aboutsummaryrefslogtreecommitdiff
path: root/main.go
blob: d41be58e057066b19aa95fcff6b804675cdc2798 (plain)
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
175
176
177
178
179
180
181
182
183
184
185
186
187
package main

import (
	"code.google.com/p/go-html-transform/h5"
	"code.google.com/p/go-html-transform/html/transform"
	"code.google.com/p/go.net/html"
	"code.google.com/p/go.tools/blog/atom"
	"encoding/xml"
	"fmt"
	"io"
	"net/http"
	"os"
	"strconv"
	"time"
)

func getattr(attrs []html.Attribute, name string) (val string, found bool) {
	for _, a := range attrs {
		if a.Key == name {
			val = a.Val
			found = true
			return
		}
	}

	return
}

func Textify(node *html.Node) string {
	switch node.Type {
	case html.TextNode:
		return node.Data
	case html.ElementNode:
		for _, att := range node.Attr {
			if att.Key == "alt" {
				return att.Val
			}
		}

		fallthrough
	case html.DocumentNode:
		text := ""
		for n := node.FirstChild; n != nil; n = n.NextSibling {
			text += Textify(n)
		}
		return text
	default:
		return ""
	}
}

type Tweet struct {
	Content string
	From    string
	ID      string
	Date    time.Time
}

func ScrapeTweets(r io.Reader) ([]Tweet, error) {
	t, err := transform.NewFromReader(r)
	if err != nil {
		return nil, fmt.Errorf("Could not scrape profile: %s", err)
	}

	tweets := make([]Tweet, 0)

	t.Apply(func(node *html.Node) {
		var tweet Tweet

		tweet.From, _ = getattr(node.Attr, "data-screen-name")
		tweet.ID, _ = getattr(node.Attr, "data-item-id")

		time_ok := false
		tree := h5.NewTree(node)
		t2 := transform.New(&tree)
		t2.Apply(func(node *html.Node) {
			if ts, ok := getattr(node.Attr, "data-time"); ok {
				if ts_int, err := strconv.ParseInt(ts, 10, 64); err == nil {
					tweet.Date = time.Unix(ts_int, 0)
					time_ok = true
				}
			}
		}, "a.ProfileTweet-timestamp span")
		if !time_ok {
			return
		}

		t2.Apply(func(node *html.Node) {
			tweet.Content = Textify(node)
		}, ".ProfileTweet-text")

		tweets = append(tweets, tweet)

	}, "div.GridTimeline .ProfileTweet")

	return tweets, nil
}

const titlelimit = 80

func (t Tweet) Atomify() *atom.Entry {
	entry := new(atom.Entry)

	entry.Title = "@" + t.From + ": " + t.Content
	if len(entry.Title) > titlelimit {
		entry.Title = string([]rune(entry.Title)[:titlelimit-2]) + " …"
	}

	url := "https://twitter.com/" + t.From + "/status/" + t.ID
	entry.ID = url
	entry.Link = []atom.Link{atom.Link{
		Rel:  "alternate",
		Href: url,
	}}
	entry.Summary = &atom.Text{Type: "text", Body: t.Content}
	entry.Content = &atom.Text{Type: "text", Body: t.Content}
	entry.Author = &atom.Person{
		Name: "@" + t.From,
		URI:  "https://twitter.com/" + t.From,
	}
	entry.Published = atom.Time(t.Date)
	entry.Updated = atom.Time(t.Date)

	return entry
}

func main() {
	os.Exit(Main())
}

func Main() int {
	if len(os.Args) < 2 {
		fmt.Fprintln(os.Stderr, "Need one argument (twitter user name, without the '@')")
		return 1
	}

	user := os.Args[1]

	resp, err := http.Get("https://twitter.com/" + user)
	if err != nil {
		fmt.Fprintf(os.Stderr, "Couldn't download @%s's stream: %s\n", user, err)
		return 1
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		fmt.Fprintf(os.Stderr, "Couldn't download @%s's stream: HTTP Status %d %s\n", user, resp.StatusCode, resp.Status)
		return 1
	}

	tweets, err := ScrapeTweets(resp.Body)
	if err != nil {
		fmt.Fprintln(os.Stderr, err)
	}

	feed := atom.Feed{
		Title: "Tweets from @" + user,
		ID:    "https://twitter.com/" + user,
		Link: []atom.Link{
			atom.Link{
				Rel:  "alternate",
				Href: "http://twitter.com/" + user,
			},
		},
		Author: &atom.Person{
			Name: "@" + user,
			URI:  "https://twitter.com/" + user,
		},
	}

	var latest time.Time
	for _, tweet := range tweets {
		feed.Entry = append(feed.Entry, tweet.Atomify())
		if tweet.Date.After(latest) {
			latest = tweet.Date
		}
	}

	feed.Updated = atom.Time(latest)

	enc := xml.NewEncoder(os.Stdout)
	if err := enc.Encode(feed); err != nil {
		fmt.Fprintf(os.Stderr, "Could not encode feed: %s\n", err)
		return 1
	}
	return 0
}