re

cmdlet/download_file.py

@@ -319,6 +319,18 @@ class Download_File(Cmdlet):
                     except Exception:
                         provider_name = None
 
+                # Heuristic: LibGen often uses landing pages like edition.php/file.php.
+                # These should never be treated as direct file URLs.
+                if not provider_name:
+                    try:
+                        p = urlparse(str(url))
+                        h = (p.hostname or "").strip().lower()
+                        path = (p.path or "").strip().lower()
+                        if "libgen" in h and any(x in path for x in ("/edition.php", "/file.php", "/ads.php", "/get.php", "/series.php")):
+                            provider_name = "libgen"
+                    except Exception:
+                        pass
+
                 if provider_name and get_provider is not None and SearchResult is not None:
                     # OpenLibrary URLs should be handled by the OpenLibrary provider.
                     if provider_name == "openlibrary":
@@ -391,11 +403,19 @@ class Download_File(Cmdlet):
                         progress.clear_status()
 
                         if downloaded_path:
+                            tags_hint: Optional[List[str]] = None
+                            try:
+                                sr_tags = getattr(sr, "tag", None)
+                                if isinstance(sr_tags, set) and sr_tags:
+                                    tags_hint = sorted([str(t) for t in sr_tags if t])
+                            except Exception:
+                                tags_hint = None
+
                             self._emit_local_file(
                                 downloaded_path=Path(downloaded_path),
                                 source=str(url),
                                 title_hint=title_hint,
-                                tags_hint=None,
+                                tags_hint=tags_hint,
                                 media_kind_hint="book",
                                 full_metadata=sr.full_metadata,
                                 provider_hint="openlibrary",
@@ -472,14 +492,42 @@ class Download_File(Cmdlet):
                         except Exception:
                             downloaded_path = None
 
+                        # Refuse to fall back to direct-download for LibGen landing pages.
+                        # This prevents saving HTML (e.g. edition.php) as a bogus file.
+                        if (not downloaded_path) and str(provider_name).lower() == "libgen":
+                            raise DownloadError("LibGen URL did not resolve to a downloadable file")
+
                         if downloaded_path:
+                            tags_hint: Optional[List[str]] = None
+                            full_md: Optional[Dict[str, Any]] = None
+                            title_hint = Path(str(downloaded_path)).stem
+                            media_kind_hint = "file"
+
+                            if str(provider_name).lower() == "libgen":
+                                media_kind_hint = "book"
+                                try:
+                                    sr_tags = getattr(sr, "tag", None)
+                                    if isinstance(sr_tags, set) and sr_tags:
+                                        tags_hint = sorted([str(t) for t in sr_tags if t])
+                                except Exception:
+                                    tags_hint = None
+
+                                try:
+                                    if isinstance(getattr(sr, "full_metadata", None), dict):
+                                        full_md = sr.full_metadata
+                                        t = str(full_md.get("title") or "").strip()
+                                        if t:
+                                            title_hint = t
+                                except Exception:
+                                    full_md = None
+
                             self._emit_local_file(
                                 downloaded_path=Path(downloaded_path),
                                 source=str(url),
-                                title_hint=Path(str(downloaded_path)).stem,
-                                tags_hint=None,
-                                media_kind_hint="file",
-                                full_metadata=None,
+                                title_hint=title_hint,
+                                tags_hint=tags_hint,
+                                media_kind_hint=media_kind_hint,
+                                full_metadata=full_md,
                                 provider_hint=str(provider_name),
                                 progress=progress,
                                 config=config,
@@ -600,6 +648,7 @@ class Download_File(Cmdlet):
                 # If this looks like a provider item and providers are available, prefer provider.download()
                 downloaded_path: Optional[Path] = None
                 attempted_provider_download = False
+                provider_sr = None
                 if table and get_search_provider and SearchResult:
                     provider = get_search_provider(str(table), config)
                     if provider is not None:
@@ -612,6 +661,7 @@ class Download_File(Cmdlet):
                         )
                         debug(f"[download-file] Downloading provider item via {table}: {sr.title}")
                         downloaded_path = provider.download(sr, final_output_dir)
+                        provider_sr = sr
 
                 # OpenLibrary: if provider download failed, do NOT try to download the OpenLibrary page HTML.
                 if downloaded_path is None and attempted_provider_download and str(table or "").lower() == "openlibrary":
@@ -693,6 +743,30 @@ class Download_File(Cmdlet):
                     log(f"Cannot download item (no provider handler / unsupported target): {title or target}", file=sys.stderr)
                     continue
 
