academic-search-mcp 0.1.3__py3-none-any.whl → 0.1.4b1__py3-none-any.whl

{academic_search_mcp-0.1.3.dist-info → academic_search_mcp-0.1.4b1.dist-info}/METADATA

@@ -1,8 +1,9 @@
 Metadata-Version: 2.4
 Name: academic-search-mcp
-Version: 0.1.3
+Version: 0.1.4b1
 Summary: A MCP server for searching and downloading academic papers from multiple sources.
 Author-email: "P.S Zhang" <pengsongzhang96@gmail.com>
+Maintainer-email: "Zadneprovskiy A. A." <zadneprovskiy_econ@mail.ru>
 License-File: LICENSE
 Requires-Python: >=3.10
 Requires-Dist: beautifulsoup4>=4.12.0

{academic_search_mcp-0.1.3.dist-info → academic_search_mcp-0.1.4b1.dist-info}/RECORD

@@ -1,13 +1,13 @@
 paper_search_mcp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 paper_search_mcp/paper.py,sha256=Flrn3ORhsojiEdEldUtKPvGF1RivXhl84zzq8mqAeFI,2969
-paper_search_mcp/pdf_utils.py,sha256=sylqOQTFyOSlYnEzUMpSIe4VkY2kfgaQw_xd_EBYw2g,1909
+paper_search_mcp/pdf_utils.py,sha256=kcutoE_HGrtaoheY9cFN0GW4LVkG-HnN54Mc15LPD44,2009
 paper_search_mcp/server.py,sha256=C542TF00oOUHF38F_5OU43D9RmIWQZSk7UiFHcXukWA,21663
 paper_search_mcp/academic_platforms/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 paper_search_mcp/academic_platforms/arxiv.py,sha256=5SsFudqH1PIXIEE_8saCQHcf75bqCL6ApRUltLpp9Ow,5911
 paper_search_mcp/academic_platforms/biorxiv.py,sha256=4k1Bg2BW-RBJiZ9jRVVmCEOge_4MtEDtXq2tMaPV0cg,6799
 paper_search_mcp/academic_platforms/core.py,sha256=6xDq3NmlVh1NIEFnTRLPNayodkztrS7CPUC-jupd-Lw,9632
 paper_search_mcp/academic_platforms/crossref.py,sha256=Zxj4U6SejaCa5o7whRmjjHVdd1U1H-DVtRP6DWzPwjk,14773
-paper_search_mcp/academic_platforms/cyberleninka.py,sha256=88p9RZxjBRn5jAaOhZLr3EpP5ibMzmd0vCh1jD6PPEs,13421
+paper_search_mcp/academic_platforms/cyberleninka.py,sha256=X6ka5QqE7pagDPcq0dZq0EXoDeKBzjq7XJYAQw3AA_g,16656
 paper_search_mcp/academic_platforms/google_scholar.py,sha256=B8VqgauJy3RJ8nR9woe107CXM-DrHQPapQAg_f948yg,9269
 paper_search_mcp/academic_platforms/hub.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 paper_search_mcp/academic_platforms/iacr.py,sha256=Vem7q18NZRm5WXsDHsqRefyRIpl4PCceGGWYXhbXB2s,21135
@@ -17,8 +17,8 @@ paper_search_mcp/academic_platforms/pubmed.py,sha256=oS-JRHNI7lcCqxUGTlSVKp2i_QK
 paper_search_mcp/academic_platforms/sci_hub.py,sha256=oma3M_gUseDByh-0Awi8Sxr0g3yojrb8XoD9iV0Exo8,7334
 paper_search_mcp/academic_platforms/semantic.py,sha256=nk7nzrlsnrDNrHNUuRIfIBQfagfAT750J5HtdLputHQ,20594
 paper_search_mcp/academic_platforms/ssrn.py,sha256=ntf22HRBZwNY6ctG5rdXjD5iT7CaML8k_xBbCn_qjbg,13694
-academic_search_mcp-0.1.3.dist-info/METADATA,sha256=uZcbHayXO9tURHo3Yl7P50e4j3v4p20a7GoPbtlLTe4,7203
-academic_search_mcp-0.1.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-academic_search_mcp-0.1.3.dist-info/entry_points.txt,sha256=RO1wFwD6a0WO_mZY8HZBYDtITfQ1dhnTR1BZlCrkRLc,69
-academic_search_mcp-0.1.3.dist-info/licenses/LICENSE,sha256=TwRnWq1drFhdcy43SdxndU0mcfBUYBnhSJTJ4hhjfwQ,1085
-academic_search_mcp-0.1.3.dist-info/RECORD,,
+academic_search_mcp-0.1.4b1.dist-info/METADATA,sha256=F3uHgcJYLLX58tRDUCGXhCoVkjc00C-qLrklwT_YJPE,7274
+academic_search_mcp-0.1.4b1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+academic_search_mcp-0.1.4b1.dist-info/entry_points.txt,sha256=RO1wFwD6a0WO_mZY8HZBYDtITfQ1dhnTR1BZlCrkRLc,69
+academic_search_mcp-0.1.4b1.dist-info/licenses/LICENSE,sha256=TwRnWq1drFhdcy43SdxndU0mcfBUYBnhSJTJ4hhjfwQ,1085
+academic_search_mcp-0.1.4b1.dist-info/RECORD,,

paper_search_mcp/academic_platforms/cyberleninka.py

@@ -379,7 +379,9 @@ class CyberLeninkaSearcher:
             return f"Failed to download PDF: {e}"
 
     def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
-        """Read and extract text from a CyberLeninka paper PDF.
+        """Read and extract text from a CyberLeninka paper.
+
+        Tries PDF extraction first, falls back to scraping article page text.
 
