podpull 1.1.2

A fast, minimal CLI tool for downloading and synchronizing podcasts from RSS feeds
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
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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269

// This Source Code Form is subject to the terms of the Mozilla Public
// License, v. 2.0. If a copy of the MPL was not distributed with this
// file, You can obtain one at https://mozilla.org/MPL/2.0/.

use chrono::{DateTime, FixedOffset};
use html_escape::decode_html_entities;
use url::Url;

use crate::error::FeedError;

/// Represents a parsed podcast feed
#[derive(Debug, Clone)]
pub struct Podcast {
    pub title: String,
    pub description: Option<String>,
    pub link: Option<Url>,
    pub author: Option<String>,
    pub image_url: Option<Url>,
    pub feed_url: Url,
    pub episodes: Vec<Episode>,
}

/// Represents a single podcast episode
#[derive(Debug, Clone)]
pub struct Episode {
    pub title: String,
    pub description: Option<String>,
    pub pub_date: Option<DateTime<FixedOffset>>,
    pub guid: Option<String>,
    pub enclosure: Enclosure,
    pub duration: Option<String>,
    pub episode_number: Option<u32>,
    pub season_number: Option<u32>,
}

/// Represents the audio file attached to an episode
#[derive(Debug, Clone)]
pub struct Enclosure {
    pub url: Url,
    pub length: Option<u64>,
    pub mime_type: Option<String>,
}

/// Parse RSS feed XML bytes into a Podcast struct
pub fn parse_feed(xml_bytes: &[u8], feed_url: Url) -> Result<Podcast, FeedError> {
    let channel = rss::Channel::read_from(xml_bytes)?;

    let episodes = channel
        .items()
        .iter()
        .filter_map(|item| parse_episode(item).ok())
        .collect();

    let image_url = channel
        .image()
        .and_then(|img| Url::parse(img.url()).ok())
        .or_else(|| {
            channel
                .itunes_ext()
                .and_then(|ext| ext.image())
                .and_then(|url| Url::parse(url).ok())
        });

    let author = channel
        .itunes_ext()
        .and_then(|ext| ext.author().map(String::from))
        .or_else(|| channel.managing_editor().map(String::from));

    Ok(Podcast {
        title: decode_html_entities(channel.title()).into_owned(),
        description: Some(decode_html_entities(channel.description()).into_owned())
            .filter(|s| !s.is_empty()),
        link: Url::parse(channel.link()).ok(),
        author: author.map(|a| decode_html_entities(&a).into_owned()),
        image_url,
        feed_url,
        episodes,
    })
}

fn parse_episode(item: &rss::Item) -> Result<Episode, FeedError> {
    let title = item
        .title()
        .map(|t| decode_html_entities(t).into_owned())
        .unwrap_or_else(|| "Untitled Episode".to_string());

    let enclosure = item
        .enclosure()
        .ok_or_else(|| FeedError::MissingEnclosure {
            title: title.clone(),
        })?;

    let enclosure_url = Url::parse(enclosure.url())?;

    let pub_date = item.pub_date().and_then(|date_str| {
        DateTime::parse_from_rfc2822(date_str)
            .or_else(|_| parse_relaxed_date(date_str))
            .ok()
    });

    let guid = item
        .guid()
        .map(|g| g.value().to_string())
        .or_else(|| Some(enclosure.url().to_string()));

    let itunes = item.itunes_ext();

    Ok(Episode {
        title,
        description: item
            .description()
            .map(|d| decode_html_entities(d).into_owned()),
        pub_date,
        guid,
        enclosure: Enclosure {
            url: enclosure_url,
            length: enclosure.length().parse().ok(),
            mime_type: Some(enclosure.mime_type().to_string()).filter(|s| !s.is_empty()),
        },
        duration: itunes.and_then(|ext| ext.duration().map(String::from)),
        episode_number: itunes.and_then(|ext| ext.episode().and_then(|e| e.parse().ok())),
        season_number: itunes.and_then(|ext| ext.season().and_then(|s| s.parse().ok())),
    })
}

/// Try to parse dates that don't strictly conform to RFC 2822
fn parse_relaxed_date(date_str: &str) -> Result<DateTime<FixedOffset>, chrono::ParseError> {
    // Try common alternative formats
    let formats = [
        "%a, %d %b %Y %H:%M:%S %z",
        "%Y-%m-%dT%H:%M:%S%:z",
        "%Y-%m-%d %H:%M:%S %z",
    ];

    for format in formats {
        if let Ok(dt) = DateTime::parse_from_str(date_str, format) {
            return Ok(dt);
        }
    }

    // Last resort: try to parse and assume UTC
    Err(chrono::DateTime::parse_from_rfc2822("invalid").unwrap_err())
}

