scitex 2.5.0__py3-none-any.whl → 2.7.0__py3-none-any.whl

scitex/scholar/cli/open_browser_auto.py

@@ -34,12 +34,14 @@ logger = getLogger(__name__)
 def get_failed_papers(project: str, config: ScholarConfig) -> List[Dict]:
     """Get papers with failed downloads."""
     from scitex.scholar.cli.open_browser import get_failed_papers as _get_failed
+
     return _get_failed(project, config)
 
 
 def get_pending_papers(project: str, config: ScholarConfig) -> List[Dict]:
     """Get papers with pending downloads."""
     from scitex.scholar.cli.open_browser import get_pending_papers as _get_pending
+
     return _get_pending(project, config)
 
 
@@ -60,7 +62,9 @@ def generate_proper_filename(metadata: dict) -> str:
     journal = basic.get("journal", "Unknown")
 
     # Clean journal name
-    journal_clean = "".join(c for c in journal if c.isalnum() or c in (' ', '-', '_'))[:50]
+    journal_clean = "".join(c for c in journal if c.isalnum() or c in (" ", "-", "_"))[
+        :50
+    ]
     journal_clean = journal_clean.strip()
 
     return f"{first_author}-{year}-{journal_clean}.pdf"
@@ -109,6 +113,7 @@ def handle_download(download, paper_id: str, paper_title: str, config: ScholarCo
         screenshot_dir = paper_dir / "screenshots"
         if screenshot_dir.exists():
             import shutil
+
             shutil.rmtree(screenshot_dir)
             logger.info(f"  Removed screenshots (download succeeded)")
 
@@ -133,10 +138,7 @@ def handle_download(download, paper_id: str, paper_title: str, config: ScholarCo
 
 
 def open_browser_with_auto_tracking(
-    papers: List[Dict],
-    project: str,
-    config: ScholarConfig,
-    profile: str = None
+    papers: List[Dict], project: str, config: ScholarConfig, profile: str = None
 ) -> None:
     """Open browser with automatic download tracking.
 
@@ -167,16 +169,18 @@ def open_browser_with_auto_tracking(
             openurl_resolved=paper.get("openurl_resolved"),
             url_publisher=paper.get("url_publisher"),
             url_doi=paper.get("url_doi"),
-            doi=paper.get("doi")
+            doi=paper.get("doi"),
         )
 
         if url:
-            papers_to_open.append({
-                "paper_id": paper_id,
-                "title": paper.get("title", "Unknown"),
-                "url": url,
-                "doi": paper.get("doi", ""),
-            })
+            papers_to_open.append(
+                {
+                    "paper_id": paper_id,
+                    "title": paper.get("title", "Unknown"),
+                    "url": url,
+                    "doi": paper.get("doi", ""),
+                }
+            )
         else:
             logger.warning(f"No URL for {paper.get('title', 'Unknown')[:50]}...")
 
@@ -201,9 +205,9 @@ def open_browser_with_auto_tracking(
             headless=False,
             accept_downloads=True,  # Enable download tracking
             args=[
-                '--disable-blink-features=AutomationControlled',
-                '--disable-features=UserAgentClientHint',
-            ]
+                "--disable-blink-features=AutomationControlled",
+                "--disable-features=UserAgentClientHint",
+            ],
         )
 
         # Track which page belongs to which paper
@@ -212,6 +216,7 @@ def open_browser_with_auto_tracking(
 
         def create_download_handler(paper_info: dict):
             """Create download handler for specific paper."""
+
             def on_download(download):
                 nonlocal download_count
                 download_count += 1
@@ -221,10 +226,7 @@ def open_browser_with_auto_tracking(
                 logger.info(f"  Paper: {paper_info['title'][:60]}...")
 
                 handle_download(
-                    download,
-                    paper_info["paper_id"],
-                    paper_info["title"],
-                    config
+                    download, paper_info["paper_id"], paper_info["title"], config
                 )
 
             return on_download
@@ -253,7 +255,9 @@ def open_browser_with_auto_tracking(
 
             try:
                 new_page.goto(paper_info["url"], timeout=30000)
-                logger.success(f"[{paper_info['paper_id']}] {paper_info['title'][:60]}...")
+                logger.success(
+                    f"[{paper_info['paper_id']}] {paper_info['title'][:60]}..."
+                )
             except Exception as e:
                 logger.warning(f"Failed to load: {e}")
 
@@ -277,7 +281,7 @@ def open_browser_with_auto_tracking(
         browser.on("page", on_page_created)
 