         Args:
             paper_id: CyberLeninka article slug
@@ -388,9 +390,83 @@ class CyberLeninkaSearcher:
         Returns:
             Extracted text or error message
         """
+        # Try PDF extraction first
         pdf_path = self.download_pdf(paper_id, save_path)
-        if not os.path.exists(pdf_path):
-            return pdf_path  # Return error message
+        if os.path.exists(pdf_path):
+            text = extract_text_from_pdf(pdf_path)
+            if text and text.strip():
+                return text
+
+        # Fallback: extract text from article HTML page
+        return self._read_from_html(paper_id)
+
+    def _read_from_html(self, paper_id: str) -> str:
+        """Extract article text from the CyberLeninka HTML page."""
+        try:
+            self._rate_limit()
+
+            url = f"{self.BASE_URL}/article/n/{paper_id}"
+            response = requests.get(url, timeout=30, impersonate=self.impersonate)
+
+            if response.status_code != 200:
+                return f"Failed to read paper {paper_id}: HTTP {response.status_code}"
 
-        text = extract_text_from_pdf(pdf_path)
-        return text if text else "Failed to extract text from PDF"
+            soup = BeautifulSoup(response.text, 'lxml')
+
+            # Build metadata header
+            parts = []
+
+            title_meta = soup.find("meta", {"name": "citation_title"})
+            if title_meta and title_meta.get("content"):
+                parts.append(f"Title: {title_meta['content']}")
+
+            authors = [m.get("content", "") for m in soup.find_all("meta", {"name": "citation_author"}) if m.get("content")]
+            if authors:
+                parts.append(f"Authors: {', '.join(authors)}")
+
+            journal_meta = soup.find("meta", {"name": "citation_journal_title"})
+            if journal_meta and journal_meta.get("content"):
+                parts.append(f"Journal: {journal_meta['content']}")
+
+            date_meta = soup.find("meta", {"name": "citation_publication_date"})
+            if date_meta and date_meta.get("content"):
+                parts.append(f"Year: {date_meta['content']}")
+
+            if parts:
+                parts.append("")  # blank line separator
+
+            # Extract article body text
+            # CyberLeninka uses div with class "ocr" for full text
+            body_div = soup.find("div", {"class": "ocr"})
+            if not body_div:
+                # Try alternative selectors
+                body_div = soup.find("div", {"itemprop": "articleBody"})
+            if not body_div:
+                body_div = soup.find("div", {"class": "full-text"})
+
+            if body_div:
+                # Get text with paragraph separation
+                paragraphs = body_div.find_all(["p", "h2", "h3", "h4"])
+                if paragraphs:
+                    for p in paragraphs:
+                        text = p.get_text(strip=True)
+                        if text:
+                            parts.append(text)
+                else:
+                    body_text = body_div.get_text(separator="\n", strip=True)
+                    if body_text:
+                        parts.append(body_text)
+
+            if len(parts) <= 4:  # Only metadata, no body text
+                # Try description as last resort
+                desc_meta = soup.find("meta", {"name": "description"})
+                if desc_meta and desc_meta.get("content"):
+                    parts.append(f"Abstract: {desc_meta['content']}")
+                else:
+                    return f"No text content found for paper {paper_id}"
+
+            return "\n".join(parts)
+
+        except Exception as e:
+            logger.error(f"Error reading CyberLeninka article HTML: {e}")
+            return f"Failed to read paper: {e}"

paper_search_mcp/pdf_utils.py

@@ -41,12 +41,14 @@ def _extract_with_pdftotext(pdf_path: str) -> Optional[str]:
             ['pdftotext', '-layout', '-enc', 'UTF-8', pdf_path, '-'],
             capture_output=True,
             text=True,
+            encoding='utf-8',
+            errors='replace',
             timeout=60
         )
-        if result.returncode == 0:
+        if result.returncode == 0 and result.stdout:
             return result.stdout.strip()
         return None
-    except (subprocess.TimeoutExpired, subprocess.SubprocessError):
+    except Exception:
         return None
 
 
@@ -61,7 +63,9 @@ def _extract_with_pypdf(pdf_path: str) -> str:
         reader = PdfReader(pdf_path)
         text = ""
         for page in reader.pages:
-            text += page.extract_text() + "\n"
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
         return text.strip()
     except Exception as e:
         return f"Error extracting text: {e}"