XY PubMed PDF Downloader

Download PDFs from PubMed Central (PMC) and Europe PMC. Use when the user needs to download open-access academic papers from PubMed Central using PMC ID, Pub...

Security Scan

The skill's code, instructions, and requirements are internally consistent: it only contacts NCBI/europepmc to convert IDs and fetch open-access PDFs and does not request unrelated credentials or perform suspicious I/O.

Purpose & Capability

The name/description (download open-access PDFs from PMC/Europe PMC) matches the included script and SKILL.md. The script implements PMC/PMID/DOI parsing, calls NCBI idconv endpoints and Europe PMC PDF rendering, and writes PDF files to a local output directory — all expected for this purpose.

Instruction Scope

SKILL.md only instructs running the bundled Python script and installing the requests library. The script only reads the provided identifier list or CLI argument and writes downloaded PDFs to a user-specified directory. It does not read unrelated system files, environment variables, or send data to unknown third parties.

Install Mechanism

There is no install spec; this is instruction-only plus a small Python script. The only third-party dependency is the widely used 'requests' library (documented in SKILL.md). No downloads from obscure URLs or archive extraction are present.

Credentials

The skill requests no environment variables, secrets, or credentials. That matches its functionality: it uses public NCBI/Europe PMC APIs and does not need auth. No disproportionate credential access is requested.

Persistence & Privilege

always is false and the skill does not modify other skills or system-wide settings. It runs as a simple CLI script and stores files only in a user-specified (or default) downloads directory.

Assessment

This skill appears to do exactly what it says: convert identifiers and download open-access PDFs from NCBI/EUROPE PMC. Before running, inspect the script (already included), run it in a controlled environment, and install only the documented dependency (pip install requests). Respect publisher terms and server load — the script includes a 1s delay for batch mode but avoid very large automated downloads. Because it performs network requests to public NCBI/europepmc endpoints and writes files locally, ensure you are comfortable with that and do not pass private identifiers or credentials (none are required).

下载 PubMed Central (PMC) 和 Europe PMC 开放获取论文的 PDF 文件。

功能

• 支持多种输入格式：PMC ID、PubMed URL、DOI
• 自动从 URL 中提取 PMC ID
• DOI 自动转换为 PMC ID
• 批量下载支持
• 自动回退到 Europe PMC

使用方法

单文件下载

python3 scripts/download_pmc_pdf.py <identifier>

支持的 identifier 格式：

• PMC ID: PMC12345678 或 12345678
• PubMed URL: https://pmc.ncbi.nlm.nih.gov/articles/PMC12345678/
• DOI: 10.3389/fcvm.2024.1368022

批量下载

创建文本文件 pmc_list.txt，每行一个 ID：

PMC12345678
PMC87654321
10.3389/fcvm.2024.1368022
https://pmc.ncbi.nlm.nih.gov/articles/PMC56789012/

运行：

python3 scripts/download_pmc_pdf.py --batch pmc_list.txt

选项

• -o, --output <dir>: 指定输出目录 (默认: ./downloads)
• -f, --filename <name>: 自定义文件名
• --batch <file>: 从文件批量下载

示例

# 下载单个 PDF
python3 scripts/download_pmc_pdf.py PMC12867338

# 指定输出目录
python3 scripts/download_pmc_pdf.py PMC12867338 -o ./papers

# 自定义文件名
python3 scripts/download_pmc_pdf.py PMC12867338 -f coronary_prediction.pdf

# 批量下载
python3 scripts/download_pmc_pdf.py --batch id_list.txt -o ./batch_downloads

注意事项

1. 仅支持开放获取 (Open Access) 的文章
2. 如果 PMC 下载失败，会自动尝试 Europe PMC
3. 批量下载时默认有 1 秒延迟，避免对服务器造成压力
4. 需要 requests 库：pip install requests

输出

下载的 PDF 文件保存在指定目录，默认命名格式：

• PMC{ID}.pdf (如 PMC12867338.pdf)

错误处理

• 404: 文章不存在或不是开放获取
• DOI 转换失败: 该 DOI 没有对应的 PMC 记录
• 其他网络错误会显示详细错误信息