         # Show instructions
-        logger.info(f"\n{'='*70}")
+        logger.info(f"\n{'=' * 70}")
         logger.info(f"Browser opened with {len(papers_to_open)} papers")
         logger.info("Download tracking ACTIVE - PDFs will auto-link to library")
         logger.info("")
@@ -293,7 +297,7 @@ def open_browser_with_auto_tracking(
         logger.info("  - Multiple downloads per paper are supported")
         logger.info("")
         logger.info("Press Ctrl+C when done")
-        logger.info(f"{'='*70}\n")
+        logger.info(f"{'=' * 70}\n")
 
         try:
             # Keep browser open
@@ -313,23 +317,16 @@ def main():
         description="Open browser with automatic download tracking and linking"
     )
     parser.add_argument(
-        "--project",
-        required=True,
-        help="Project name (e.g., neurovista, pac)"
+        "--project", required=True, help="Project name (e.g., neurovista, pac)"
     )
     parser.add_argument(
-        "--all",
-        action="store_true",
-        help="Open both failed and pending PDFs"
+        "--all", action="store_true", help="Open both failed and pending PDFs"
     )
     parser.add_argument(
-        "--pending",
-        action="store_true",
-        help="Open only pending (not attempted) PDFs"
+        "--pending", action="store_true", help="Open only pending (not attempted) PDFs"
     )
     parser.add_argument(
-        "--profile",
-        help="Browser profile name to use (default: system)"
+        "--profile", help="Browser profile name to use (default: system)"
     )
 
     args = parser.parse_args()
@@ -364,12 +361,7 @@ def main():
         logger.info(f"  ... and {len(papers) - 10} more")
 
     # Open browser with auto-tracking
-    open_browser_with_auto_tracking(
-        papers,
-        args.project,
-        config,
-        profile=args.profile
-    )
+    open_browser_with_auto_tracking(papers, args.project, config, profile=args.profile)
 
 
 if __name__ == "__main__":

scitex/scholar/cli/open_browser_monitored.py

@@ -36,7 +36,9 @@ logger = getLogger(__name__)
 class DownloadMonitor(FileSystemEventHandler):
     """Monitor downloads folder and link PDFs to library."""
 
-    def __init__(self, paper_id_map: Dict[str, str], library_manager, config: ScholarConfig):
+    def __init__(
+        self, paper_id_map: Dict[str, str], library_manager, config: ScholarConfig
+    ):
         """
         Args:
             paper_id_map: Maps download filenames to paper_ids
@@ -57,7 +59,7 @@ class DownloadMonitor(FileSystemEventHandler):
         file_path = Path(event.src_path)
 
         # Only process PDF files
-        if file_path.suffix.lower() != '.pdf':
+        if file_path.suffix.lower() != ".pdf":
             return
 
         # Avoid processing the same file twice
@@ -103,11 +105,12 @@ class DownloadMonitor(FileSystemEventHandler):
         # Strategy 3: Extract and match metadata from PDF
         try:
             from PyPDF2 import PdfReader
+
             reader = PdfReader(pdf_path)
 
             # Check PDF metadata
             if reader.metadata:
-                pdf_title = reader.metadata.get('/Title', '').lower()
+                pdf_title = reader.metadata.get("/Title", "").lower()
 
                 # Match against paper titles
                 for paper_id, title in self.paper_id_map.items():
@@ -121,7 +124,8 @@ class DownloadMonitor(FileSystemEventHandler):
 
                 # Look for DOI pattern
                 import re
-                doi_match = re.search(r'10\.\d{4,}/[^\s]+', first_page)
+
+                doi_match = re.search(r"10\.\d{4,}/[^\s]+", first_page)
                 if doi_match:
                     doi = doi_match.group()
                     for paper_id, paper_doi in self.paper_id_map.items():
@@ -159,7 +163,9 @@ class DownloadMonitor(FileSystemEventHandler):
                 journal = basic.get("journal", "Unknown")
 
                 # Clean filename
-                journal_clean = "".join(c for c in journal if c.isalnum() or c in (' ', '-', '_'))[:50]
+                journal_clean = "".join(
+                    c for c in journal if c.isalnum() or c in (" ", "-", "_")
+                )[:50]
                 proper_name = f"{first_author}-{year}-{journal_clean}.pdf"
             else:
                 # Fallback to original name
@@ -174,6 +180,7 @@ class DownloadMonitor(FileSystemEventHandler):
 
