gthings 0.6.4

CLI binary for gthings — browser-automated web research toolkit
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

//! `gthings extract` and `gthings pdf` — content extraction from URLs, PDFs.

use crate::commands::print_error;
use gthings_common::pagination::ExtractParams;
use gthings_extraction::PdfExtractor;
use gthings_extraction::article::format_as_markdown;
use gthings_extraction::dispatch::AutoExtractor;

/// Extract content from any URL using auto-detection.
pub(crate) async fn cmd_extract(url: &str, max_chars: usize, offset: usize, json: bool) -> i32 {
    let client = reqwest::Client::builder()
        .user_agent("Mozilla/5.0 (compatible; gthings/0.5)")
        .timeout(std::time::Duration::from_secs(30))
        .build()
        .expect("reqwest Client::builder() with default config should never fail");

    let extractor = AutoExtractor::new(client);
    let params = ExtractParams { offset, max_chars };
    match extractor.extract(url, params).await {
        Ok(article) => {
            if json {
                println!(
                    "{}",
                    serde_json::to_string_pretty(&article).unwrap_or_else(|e| {
                        tracing::error!("JSON serialization failed: {e}");
                        String::new()
                    })
                );
            } else {
                println!("{}", format_as_markdown(&article));
            }
            0
        }
        Err(e) => {
            print_error(
                "EXTRACT_FAILED",
                &e.to_string(),
                "Check URL and connectivity",
            );
            1
        }
    }
}

/// Extract text from PDF at URL.
pub(crate) async fn cmd_pdf_url(url: &str, max_chars: usize, offset: usize, json: bool) -> i32 {
    let client = reqwest::Client::builder()
        .user_agent("Mozilla/5.0 (compatible; gthings/0.5)")
        .timeout(std::time::Duration::from_secs(30))
        .build()
        .expect("reqwest Client::builder() with default config should never fail");

    let resp = match client.get(url).send().await {
        Ok(r) => r,
        Err(e) => {
            print_error("PDF_FETCH_FAILED", &e.to_string(), "Check URL");
            return 1;
        }
    };

    if !resp.status().is_success() {
        print_error(
            "PDF_HTTP_ERROR",
            &format!("HTTP {}", resp.status()),
            "Verify URL",
        );
        return 1;
    }

    let bytes = match resp.bytes().await {
        Ok(b) => b.to_vec(),
        Err(e) => {
            print_error("PDF_READ_FAILED", &e.to_string(), "Retry");
            return 1;
        }
    };

    let extractor = PdfExtractor;
    let params = ExtractParams { offset, max_chars };
    match extractor.extract_article(url, &bytes, &params) {
        Ok(article) => {
            if json {
                println!(
                    "{}",
                    serde_json::to_string_pretty(&article).unwrap_or_else(|e| {
                        tracing::error!("JSON serialization failed: {e}");
                        String::new()
                    })
                );
            } else {
                println!("{}", format_as_markdown(&article));
            }
            0
        }
        Err(e) => {
            print_error("PDF_EXTRACT_FAILED", &e.to_string(), "Try a different PDF");
            1
        }
    }
}

/// Extract text from local PDF file.
pub(crate) async fn cmd_pdf_file(
    path: &std::path::Path,
    max_chars: usize,
    offset: usize,
    json: bool,
) -> i32 {
    let bytes = match tokio::fs::read(path).await {
        Ok(b) => b,
        Err(e) => {
            print_error("PDF_READ_FAILED", &e.to_string(), "Check file path");
            return 1;
        }
    };

    let url = format!("file://{}", path.display());
    let extractor = PdfExtractor;
    let params = ExtractParams { offset, max_chars };
    match extractor.extract_article(&url, &bytes, &params) {
        Ok(article) => {
            if json {
                println!(
                    "{}",
                    serde_json::to_string_pretty(&article).unwrap_or_else(|e| {
                        tracing::error!("JSON serialization failed: {e}");
                        String::new()
                    })
                );
            } else {
                println!("{}", format_as_markdown(&article));
            }
            0
        }
        Err(e) => {
            print_error(
                "PDF_EXTRACT_FAILED",
                &e.to_string(),
                "File may not be a valid PDF",
            );
            1
        }
    }
}