hoot.go (view raw)
1//
2// Copyright (c) 2019 Ted Unangst <tedu@tedunangst.com>
3//
4// Permission to use, copy, modify, and distribute this software for any
5// purpose with or without fee is hereby granted, provided that the above
6// copyright notice and this permission notice appear in all copies.
7//
8// THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
9// WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
10// MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
11// ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
12// WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
13// ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
14// OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
15
16package main
17
18import (
19 "fmt"
20 "io"
21 "net/http"
22 "os"
23 "regexp"
24 "strings"
25
26 "github.com/andybalholm/cascadia"
27 "golang.org/x/net/html"
28 "humungus.tedunangst.com/r/webs/htfilter"
29)
30
31var tweetsel = cascadia.MustCompile("p.tweet-text")
32var linksel = cascadia.MustCompile("a.tweet-timestamp")
33var replyingto = cascadia.MustCompile(".ReplyingToContextBelowAuthor")
34var imgsel = cascadia.MustCompile("div.js-adaptive-photo img")
35var authorregex = regexp.MustCompile("twitter.com/([^/]+)")
36
37var re_hoots = regexp.MustCompile(`hoot: ?https://\S+`)
38var re_removepics = regexp.MustCompile(`pic\.twitter\.com/[[:alnum:]]+`)
39
40func hootextractor(r io.Reader, url string, seen map[string]bool) string {
41 root, err := html.Parse(r)
42 if err != nil {
43 elog.Printf("error parsing hoot: %s", err)
44 return url
45 }
46
47 url = strings.Replace(url, "mobile.twitter.com", "twitter.com", -1)
48 wantmatch := authorregex.FindStringSubmatch(url)
49 var wanted string
50 if len(wantmatch) == 2 {
51 wanted = wantmatch[1]
52 }
53
54 var htf htfilter.Filter
55 htf.Imager = func(node *html.Node) string {
56 return fmt.Sprintf(" <img src='%s'>", htfilter.GetAttr(node, "src"))
57 }
58
59 var buf strings.Builder
60 fmt.Fprintf(&buf, "%s\n", url)
61
62 divs := tweetsel.MatchAll(root)
63 for i, div := range divs {
64 twp := div.Parent.Parent.Parent
65 link := url
66 alink := linksel.MatchFirst(twp)
67 if alink == nil {
68 if i != 0 {
69 dlog.Printf("missing link")
70 continue
71 }
72 } else {
73 link = "https://twitter.com" + htfilter.GetAttr(alink, "href")
74 }
75 replto := replyingto.MatchFirst(twp)
76 if replto != nil {
77 continue
78 }
79 authormatch := authorregex.FindStringSubmatch(link)
80 if len(authormatch) < 2 {
81 dlog.Printf("no author?: %s", link)
82 continue
83 }
84 author := authormatch[1]
85 if wanted == "" {
86 wanted = author
87 }
88 if author != wanted {
89 continue
90 }
91 for img := imgsel.MatchFirst(twp); img != nil; imgsel.MatchFirst(twp) {
92 img.Parent.RemoveChild(img)
93 div.AppendChild(img)
94 }
95 text := htf.NodeText(div)
96 text = strings.Replace(text, "\n", " ", -1)
97 text = re_removepics.ReplaceAllString(text, "")
98
99 if seen[text] {
100 continue
101 }
102
103 fmt.Fprintf(&buf, "> @%s: %s\n", author, text)
104 seen[text] = true
105 }
106 return buf.String()
107}
108
109func hooterize(noise string) string {
110 seen := make(map[string]bool)
111
112 hootfetcher := func(hoot string) string {
113 url := hoot[5:]
114 if url[0] == ' ' {
115 url = url[1:]
116 }
117 url = strings.Replace(url, "mobile.twitter.com", "twitter.com", -1)
118 dlog.Printf("hooterizing %s", url)
119 req, err := http.NewRequest("GET", url, nil)
120 if err != nil {
121 ilog.Printf("error: %s", err)
122 return hoot
123 }
124 req.Header.Set("User-Agent", "Bot")
125 req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
126 req.Header.Set("Accept-Language", "en-US,en;q=0.9")
127 resp, err := http.DefaultClient.Do(req)
128 if err != nil {
129 ilog.Printf("error: %s", err)
130 return hoot
131 }
132 defer resp.Body.Close()
133 if resp.StatusCode != 200 {
134 ilog.Printf("error getting %s: %d", url, resp.StatusCode)
135 return hoot
136 }
137 ld, _ := os.Create("lasthoot.html")
138 r := io.TeeReader(resp.Body, ld)
139 return hootextractor(r, url, seen)
140 }
141
142 return re_hoots.ReplaceAllStringFunc(noise, hootfetcher)
143}