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
|
package main
import (
"io"
"strconv"
"strings"
"time"
"golang.org/x/net/html"
)
// parse takes an io.Reader which is supposed to be an entire web page (like http.Response.Body)
// and returns the separate posts found inside.
func parse(r io.Reader) (c *channel, err error) {
c = &channel{}
doc, err := html.Parse(r)
if err != nil {
return
}
var f func(*html.Node)
f = func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "meta" {
var prop string
for _, a := range n.Attr {
if a.Key == "property" {
prop = a.Val
}
if a.Key == "content" {
switch prop {
case "og:title":
c.Title = a.Val
case "og:description":
c.Description = a.Val
}
}
}
}
if n.Type == html.ElementNode && n.Data == "div" {
for _, a := range n.Attr {
if a.Key == "class" && strings.Contains(a.Val, "userContentWrapper") {
var p post
parseNode(n, &p)
c.Items = append(c.Items, &p)
break
}
}
}
// loop further down
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c)
}
}
f(doc)
return
}
func parseNode(n *html.Node, p *post) {
if n.Type == html.ElementNode {
switch n.Data {
// fetch time stamp from header
case "abbr":
for _, attr := range n.Attr {
if attr.Key == "data-utime" {
unix, _ := strconv.ParseInt(attr.Val, 10, 64)
p.Time = time.Unix(unix, 0)
return
}
}
// skip post header with name of group and check-in
case "h5":
return
// skip "show more" and aria-hidden stuff
case "span":
fallthrough
case "a":
for _, attr := range n.Attr {
if attr.Key == "class" && attr.Val == "text_exposed_hide" {
return
}
if attr.Key == "aria-hidden" && attr.Val == "true" {
return
}
}
// parse paragraphs
case "p":
parseParagraph(n, p)
p.Content += "\n\n"
return
// get images
case "img":
parseImage(n, p)
return
}
}
// fetch all pure text elements outside proper post paragraphs
if n.Type == html.TextNode {
p.Content += n.Data + "\n"
}
// loop deeper
for c := n.FirstChild; c != nil; c = c.NextSibling {
parseNode(c, p)
}
}
func parseParagraph(n *html.Node, p *post) {
// fetch all pure text elements
if n.Type == html.TextNode {
p.Content += n.Data
}
// loop deeper
for c := n.FirstChild; c != nil; c = c.NextSibling {
parseParagraph(c, p)
}
}
func parseImage(n *html.Node, p *post) {
img := &image{}
for _, attr := range n.Attr {
switch attr.Key {
case "src":
img.Source = attr.Val
case "alt":
fallthrough
case "title":
fallthrough
case "aria-label":
img.Caption = attr.Val
}
}
p.Images = append(p.Images, img)
}
|