rss/atom.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
package rss
import (
"bytes"
"encoding/xml"
"fmt"
"time"
)
func parseAtom(data []byte) (*Feed, error) {
warnings := false
feed := atomFeed{}
p := xml.NewDecoder(bytes.NewReader(data))
p.Strict = false
p.CharsetReader = charsetReader
err := p.Decode(&feed)
if err != nil {
return nil, err
}
out := new(Feed)
out.Title = feed.Title
out.Description = feed.Description
for _, link := range feed.Link {
if link.Rel == "alternate" || link.Rel == "" {
out.Link = link.Href
break
}
}
out.Image = feed.Image.Image()
out.Refresh = time.Now().Add(DefaultRefreshInterval)
out.Items = make([]*Item, 0, len(feed.Items))
out.ItemMap = make(map[string]struct{})
// Process items.
for _, item := range feed.Items {
// Skip items already known.
if _, ok := out.ItemMap[item.ID]; ok {
continue
}
next := new(Item)
next.Title = item.Title
next.Summary = item.Summary
next.Content = item.Content.RAWContent
if item.Date != "" {
next.Date, err = parseTime(item.Date)
if err == nil {
next.DateValid = true
}
}
next.ID = item.ID
for _, link := range item.Links {
if link.Rel == "alternate" || link.Rel == "" {
next.Link = link.Href
} else {
next.Enclosures = append(next.Enclosures, &Enclosure{
URL: link.Href,
Type: link.Type,
Length: link.Length,
})
}
}
next.Read = false
if next.ID == "" {
if debug {
fmt.Printf("[w] Item %q has no ID and will be ignored.\n", next.Title)
fmt.Printf("[w] %#v\n", item)
}
warnings = true
continue
}
if _, ok := out.ItemMap[next.ID]; ok {
if debug {
fmt.Printf("[w] Item %q has duplicate ID.\n", next.Title)
fmt.Printf("[w] %#v\n", next)
}
warnings = true
continue
}
out.Items = append(out.Items, next)
out.ItemMap[next.ID] = struct{}{}
out.Unread++
}
if warnings && debug {
fmt.Printf("[i] Encountered warnings:\n%s\n", data)
}
return out, nil
}
type RAWContent struct {
RAWContent string `xml:",innerxml"`
}
type atomFeed struct {
XMLName xml.Name `xml:"feed"`
Title string `xml:"title"`
Description string `xml:"subtitle"`
Link []atomLink `xml:"link"`
Image atomImage `xml:"image"`
Items []atomItem `xml:"entry"`
Updated string `xml:"updated"`
}
type atomItem struct {
XMLName xml.Name `xml:"entry"`
Title string `xml:"title"`
Summary string `xml:"summary"`
Content RAWContent `xml:"content"`
Links []atomLink `xml:"link"`
Date string `xml:"updated"`
DateValid bool
ID string `xml:"id"`
}
type atomImage struct {
XMLName xml.Name `xml:"image"`
Title string `xml:"title"`
URL string `xml:"url"`
Height int `xml:"height"`
Width int `xml:"width"`
}
type atomLink struct {
Href string `xml:"href,attr"`
Rel string `xml:"rel,attr"`
Type string `xml:"type,attr"`
Length uint `xml:"length,attr"`
}
func (a *atomImage) Image() *Image {
out := new(Image)
out.Title = a.Title
out.URL = a.URL
out.Height = uint32(a.Height)
out.Width = uint32(a.Width)
return out
}