+                # Allow providers to add/enrich tags and metadata during download.
+                if str(table or "").lower() == "libgen" and provider_sr is not None:
+                    try:
+                        sr_tags = getattr(provider_sr, "tag", None)
+                        if tags_list is None and isinstance(sr_tags, set) and sr_tags:
+                            tags_list = sorted([str(t) for t in sr_tags if t])
+                    except Exception:
+                        pass
+
+                    try:
+                        sr_md = getattr(provider_sr, "full_metadata", None)
+                        if isinstance(sr_md, dict) and sr_md:
+                            full_metadata = sr_md
+                    except Exception:
+                        pass
+
+                    try:
+                        if isinstance(full_metadata, dict):
+                            t = str(full_metadata.get("title") or "").strip()
+                            if t:
+                                title = t
+                    except Exception:
+                        pass
+
                 self._emit_local_file(
                     downloaded_path=downloaded_path,
                     source=str(target) if target else None,

cmdlet/download_media.py

@@ -1593,6 +1593,36 @@ class Download_Media(Cmdlet):
             debug("Preflight URL check: no matches")
             return True
 
+        # If the user already answered the duplicate URL prompt for this pipeline/command,
+        # respect that decision and don't re-prompt for every item.
+        try:
+            current_cmd_text = pipeline_context.get_current_command_text("")
+        except Exception:
+            current_cmd_text = ""
+
+        try:
+            stage_ctx = pipeline_context.get_stage_context()
+        except Exception:
+            stage_ctx = None
+
+        in_pipeline = bool(stage_ctx is not None or ("|" in str(current_cmd_text or "")))
+        if in_pipeline:
+            try:
+                cached_cmd = pipeline_context.load_value("preflight.url_duplicates.command", default="")
+                cached_decision = pipeline_context.load_value("preflight.url_duplicates.continue", default=None)
+            except Exception:
+                cached_cmd = ""
+                cached_decision = None
+
+            if cached_decision is not None and str(cached_cmd or "") == str(current_cmd_text or ""):
+                if bool(cached_decision):
+                    return True
+                try:
+                    pipeline_context.request_pipeline_stop(reason="duplicate-url declined", exit_code=0)
+                except Exception:
+                    pass
+                return False
+
         table = ResultTable(f"URL already exists ({len(url_matches)} match(es))")
         results_list: List[Dict[str, Any]] = []
         for item in url_matches:
@@ -1639,8 +1669,28 @@ class Download_Media(Cmdlet):
         with cm:
             get_stderr_console().print(table)
             setattr(table, "_rendered_by_cmdlet", True)
-            if not Confirm.ask("Continue anyway?", default=False, console=get_stderr_console()):
-                if used_suspend:
+            answered_yes = bool(Confirm.ask("Continue anyway?", default=False, console=get_stderr_console()))
+
+            # Cache decision for the duration of this pipeline/command.
+            if in_pipeline:
+                try:
+                    existing = pipeline_context.load_value("preflight", default=None)
+                except Exception:
+                    existing = None
+                preflight_cache: Dict[str, Any] = existing if isinstance(existing, dict) else {}
+                url_dup_cache = preflight_cache.get("url_duplicates")
+                if not isinstance(url_dup_cache, dict):
+                    url_dup_cache = {}
+                url_dup_cache["command"] = str(current_cmd_text or "")
+                url_dup_cache["continue"] = bool(answered_yes)
+                preflight_cache["url_duplicates"] = url_dup_cache
+                try:
+                    pipeline_context.store_value("preflight", preflight_cache)
+                except Exception:
+                    pass
+
+            if not answered_yes:
+                if in_pipeline and used_suspend:
                     try:
                         pipeline_context.request_pipeline_stop(reason="duplicate-url declined", exit_code=0)
                     except Exception:
@@ -1666,6 +1716,35 @@ class Download_Media(Cmdlet):
             debug("Bulk URL preflight skipped: storage unavailable")
             return True
 
