harvester/package.json at main · tmptrash/harvester · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
{
  "name": "js-harvester",
  "version": "0.3.14",
  "description": "Harvester is a lightweight and highly optimized javascript library for extracting data from the DOM tree. It supports extraction of tag texts with specified types and attributes. it's tiny and has no dependencies and also works with Puppeteer",
  "type": "module",
  "main": "index.js",
  "scripts": {
    "test": "standard && jest",
    "lint": "standard"
  },
  "repository": {
    "type": "git",
    "url": "git+https://github.com/tmptrash/harvester.git"
  },
  "keywords": [
    "puppeteer",
    "playwright",
    "lightweight",
    "optimized",
    "web-scraping",
    "web",
    "scraping",
    "data-extraction",
    "data",
    "extraction",
    "html-parsing",
    "html",
    "parsing",
    "dom-parsing",
    "dom",
    "parsing",
    "scraping",
    "extraction",
    "harvesting",
    "data-harvesting",
    "template-based-scraping",
    "template-based",
    "scraping",
    "template-extraction",
    "template",
    "extraction",
    "pattern-based-scraping",
    "pattern-based",
    "scraping",
    "visual-scraping-template",
    "declarative-scraping",
    "fuzzy-scraping",
    "fuzzy",
    "scraping",
    "approximate-scraping",
    "approximate",
    "scraping",
    "resilient-scraping",
    "resilient",
    "scraping",
    "flexible-scraping",
    "flexible",
    "scraping",
    "structure-agnostic-scraping",
    "semantic-scraping",
    "tree-template-scraping",
    "tree-template",
    "scraping",
    "pseudo-tree-template",
    "string-template-scraping",
    "string-template",
    "scraping",
    "indentation-based-template",
    "visual-template",
    "javascript-scraping",
    "javascript",
    "scraping",
    "npm-package",
    "browser-scraping",
    "nodejs-scraping",
    "node-js",
    "nodejs",
    "dom-traversal",
    "dom-manipulation",
    "frontend-scraping",
    "hierarchical-data-extraction",
    "nested-data-extraction",
    "attribute-extraction",
    "text-extraction",
    "web-automation",
    "content-extraction",
    "web-data-extraction"
  ],
  "author": "flatline",
  "license": "MIT",
  "bugs": {
    "url": "https://github.com/tmptrash/harvester/issues"
  },
  "homepage": "https://github.com/tmptrash/harvester#readme",
  "devDependencies": {
    "jest": "^29.7.0",
    "jsdom": "^26.0.0",
    "standard": "^17.1.2"
  }
}