tweet2media 0.2.0

Library to get media URLs from tweet URLs
Documentation 
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

use serde_json::Value;
use std::collections::HashSet;

pub(super) fn extract_media_urls(tweet: &Value) -> Vec<String> {
    let mut out = Vec::new();
    let mut seen = HashSet::new();

    let media_arrays = [
        tweet.pointer("/legacy/extended_entities/media"),
        tweet.pointer("/legacy/entities/media"),
        tweet.pointer("/extended_entities/media"),
        tweet.pointer("/entities/media"),
    ];

    for media_array in media_arrays.into_iter().flatten() {
        let Some(items) = media_array.as_array() else {
            continue;
        };

        for media in items {
            if media_unavailable(media) {
                continue;
            }

            if let Some(url) = best_video_url(media).or_else(|| image_url(media))
                && seen.insert(url.clone())
            {
                out.push(url);
            }
        }
    }

    out
}

fn media_unavailable(media: &Value) -> bool {
    media
        .pointer("/ext_media_availability/status")
        .and_then(Value::as_str)
        == Some("Unavailable")
}

fn best_video_url(media: &Value) -> Option<String> {
    let variants = media.pointer("/video_info/variants")?.as_array()?;

    variants
        .iter()
        .filter(|variant| {
            let url = variant
                .get("url")
                .and_then(Value::as_str)
                .unwrap_or_default();
            let content_type = variant
                .get("content_type")
                .and_then(Value::as_str)
                .unwrap_or_default();
            content_type == "video/mp4" || url.contains(".mp4")
        })
        .max_by_key(|variant| variant.get("bitrate").and_then(Value::as_u64).unwrap_or(0))
        .and_then(|variant| variant.get("url").and_then(Value::as_str))
        .or_else(|| {
            variants
                .iter()
                .max_by_key(|variant| variant.get("bitrate").and_then(Value::as_u64).unwrap_or(0))
                .and_then(|variant| variant.get("url").and_then(Value::as_str))
        })
        .map(str::to_string)
}

fn image_url(media: &Value) -> Option<String> {
    let url = media
        .get("media_url_https")
        .or_else(|| media.get("media_url"))
        .and_then(Value::as_str)?;
    Some(original_image_url(url))
}

fn original_image_url(url: &str) -> String {
    if url.contains("?format=") {
        if let Some((prefix, _)) = url.split_once("name=") {
            return format!("{prefix}name=orig");
        }
        return format!("{url}&name=orig");
    }

    let clean = url.split('?').next().unwrap_or(url);
    if let Some((base, ext)) = clean.rsplit_once('.') {
        return format!("{base}?format={ext}&name=orig");
    }

    url.to_string()
}

#[cfg(test)]
mod tests {
    use super::*;
    use serde_json::json;

    #[test]
    fn rewrites_image_to_original() {
        assert_eq!(
            original_image_url("https://pbs.twimg.com/media/abc.jpg"),
            "https://pbs.twimg.com/media/abc?format=jpg&name=orig"
        );
        assert_eq!(
            original_image_url("https://pbs.twimg.com/media/abc?format=png&name=small"),
            "https://pbs.twimg.com/media/abc?format=png&name=orig"
        );
    }

    #[test]
    fn extracts_images_and_best_video() {
        let tweet = json!({
            "legacy": {
                "extended_entities": {
                    "media": [
                        {"media_url_https": "https://pbs.twimg.com/media/a.jpg"},
                        {
                            "video_info": {
                                "variants": [
                                    {"content_type": "application/x-mpegURL", "url": "https://video.twimg.com/a.m3u8"},
                                    {"content_type": "video/mp4", "bitrate": 256000, "url": "https://video.twimg.com/a-low.mp4"},
                                    {"content_type": "video/mp4", "bitrate": 832000, "url": "https://video.twimg.com/a-high.mp4"}
                                ]
                            },
                            "media_url_https": "https://pbs.twimg.com/media/video-thumb.jpg"
                        }
                    ]
                }
            }
        });

        assert_eq!(
            extract_media_urls(&tweet),
            vec![
                "https://pbs.twimg.com/media/a?format=jpg&name=orig".to_string(),
                "https://video.twimg.com/a-high.mp4".to_string()
            ]
        );
    }
}