-
Notifications
You must be signed in to change notification settings - Fork 1
/
htmlextract_cliDef.go
174 lines (141 loc) · 5.22 KB
/
htmlextract_cliDef.go
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
////////////////////////////////////////////////////////////////////////////
// Program: htmlextract
// Purpose: HTML Extraction Tool
// Authors: Antonio Sun (c) 2018, All rights reserved
////////////////////////////////////////////////////////////////////////////
package main
import (
"github.com/go-easygen/cli"
clix "github.com/go-easygen/cli/ext"
)
////////////////////////////////////////////////////////////////////////////
// Constant and data type/structure definitions
//==========================================================================
// htmlextract
type rootT struct {
cli.Helper
Case int `cli:"c,case" usage:"1: lowercase tags, 2: uppercase, 0: no-change."`
Verbose cli.Counter `cli:"v,verbose" usage:"Verbose mode (Multiple -v options increase the verbosity.)"`
}
var root = &cli.Command{
Name: "htmlextract",
Desc: "HTML Extraction Tool\nVersion " + version + " built on " + date,
Text: "Tool to extract info from HTML",
Global: true,
Argv: func() interface{} { return new(rootT) },
Fn: htmlextract,
NumArg: cli.AtLeast(1),
}
// Template for main starts here
////////////////////////////////////////////////////////////////////////////
// Constant and data type/structure definitions
// The OptsT type defines all the configurable options from cli.
// type OptsT struct {
// Case int
// Verbose cli.Counter
// Verbose int
// }
////////////////////////////////////////////////////////////////////////////
// Global variables definitions
// var (
// progname = "htmlextract"
// version = "0.1.0"
// date = "2018-01-07"
// rootArgv *rootT
// // Opts store all the configurable options
// Opts OptsT
// )
////////////////////////////////////////////////////////////////////////////
// Function definitions
// Function main
// func main() {
// cli.SetUsageStyle(cli.ManualStyle) // up-down, for left-right, use NormalStyle
// //NOTE: You can set any writer implements io.Writer
// // default writer is os.Stdout
// if err := cli.Root(root,
// cli.Tree(outlineDef),
// cli.Tree(cleanDef),
// cli.Tree(h2mdDef)).Run(os.Args[1:]); err != nil {
// fmt.Fprintln(os.Stderr, err)
// }
// fmt.Println("")
// }
// Template for main dispatcher starts here
//==========================================================================
// Main dispatcher
// func htmlextract(ctx *cli.Context) error {
// ctx.JSON(ctx.RootArgv())
// ctx.JSON(ctx.Argv())
// fmt.Println()
// return nil
// }
// Template for CLI handling starts here
////////////////////////////////////////////////////////////////////////////
// outline
// func outlineCLI(ctx *cli.Context) error {
// rootArgv = ctx.RootArgv().(*rootT)
// argv := ctx.Argv().(*outlineT)
// fmt.Printf("[outline]:\n %+v\n %+v\n %v\n", rootArgv, argv, ctx.Args())
// Opts.Case, Opts.Verbose, Opts.Verbose =
// rootArgv.Case, rootArgv.Verbose, rootArgv.Verbose.Value()
// return nil
// }
type outlineT struct {
Filei *clix.Reader `cli:"*i,input" usage:"The file/url to extract from (mandatory)"`
Fileo *clix.Writer `cli:"o,output" usage:"The output outline file (default: input.json)"`
Attributes []string `cli:"a,attributes" usage:"extra attributes to include (may be more than one)"`
}
var outlineDef = &cli.Command{
Name: "outline",
Desc: "Extract HTML structure as outline",
Text: "Usage:\n htmlextract outline -i /tmp/f.html",
Argv: func() interface{} { return new(outlineT) },
Fn: outlineCLI,
NumOption: cli.AtLeast(1),
}
////////////////////////////////////////////////////////////////////////////
// clean
// func cleanCLI(ctx *cli.Context) error {
// rootArgv = ctx.RootArgv().(*rootT)
// argv := ctx.Argv().(*cleanT)
// fmt.Printf("[clean]:\n %+v\n %+v\n %v\n", rootArgv, argv, ctx.Args())
// Opts.Case, Opts.Verbose, Opts.Verbose =
// rootArgv.Case, rootArgv.Verbose, rootArgv.Verbose.Value()
// return nil
// }
type cleanT struct {
Filei *clix.Reader `cli:"*i,input" usage:"The file/url to extract from (mandatory)"`
Fileo *clix.Writer `cli:"*o,output" usage:"The output html file (mandatory)"`
}
var cleanDef = &cli.Command{
Name: "clean",
Desc: "Clean up HTML tags & attributes as much as possible",
Text: "Usage:\n htmlextract clean -i /tmp/fi.html -o /tmp/fo.html",
Argv: func() interface{} { return new(cleanT) },
Fn: cleanCLI,
NumArg: cli.AtLeast(1),
CanSubRoute: true,
}
////////////////////////////////////////////////////////////////////////////
// h2md
// func h2mdCLI(ctx *cli.Context) error {
// rootArgv = ctx.RootArgv().(*rootT)
// argv := ctx.Argv().(*h2mdT)
// fmt.Printf("[h2md]:\n %+v\n %+v\n %v\n", rootArgv, argv, ctx.Args())
// Opts.Case, Opts.Verbose, Opts.Verbose =
// rootArgv.Case, rootArgv.Verbose, rootArgv.Verbose.Value()
// return nil
// }
type h2mdT struct {
Filei *clix.Reader `cli:"*i,input" usage:"The file/url to extract from (mandatory)"`
Fileo *clix.Writer `cli:"o,output" usage:"The output .md file (default: input.md)"`
}
var h2mdDef = &cli.Command{
Name: "h2md",
Desc: "Convert HTML to .md file (on top of above clean up)",
Text: "Usage:\n htmlextract h2md -i /tmp/f.html",
Argv: func() interface{} { return new(h2mdT) },
Fn: h2mdCLI,
NumArg: cli.AtLeast(1),
CanSubRoute: true,
}