+        # Honor any prior duplicate URL decision for this pipeline/command.
+        try:
+            current_cmd_text = pipeline_context.get_current_command_text("")
+        except Exception:
+            current_cmd_text = ""
+
+        try:
+            stage_ctx = pipeline_context.get_stage_context()
+        except Exception:
+            stage_ctx = None
+
+        in_pipeline = bool(stage_ctx is not None or ("|" in str(current_cmd_text or "")))
+        if in_pipeline:
+            try:
+                cached_cmd = pipeline_context.load_value("preflight.url_duplicates.command", default="")
+                cached_decision = pipeline_context.load_value("preflight.url_duplicates.continue", default=None)
+            except Exception:
+                cached_cmd = ""
+                cached_decision = None
+
+            if cached_decision is not None and str(cached_cmd or "") == str(current_cmd_text or ""):
+                if bool(cached_decision):
+                    return True
+                try:
+                    pipeline_context.request_pipeline_stop(reason="duplicate-url declined", exit_code=0)
+                except Exception:
+                    pass
+                return False
+
         unique_urls: List[str] = []
         for u in urls or []:
             s = str(u or "").strip()
@@ -1930,7 +2009,32 @@ class Download_Media(Cmdlet):
                 cm = nullcontext()
 
         with cm:
-            if not Confirm.ask("Continue anyway?", default=False, console=get_stderr_console()):
+            answered_yes = bool(Confirm.ask("Continue anyway?", default=False, console=get_stderr_console()))
+
+            # Cache decision for the duration of this pipeline/command.
+            if in_pipeline:
+                try:
+                    existing = pipeline_context.load_value("preflight", default=None)
+                except Exception:
+                    existing = None
+                preflight_cache: Dict[str, Any] = existing if isinstance(existing, dict) else {}
+                url_dup_cache = preflight_cache.get("url_duplicates")
+                if not isinstance(url_dup_cache, dict):
+                    url_dup_cache = {}
+                url_dup_cache["command"] = str(current_cmd_text or "")
+                url_dup_cache["continue"] = bool(answered_yes)
+                preflight_cache["url_duplicates"] = url_dup_cache
+                try:
+                    pipeline_context.store_value("preflight", preflight_cache)
+                except Exception:
+                    pass
+
+            if not answered_yes:
+                if in_pipeline:
+                    try:
+                        pipeline_context.request_pipeline_stop(reason="duplicate-url declined", exit_code=0)
+                    except Exception:
+                        pass
                 return False
         return True
 
@@ -1947,6 +2051,20 @@ class Download_Media(Cmdlet):
         if not isinstance(entries, list) or len(entries) <= 1:
             return False
 
+        # Identify a stable table type so `@* | ...` pipelines can auto-insert the
+        # appropriate downloader stage (e.g., Bandcamp selections should insert
+        # `download-media` before `merge-file`).
+        extractor_name = ""
+        try:
+            extractor_name = str(pr.get("extractor") or pr.get("extractor_key") or "").strip().lower()
+        except Exception:
+            extractor_name = ""
+        table_type: Optional[str] = None
+        if "bandcamp" in extractor_name:
+            table_type = "bandcamp"
+        elif "youtube" in extractor_name:
+            table_type = "youtube"
+
         # Display table (limit rows to keep output reasonable)
         max_rows = 200
         display_entries = entries[:max_rows]
@@ -1976,6 +2094,11 @@ class Download_Media(Cmdlet):
         table = ResultTable()
         safe_url = str(url or "").strip()
         table.title = f'download-media -url "{safe_url}"' if safe_url else "download-media"
+        if table_type:
+            try:
+                table.set_table(table_type)
+            except Exception:
+                table.table = table_type
         table.set_source_command("download-media", [])
         try:
             table.set_preserve_order(True)
@@ -2581,7 +2704,10 @@ class Download_Media(Cmdlet):
                 PipelineProgress(pipeline_context).step("finalized")
 
                 stage_ctx = pipeline_context.get_stage_context()
-                emit_enabled = bool(stage_ctx is not None and not getattr(stage_ctx, "is_last_stage", False))
+                # Emit per downloaded item whenever we're running under the pipeline runner.
+                # Live progress advances on emit(), and suppressing emits for the last stage
+                # causes the pipe bar to stay at 0% even while downloads complete.
+                emit_enabled = bool(stage_ctx is not None)
                 for pipe_obj_dict in pipe_objects:
                     if emit_enabled:
                         pipeline_context.emit(pipe_obj_dict)

cmdlet/get_url.py

@@ -85,7 +85,12 @@ class Get_Url(Cmdlet):
             if title:
                 table_title = f"Title: {title}"
 
-            table = ResultTable(table_title, max_columns=1).set_preserve_order(True)
+            table = (
+                ResultTable(table_title, max_columns=1)
+                .set_preserve_order(True)
+                .set_table("url")
+                .set_value_case("preserve")
+            )
             table.set_source_command("get-url", [])
 
             items: List[UrlItem] = []