Convert Zotero CSV exports to Marp markdown slides with PubMed abstracts and ChatGPT-summarized bullet points. Usage: `python script.py -f collection.csv`

zotero_csv_to_marp_slide.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Zotero CSV to Marp Slide Generator
Converts Zotero bibliography exports (CSV format) into Marp-compatible markdown presentations.
Fetches PubMed abstracts via DOI, summarizes with ChatGPT into bullet points.

Dependencies: openai, pandas, biopython, requests
Usage: python script.py -f zotero_export.csv
Output: output.md (marp-compatible presentation)
"""

import os
import re
import subprocess
import sys

import openai
import pandas as pd
import requests
from Bio import Entrez

def respond(prompt):
    openai.api_key = "YOUR_API_KEY"
    completions = openai.Completion.create(
        engine="text-davinci-002",
        prompt=prompt,
        max_tokens=1000,
        n=1,
        stop=None,
        temperature=0.5,
    )

    message = completions.choices[0].text
    return message


def doi_to_pmid(doi):
    """Convert DOI to PubMed ID via NCBI esearch API."""
    base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
    params = {"db": "pubmed", "term": f"{doi}[DOI]", "retmode": "json"}

    response = requests.get(base_url, params=params)
    response_json = response.json()

    if "esearchresult" in response_json and "idlist" in response_json[
            "esearchresult"]:
        pmids = response_json["esearchresult"]["idlist"]
        if pmids:
            return pmids[0]
    return None


def get_abstract_from_pmid(pmid):
    """Fetch abstract text from PubMed ID."""
    # NCBI 要求提供聯絡信箱；設環境變數 NCBI_EMAIL 即可
    Entrez.email = os.environ.get("NCBI_EMAIL", "your-email@example.com")
    handle = Entrez.efetch(db="pubmed", id=pmid, retmode="xml")
    records = Entrez.read(handle)
    try:
        abstract = records["PubmedArticle"][0]["MedlineCitation"]["Article"][
            "Abstract"]["AbstractText"][0]
    except (KeyError, IndexError):
        abstract = "Abstract not available"

    return abstract


def get_abstract(doi):
    """Retrieve abstract from DOI."""
    pmid = doi_to_pmid(doi)
    print(pmid)
    if pmid:
        return get_abstract_from_pmid(pmid)
    else:
        print("No DOI Found")
        return None


def clean_text(string):
    """Format bullet points with slide separators every 3 items."""
    lines = string.split("\n")
    filtered_lines = [line for line in lines if line.startswith("- ")]
    grouped_lines = []
    for i in range(0, len(filtered_lines), 3):
        grouped_lines.extend(filtered_lines[i:i + 3])
        if i + 3 < len(filtered_lines):
            grouped_lines.append("\n\n---\n\n")

    return "\n".join(grouped_lines)


def extract_plain_text_line_by_line(string: str) -> str:
    """Extract plain text from HTML-formatted notes."""
    lines = re.split(r"<\/[^>]+>", string)
    lines = [
        re.sub(r"<[^>]+>", "", line).strip() for line in lines
        if re.sub(r"<[^>]+>", "", line).strip()
    ]

    combined = "- " + "\n- ".join(lines)
    combined = clean_text(combined)
    return combined


if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: script_name.py -f filename.csv")
        sys.exit(1)

    flag, filename = sys.argv[1], sys.argv[2]

    if flag != "-f":
        print("Usage: script_name.py -f filename.csv")
        sys.exit(1)

    df = pd.read_csv(filename)
    doi_list = df["DOI"].dropna().unique().tolist()
    markdown_content = "# Title Page\n\n---\n\n"

    for doi in doi_list:
        title = df[df["DOI"] == doi]["Title"].iloc[0]
        note = df[df["DOI"] == doi]["Notes"].iloc[0]
        if isinstance(note, str) and len(note) > 0:
            cleaned_note = (f"## {title}\n\n### Hightlights\n\n" +
                            extract_plain_text_line_by_line(note) +
                            "\n\n---\n\n")
        else:
            cleaned_note = ""
        print(title)
        abstract = get_abstract(doi)
        response = respond(
            f"transferred to bullet points in markdown, like '- content\n- content' here are the context:\n{abstract}"
        )
        lines = [line for line in response.splitlines() if line.strip()]
        bullet_points = "\n".join(lines)
        bullet_points = clean_text(bullet_points)
        year = df[df["DOI"] == doi]["Publication Year"].iloc[0]

        markdown_content += f"{cleaned_note}## {title}\n\n### Summary\n\n{bullet_points}\n\n<!-- {abstract} -->\n\n> {title} ({year}). DOI: {doi}\n\n---\n\n"

    markdown_content += "\n\n## Thank You for Your Listening\n"
    with open("output.md", "w") as file:
        file.write(markdown_content)