Araştırma Araçları & Kaynaklar

import re

INTERESTS = {
    "Superintegrability & Integrable Systems": [
        "superintegrable", "superintegrability", "liouville integrability",
        "integrable system", "lax pair", "hamilton-jacobi", "separation of variables"
    ],
    "Clifford Structures & Killing Geometries": [
        "clifford algebroid", "killing-yano", "super-carter", "carter constant",
        "spinor", "killing tensor", "hidden symmetry"
    ],
    "Linearization Instability & Gravitational Perturbations": [
        "linearization instability", "penrose diagram", "perturbed kerr",
        "perturbed schwarzschild", "linearized gravity", "gravitational perturbations"
    ],
    "Conserved Charges & Modified Gravity": [
        "conserved charges", "conserved quantities", "abbott-deser-tekin", "adt charges",
        "massive gravity", "topologically massive", "critical gravity", "gauss-bonnet"
    ]
}


def analyze_expanded_arxiv_mail(raw_text):
    raw_papers = re.split(r"-{10,}", raw_text)

    categorized_papers = {category: [] for category in INTERESTS}
    categorized_papers["Diğer (İlgi Alanı Dışı)"] = []

    for block in raw_papers:
        if not block.strip() or "Title:" not in block:
            continue

        title_match = re.search(
            r"Title:\s*(.*?)(?=\n(?:Authors:|Categories:|Comments:|Report-no:)|$)",
            block,
            re.DOTALL,
        )
        authors_match = re.search(
            r"Authors:\s*(.*?)(?=\n(?:Comments:|Categories:|MSC-class:|Report-no:|\\)|$)",
            block,
            re.DOTALL,
        )

        title = (
            title_match.group(1).replace("\n", " ").strip()
            if title_match
            else "Bilinmeyen Başlık"
        )

        authors_raw = (
            authors_match.group(1).replace("\n", " ").strip()
            if authors_match
            else "Bilinmeyen Yazarlar"
        )

        link_match = re.search(
            r"https://arxiv\.org/abs/\d{4}\.\d{4,5}",
            block,
        )

        if link_match:
            paper_link = link_match.group(0)
        else:
            id_match = re.search(r"arXiv:\d{4}\.\d{4,5}", block)
            paper_link = (
                f"https://arxiv.org/abs/{id_match.group(0).split(':')[1]}"
                if id_match
                else "Link Bulunamadı"
            )

        authors_cleaned = re.sub(r"\(.*?\)", "", authors_raw)
        clean_authors = [
            author.strip()
            for author in re.split(r",| and ", authors_cleaned)
            if author.strip()
        ]

        block_lower = block.lower()
        matched_any_category = False

        for category, keywords in INTERESTS.items():
            if any(keyword in block_lower for keyword in keywords):
                categorized_papers[category].append(
                    {
                        "title": title,
                        "authors": clean_authors,
                        "link": paper_link,
                    }
                )
                matched_any_category = True
                break

        if not matched_any_category:
            categorized_papers["Diğer (İlgi Alanı Dışı)"].append(
                {
                    "title": title,
                    "authors": clean_authors,
                    "link": paper_link,
                }
            )

    return categorized_papers


def print_results(categorized_data):
    for category, papers in categorized_data.items():
        if not papers:
            continue

        print(f"\n=== {category} ({len(papers)} Makale) ===")

        for index, paper in enumerate(papers, start=1):
            authors_str = ", ".join(paper["authors"])

            print(f"{index}. Başlık: {paper['title']}")
            print(f"   Yazarlar: {authors_str}")
            print(f"   Link: {paper['link']}")
            print("-" * 40)


mail_icerigi = r"""
E-POSTA İÇERİĞİNİ BURAYA YAPIŞTIRIN
"""

sonuc = analyze_expanded_arxiv_mail(mail_icerigi)
print_results(sonuc)

import arxiv


def fetch_arxiv_papers():
    main_topic_terms = ""
    first_subtopic_terms = ""
    second_subtopic_terms = ""
    third_subtopic_terms = ""