             # Update symlinks to reflect PDF_s status
             from scitex.scholar.storage._LibraryManager import LibraryManager
+
             # Trigger symlink update by touching metadata
             if metadata_file.exists():
                 metadata_file.touch()
@@ -185,12 +192,14 @@ class DownloadMonitor(FileSystemEventHandler):
 def get_failed_papers(project: str, config: ScholarConfig) -> List[Dict]:
     """Get papers with failed downloads - reuse from open_browser.py"""
     from scitex.scholar.cli.open_browser import get_failed_papers as _get_failed
+
     return _get_failed(project, config)
 
 
 def get_pending_papers(project: str, config: ScholarConfig) -> List[Dict]:
     """Get papers with pending downloads - reuse from open_browser.py"""
     from scitex.scholar.cli.open_browser import get_pending_papers as _get_pending
+
     return _get_pending(project, config)
 
 
@@ -199,7 +208,7 @@ def open_browser_with_monitoring(
     project: str,
     config: ScholarConfig,
     profile: str = None,
-    downloads_dir: Path = None
+    downloads_dir: Path = None,
 ) -> None:
     """Open browser and monitor downloads for auto-linking.
 
@@ -264,6 +273,7 @@ def open_browser_with_monitoring(
 
     # Setup download monitor
     from scitex.scholar.storage._LibraryManager import LibraryManager
+
     library_manager = LibraryManager(config)
 
     event_handler = DownloadMonitor(paper_id_map, library_manager, config)
@@ -288,9 +298,9 @@ def open_browser_with_monitoring(
                 str(profile_dir),
                 headless=False,  # Always visible for manual downloads
                 args=[
-                    '--disable-blink-features=AutomationControlled',
-                    '--disable-features=UserAgentClientHint',
-                ]
+                    "--disable-blink-features=AutomationControlled",
+                    "--disable-features=UserAgentClientHint",
+                ],
             )
 
             # Open URLs in tabs
@@ -310,12 +320,12 @@ def open_browser_with_monitoring(
                 new_page.goto(url)
                 logger.success(f"[{paper_id}] {url[:80]}...")
 
-            logger.info(f"\n{'='*60}")
+            logger.info(f"\n{'=' * 60}")
             logger.info(f"Browser opened with {len(urls_to_open)} tabs")
             logger.info("Download monitoring active - PDFs will be auto-linked")
             logger.info("Use Zotero connector or save PDFs manually")
             logger.info("Press Ctrl+C when done")
-            logger.info(f"{'='*60}\n")
+            logger.info(f"{'=' * 60}\n")
 
             try:
                 # Keep browser open
@@ -336,28 +346,21 @@ def main():
         description="Open browser with download monitoring and auto-linking"
     )
     parser.add_argument(
-        "--project",
-        required=True,
-        help="Project name (e.g., neurovista, pac)"
+        "--project", required=True, help="Project name (e.g., neurovista, pac)"
     )
     parser.add_argument(
-        "--all",
-        action="store_true",
-        help="Open both failed and pending PDFs"
+        "--all", action="store_true", help="Open both failed and pending PDFs"
     )
     parser.add_argument(
-        "--pending",
-        action="store_true",
-        help="Open only pending (not attempted) PDFs"
+        "--pending", action="store_true", help="Open only pending (not attempted) PDFs"
     )
     parser.add_argument(
-        "--profile",
-        help="Browser profile name to use (default: system)"
+        "--profile", help="Browser profile name to use (default: system)"
     )
     parser.add_argument(
         "--downloads-dir",
         type=Path,
-        help="Downloads directory to monitor (default: ~/Downloads)"
+        help="Downloads directory to monitor (default: ~/Downloads)",
     )
 
     args = parser.parse_args()
@@ -396,7 +399,7 @@ def main():
         args.project,
         config,
         profile=args.profile,
-        downloads_dir=args.downloads_dir
+        downloads_dir=args.downloads_dir,
     )
 
 

scitex/scholar/config/ScholarConfig.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/scholar/config/ScholarConfig.py"
-)
+
+__FILE__ = "./src/scitex/scholar/config/ScholarConfig.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -68,8 +67,7 @@ class ScholarConfig:
         path_manager_get_methods = [
             attr
             for attr in dir(self.path_manager)
-            if attr.startswith("get_")
-            and callable(getattr(self.path_manager, attr))
+            if attr.startswith("get_") and callable(getattr(self.path_manager, attr))
         ]
         return list(own_attrs) + path_manager_get_methods
 
@@ -107,9 +105,7 @@ class ScholarConfig:
                     return value
                 elif value == "null":
                     return "null"
-                elif value and not (
-                    value.startswith('"') and value.endswith('"')
-                ):
+                elif value and not (value.startswith('"') and value.endswith('"')):
                     return f'"{value}"'
                 else:
                     return value or "null"
@@ -143,4 +139,5 @@ class ScholarConfig:
         """Access to path manager for organized directory structure"""
         return self.path_manager
 