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

    const SAMPLE_FEED: &str = r#"<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd">
  <channel>
    <title>Test Podcast</title>
    <description>A test podcast for unit testing</description>
    <link>https://example.com</link>
    <itunes:author>Test Author</itunes:author>
    <itunes:image href="https://example.com/image.jpg"/>
    <item>
      <title>Episode 1</title>
      <description>First episode</description>
      <pubDate>Mon, 01 Jan 2024 12:00:00 +0000</pubDate>
      <guid>ep1-guid</guid>
      <enclosure url="https://example.com/ep1.mp3" length="1234567" type="audio/mpeg"/>
      <itunes:duration>30:00</itunes:duration>
      <itunes:episode>1</itunes:episode>
      <itunes:season>1</itunes:season>
    </item>
    <item>
      <title>Episode 2</title>
      <enclosure url="https://example.com/ep2.mp3" type="audio/mpeg"/>
    </item>
  </channel>
</rss>"#;

    #[test]
    fn parse_feed_extracts_podcast_metadata() {
        let feed_url = Url::parse("https://example.com/feed.xml").unwrap();
        let podcast = parse_feed(SAMPLE_FEED.as_bytes(), feed_url.clone()).unwrap();

        assert_eq!(podcast.title, "Test Podcast");
        assert_eq!(
            podcast.description,
            Some("A test podcast for unit testing".to_string())
        );
        assert_eq!(podcast.author, Some("Test Author".to_string()));
        assert_eq!(podcast.feed_url, feed_url);
    }

    #[test]
    fn parse_feed_extracts_episodes() {
        let feed_url = Url::parse("https://example.com/feed.xml").unwrap();
        let podcast = parse_feed(SAMPLE_FEED.as_bytes(), feed_url).unwrap();

        assert_eq!(podcast.episodes.len(), 2);

        let ep1 = &podcast.episodes[0];
        assert_eq!(ep1.title, "Episode 1");
        assert_eq!(ep1.guid, Some("ep1-guid".to_string()));
        assert_eq!(ep1.duration, Some("30:00".to_string()));
        assert_eq!(ep1.episode_number, Some(1));
        assert_eq!(ep1.season_number, Some(1));
        assert_eq!(ep1.enclosure.length, Some(1234567));
    }

    #[test]
    fn parse_feed_handles_missing_optional_fields() {
        let feed_url = Url::parse("https://example.com/feed.xml").unwrap();
        let podcast = parse_feed(SAMPLE_FEED.as_bytes(), feed_url).unwrap();

        let ep2 = &podcast.episodes[1];
        assert_eq!(ep2.title, "Episode 2");
        assert!(ep2.pub_date.is_none());
        assert!(ep2.duration.is_none());
        assert!(ep2.episode_number.is_none());
    }

    #[test]
    fn parse_feed_skips_items_without_enclosure() {
        let feed_no_enclosure = r#"<?xml version="1.0"?>
<rss version="2.0">
  <channel>
    <title>Test</title>
    <description>Test</description>
    <item>
      <title>No Audio</title>
    </item>
  </channel>
</rss>"#;

        let feed_url = Url::parse("https://example.com/feed.xml").unwrap();
        let podcast = parse_feed(feed_no_enclosure.as_bytes(), feed_url).unwrap();
        assert!(podcast.episodes.is_empty());
    }

    #[test]
    fn parse_feed_decodes_html_entities() {
        // Uses numeric character references (&#8212; for em dash, &#8230; for ellipsis)
        // which are valid in XML and decoded by html_escape
        let feed_with_entities = r#"<?xml version="1.0"?>
<rss version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd">
  <channel>
    <title>Tom &amp; Jerry&apos;s &quot;Show&quot;</title>
    <description>A show about &lt;cats&gt; &amp; dogs</description>
    <itunes:author>Tom &amp; Jerry</itunes:author>
    <item>
      <title>Episode: &quot;The Chase&quot; &#8212; Part 1</title>
      <description>Jerry escapes &amp; Tom chases&#8230;</description>
      <enclosure url="https://example.com/ep.mp3" type="audio/mpeg"/>
    </item>
  </channel>
</rss>"#;

        let feed_url = Url::parse("https://example.com/feed.xml").unwrap();
        let podcast = parse_feed(feed_with_entities.as_bytes(), feed_url).unwrap();

        assert_eq!(podcast.title, "Tom & Jerry's \"Show\"");
        assert_eq!(
            podcast.description,
            Some("A show about <cats> & dogs".to_string())
        );
        assert_eq!(podcast.author, Some("Tom & Jerry".to_string()));

        let ep = &podcast.episodes[0];
        assert_eq!(ep.title, "Episode: \"The Chase\" — Part 1");
        assert_eq!(
            ep.description,
            Some("Jerry escapes & Tom chases…".to_string())
        );
    }
}