://baltnews.com/v-litve/",
   "base_url": "https://baltnews.com",
   "test_url": "https://baltnews.com/v-litve/20221026/1025778858/Kitay--ne-prioritet-Litva-ukreplyaet-sotrdunichestvo-s-Yuzhnoy-Koreey.html",
   "link_selector": [
     ".rubric-list__article-media-link"
   ],
   "image_selector": [
     "figure.article-header__media > img"
   ],
   "headless": true,
   "language": "ru",
   "feed_id": "feed-32fc2232",
   "source_id": "source-1d9e7e56-cd9e-675f-456b-23af3fc0efeb",
   "title": {
     "attribute": null,
     "format": "str",
     "regex": null,
     "required": false,
     "selector": ".article-header h1",
     "type": "field"
   },
   "text": {
     "attribute": null,
     "format": "str",
     "regex": null,
     "required": false,
     "selector": ".article-content__body > p",
     "type": "field"
   },
   "proxy": null,
   "proxy_auth": null,
   "likes": null,
   "dislikes": null,
   "views": null,
   "shares": null
 }