+
 # EOF

scitex/scholar/config/__init__.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------

scitex/scholar/config/core/_CascadeConfig.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -88,9 +89,7 @@ class CascadeConfig:
         else:
             should_mask = self._is_sensitive(key)
 
-        display_value = (
-            self._mask_value(final_value) if should_mask else final_value
-        )
+        display_value = self._mask_value(final_value) if should_mask else final_value
 
         self.resolution_log.append(
             {
@@ -153,4 +152,5 @@ class CascadeConfig:
             return "****"
         return value_str[:2] + "*" * (len(value_str) - 4) + value_str[-2:]
 
+
 # EOF

scitex/scholar/config/core/_PathManager.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/scholar/config/core/_PathManager.py"
-)
+
+__FILE__ = "./src/scitex/scholar/config/core/_PathManager.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -167,15 +166,13 @@ class PathManager:
 
     def get_cache_auth_json_lock(self, auth_name) -> Path:
         """cache/auth/{auth_name}.json.lock"""
-        return self.scholar_dir / PATH_STRUCTURE[
-            "cache_auth_json_lock"
-        ].format(auth_name=auth_name)
+        return self.scholar_dir / PATH_STRUCTURE["cache_auth_json_lock"].format(
+            auth_name=auth_name
+        )
 
     def get_cache_chrome_dir(self, profile_name: str) -> Path:
         """cache/chrome/{profile_name}"""
-        return self._ensure_directory(
-            self.dirs["cache_chrome_dir"] / profile_name
-        )
+        return self._ensure_directory(self.dirs["cache_chrome_dir"] / profile_name)
 
     def get_cache_engine_dir(self) -> Path:
         """cache/engine"""
@@ -297,9 +294,7 @@ class PathManager:
             journal_name=journal_name,
         )
 
-    def get_library_project_entry_dir(
-        self, project: str, entry_dir_name: str
-    ) -> Path:
+    def get_library_project_entry_dir(self, project: str, entry_dir_name: str) -> Path:
         """library/{project_name}/{entry_dir_name}"""
         project = self._sanitize_collection_name(project)
         path_template = PATH_STRUCTURE["library_project_entry_dir"]
@@ -337,21 +332,15 @@ class PathManager:
         """workspace/logs"""
         return self._ensure_directory(self.dirs["workspace_logs_dir"])
 
-    def get_workspace_screenshots_dir(
-        self, category: Optional[str] = None
-    ) -> Path:
+    def get_workspace_screenshots_dir(self, category: Optional[str] = None) -> Path:
         """workspace/screenshots or workspace/screenshots/{category}"""
         if category:
             category = self._sanitize_filename(category)
-            path_template = PATH_STRUCTURE[
-                "workspace_screenshots_category_dir"
-            ]
+            path_template = PATH_STRUCTURE["workspace_screenshots_category_dir"]
             relative_path = path_template.format(category=category)
             return self._ensure_directory(self.scholar_dir / relative_path)
         else:
-            return self._ensure_directory(
-                self.dirs["workspace_screenshots_dir"]
-            )
+            return self._ensure_directory(self.dirs["workspace_screenshots_dir"])
 
     # ========================================
     # Helper Methods
@@ -414,9 +403,7 @@ class PathManager:
 
         return collection_name
 
-    def _generate_paper_id(
-        self, doi=None, title=None, authors=None, year=None
-    ) -> str:
+    def _generate_paper_id(self, doi=None, title=None, authors=None, year=None) -> str:
         """Generate unique 8-digit paper ID."""
         doi = doi.strip() if isinstance(doi, str) and doi else None
         title = title.strip() if isinstance(title, str) and title else ""
@@ -469,7 +456,9 @@ class PathManager:
             Tuple of (storage_path, readable_name, paper_id)
         """
         # Generate unique paper ID
-        paper_id = self._generate_paper_id(doi=doi, title=title, authors=authors, year=year)
+        paper_id = self._generate_paper_id(
+            doi=doi, title=title, authors=authors, year=year
+        )
 
         # Get storage path (always in MASTER directory)
         storage_path = self.get_library_master_paper_dir(paper_id)
@@ -529,9 +518,7 @@ class PathManager:
         try:
             for file_path in directory.rglob("*"):
                 if file_path.is_file():
-                    file_time = datetime.fromtimestamp(
-                        file_path.stat().st_mtime
-                    )
+                    file_time = datetime.fromtimestamp(file_path.stat().st_mtime)
                     if file_time < cutoff_date:
                         file_path.unlink()
                         cleaned_count += 1
@@ -540,4 +527,5 @@ class PathManager:
 
         return cleaned_count
 
+
 # EOF