    queries = {}

    if main_topic_terms:
        queries["Ana konu"] = main_topic_terms

    if main_topic_terms and first_subtopic_terms:
        queries["Ana konu + Birinci alt konu"] = (
            f"({main_topic_terms}) AND ({first_subtopic_terms})"
        )

    if main_topic_terms and second_subtopic_terms:
        queries["Ana konu + İkinci alt konu"] = (
            f"({main_topic_terms}) AND ({second_subtopic_terms})"
        )

    if main_topic_terms and third_subtopic_terms:
        queries["Ana konu + Üçüncü alt konu"] = (
            f"({main_topic_terms}) AND ({third_subtopic_terms})"
        )

    if not queries:
        print("En az bir arama terimi veya sorgusu tanımlamalısınız.")
        return

    client = arxiv.Client(
        page_size=100,
        delay_seconds=3,
        num_retries=3,
    )

    unique_papers = {}

    for search_name, query in queries.items():
        print("\n" + "=" * 100)
        print(f"ARAMA BAŞLIĞI: {search_name}")
        print("=" * 100)

        search = arxiv.Search(
            query=query,
            max_results=100,
            sort_by=arxiv.SortCriterion.Relevance,
            sort_order=arxiv.SortOrder.Descending,
        )

        try:
            results = list(client.results(search))
        except Exception as error:
            print(f"Sorgu çalıştırılırken hata oluştu: {error}")
            continue

        print(f"Bu sorguda bulunan sonuç sayısı: {len(results)}")

        for paper in results:
            paper_id = paper.entry_id.rstrip("/").split("/")[-1]

            if paper_id not in unique_papers:
                unique_papers[paper_id] = {
                    "paper": paper,
                    "matched_searches": [],
                }

            unique_papers[paper_id]["matched_searches"].append(search_name)

    print("\n" + "#" * 100)
    print(f"TOPLAM BENZERSİZ MAKALE SAYISI: {len(unique_papers)}")
    print("#" * 100)

    if not unique_papers:
        print("Girilen sorgularla bağlantılı makale bulunamadı.")
        return

    keyword_scores = {}
    title_keyword_scores = {}
    ranked_papers = []

    for paper_id, data in unique_papers.items():
        paper = data["paper"]

        title = " ".join(paper.title.split()).lower()
        summary = " ".join(paper.summary.split()).lower()
        combined_text = f"{title} {summary}"

        score = 0

        for keyword, weight in keyword_scores.items():
            if keyword.lower() in combined_text:
                score += weight

        for keyword, weight in title_keyword_scores.items():
            if keyword.lower() in title:
                score += weight

        ranked_papers.append(
            {
                "score": score,
                "paper": paper,
                "matched_searches": data["matched_searches"],
            }
        )

    ranked_papers.sort(
        key=lambda item: (
            item["score"],
            item["paper"].published,
        ),
        reverse=True,
    )

    for index, item in enumerate(ranked_papers, start=1):
        paper = item["paper"]
        score = item["score"]

        authors = ", ".join(author.name for author in paper.authors)
        abstract = " ".join(paper.summary.split())
        published = paper.published.strftime("%d %B %Y")
        updated = paper.updated.strftime("%d %B %Y")

        print("\n" + "-" * 100)
        print(f"[{index}] İLGİ PUANI : {score}")
        print(f"BAŞLIK          : {paper.title}")
        print(f"YAZARLAR        : {authors}")
        print(f"YAYIN TARİHİ    : {published}")
        print(f"GÜNCELLEME      : {updated}")
        print(f"ANA KATEGORİ    : {paper.primary_category}")

        categories = ", ".join(paper.categories)
        print(f"TÜM KATEGORİLER : {categories}")
        print(f"ARXIV SAYFASI   : {paper.entry_id}")
        print(f"PDF             : {paper.pdf_url}")
        print(
            "EŞLEŞEN ARAMALAR: "
            + ", ".join(item["matched_searches"])
        )
        print(f"ÖZET            : {abstract}")


if __name__ == "__main__":
    fetch_arxiv_papers()

pip install arxiv