Struct PmcTarClient 

pub struct PmcTarClient { /* private fields */ }

TAR extraction client for PMC Open Access articles

Implementations

impl PmcTarClient

pub fn new(config: ClientConfig) -> Self

Create a new PMC TAR client with configuration

pub async fn download_and_extract_tar<P: AsRef<Path>>( &self, pmcid: &str, output_dir: P, ) -> Result<Vec<String>>

Download and extract tar.gz file for a PMC article using the OA API

Arguments

• pmcid - PMC ID (with or without “PMC” prefix)
• output_dir - Directory to extract the tar.gz contents to

Returns

Returns a Result<Vec<String>> containing the list of extracted file paths

Errors

• ParseError::InvalidPmid - If the PMCID format is invalid
• PubMedError::RequestError - If the HTTP request fails
• ParseError::IoError - If file operations fail
• ParseError::PmcNotAvailable - If the article is not available in OA

Example

use pubmed_client::pmc::tar::PmcTarClient;
use pubmed_client::ClientConfig;
use std::path::Path;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = ClientConfig::new();
    let client = PmcTarClient::new(config);
    let output_dir = Path::new("./extracted_articles");
    let files = client.download_and_extract_tar("PMC7906746", output_dir).await?;

    for file in files {
        println!("Extracted: {}", file);
    }
    Ok(())
}

pub async fn extract_figures_with_captions<P: AsRef<Path>>( &self, pmcid: &str, output_dir: P, ) -> Result<Vec<ExtractedFigure>>

Download, extract tar.gz file, and match figures with their captions from XML

Arguments

• pmcid - PMC ID (with or without “PMC” prefix)
• output_dir - Directory to extract the tar.gz contents to

Returns

Returns a Result<Vec<ExtractedFigure>> containing figures with both XML metadata and file paths

Errors

• ParseError::InvalidPmid - If the PMCID format is invalid
• PubMedError::RequestError - If the HTTP request fails
• ParseError::IoError - If file operations fail
• ParseError::PmcNotAvailable - If the article is not available in OA

Example

use pubmed_client::pmc::tar::PmcTarClient;
use pubmed_client::ClientConfig;
use std::path::Path;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = ClientConfig::new();
    let client = PmcTarClient::new(config);
    let output_dir = Path::new("./extracted_articles");
    let figures = client.extract_figures_with_captions("PMC7906746", output_dir).await?;

    for figure in figures {
        println!("Figure {}: {}", figure.figure.id, figure.figure.caption);
        println!("File: {}", figure.extracted_file_path);
    }
    Ok(())
}

pub fn find_matching_file( figure: &Figure, extracted_files: &[String], image_extensions: &[&str], ) -> Option<String>

Find a matching file for a figure based on ID, label, or filename patterns

Trait Implementations

impl Clone for PmcTarClient

fn clone(&self) -> PmcTarClient

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.