html-to-markdown 1.3.3__py3-none-any.whl → 1.5.0__py3-none-any.whl

html_to_markdown/__init__.py

@@ -1,5 +1,6 @@
-from html_to_markdown.processing import convert_to_markdown
+from html_to_markdown.processing import convert_to_markdown, convert_to_markdown_stream
 
+# For backward compatibility and to maintain the existing API
 markdownify = convert_to_markdown
 
-__all__ = ["convert_to_markdown", "markdownify"]
+__all__ = ["convert_to_markdown", "convert_to_markdown_stream", "markdownify"]

html_to_markdown/__main__.py

@@ -1,8 +1,10 @@
 import sys
 
-def cli():
-    from html_to_markdown.cli import main
+from html_to_markdown.cli import main
 
+
+def cli() -> None:
+    """Main CLI entrypoint."""
     try:
         result = main(sys.argv[1:])
         print(result)  # noqa: T201
@@ -10,5 +12,6 @@ def cli():
         print(str(e), file=sys.stderr)  # noqa: T201
         sys.exit(1)
 
+
 if __name__ == "__main__":
     cli()

html_to_markdown/cli.py

@@ -1,11 +1,21 @@
-def main(argv: list[str]) -> str:
-    """Command-line entry point."""
-    from argparse import ArgumentParser, FileType
-    from sys import stdin
+import sys
+from argparse import ArgumentParser, FileType
+
+from html_to_markdown.constants import (
+    ASTERISK,
+    ATX,
+    ATX_CLOSED,
+    BACKSLASH,
+    DOUBLE_EQUAL,
+    SPACES,
+    UNDERLINED,
+    UNDERSCORE,
+)
+from html_to_markdown.processing import convert_to_markdown
 
-    from html_to_markdown.constants import ASTERISK, ATX, ATX_CLOSED, BACKSLASH, SPACES, UNDERLINED, UNDERSCORE
-    from html_to_markdown.processing import convert_to_markdown
 
+def main(argv: list[str]) -> str:
+    """Command-line entry point."""
     parser = ArgumentParser(
         prog="html_to_markdown",
         description="Converts HTML to Markdown.",
@@ -15,7 +25,7 @@ def main(argv: list[str]) -> str:
         "html",
         nargs="?",
         type=FileType("r"),
-        default=stdin,
+        default=sys.stdin,
         help="The HTML file to convert. Defaults to STDIN if not provided.",
     )
 
@@ -42,8 +52,8 @@ def main(argv: list[str]) -> str:
 
     parser.add_argument(
         "--default-title",
-        action="store_false",
-        help="Use this flag to disable setting the link title to its href when no title is provided.",
+        action="store_true",
+        help="Set the link title to its href when no title is provided.",
     )
 
     parser.add_argument(
@@ -106,6 +116,13 @@ def main(argv: list[str]) -> str:
         help="Disable escaping of '_' characters in text to '\\_'.",
     )
 
+    parser.add_argument(
+        "--no-escape-misc",
+        dest="escape_misc",
+        action="store_false",
+        help="Disable escaping of miscellaneous characters to prevent conflicts in Markdown.",
+    )
+
     parser.add_argument(
         "-i",
         "--keep-inline-images-in",
@@ -127,24 +144,93 @@ def main(argv: list[str]) -> str:
         help="The number of characters at which text paragraphs should wrap. Defaults to 80.",
     )
 
-    args = parser.parse_args(argv)
+    parser.add_argument(
+        "--strip-newlines",
+        action="store_true",
+        help="Remove newlines from HTML input before processing. This helps flatten janky output from HTML with unnecessary line breaks.",
+    )
+
+    parser.add_argument(
+        "--convert-as-inline",
+        action="store_true",
+        help="Treat the content as inline elements (no block elements like paragraphs).",
+    )
+
+    parser.add_argument(
+        "--no-extract-metadata",
+        dest="extract_metadata",
+        action="store_false",
+        help="Disable extraction of document metadata (title, meta tags) as a comment header.",
+    )
+
+    parser.add_argument(
+        "--highlight-style",
+        default=DOUBLE_EQUAL,
+        choices=("double-equal", "html", "bold"),
+        help="Style to use for highlighted text (mark elements). Defaults to 'double-equal'.",
+    )
 
-    return convert_to_markdown(
-        args.html.read(),
-        strip=args.strip,
-        convert=args.convert,
-        autolinks=args.autolinks,
-        default_title=args.default_title,
-        heading_style=args.heading_style,
-        bullets=args.bullets,
-        strong_em_symbol=args.strong_em_symbol,
-        sub_symbol=args.sub_symbol,
-        sup_symbol=args.sup_symbol,
-        newline_style=args.newline_style,
-        code_language=args.code_language,
-        escape_asterisks=args.escape_asterisks,
-        escape_underscores=args.escape_underscores,
-        keep_inline_images_in=args.keep_inline_images_in,
-        wrap=args.wrap,
-        wrap_width=args.wrap_width,
+    parser.add_argument(
+        "--stream-processing",
+        action="store_true",
+        help="Use streaming processing for large documents to reduce memory usage.",
     )
+
+    parser.add_argument(
+        "--chunk-size",
+        type=int,
+        default=1024,
+        help="Size of chunks when using streaming processing. Defaults to 1024 characters.",
+    )
+
+    parser.add_argument(
+        "--show-progress",
+        action="store_true",
+        help="Show progress information when processing large documents.",
+    )
+
+    args = parser.parse_args(argv)
+
+    # Prepare base arguments
+    base_args = {
+        "strip": args.strip,
+        "convert": args.convert,
+        "autolinks": args.autolinks,
+        "default_title": args.default_title,
+        "heading_style": args.heading_style,
+        "bullets": args.bullets,
+        "strong_em_symbol": args.strong_em_symbol,
+        "sub_symbol": args.sub_symbol,
+        "sup_symbol": args.sup_symbol,
+        "newline_style": args.newline_style,
+        "code_language": args.code_language,
+        "escape_asterisks": args.escape_asterisks,
+        "escape_underscores": args.escape_underscores,
+        "escape_misc": args.escape_misc,
+        "keep_inline_images_in": args.keep_inline_images_in,
+        "wrap": args.wrap,
+        "wrap_width": args.wrap_width,
+        "strip_newlines": args.strip_newlines,
+        "convert_as_inline": args.convert_as_inline,
+        "extract_metadata": args.extract_metadata,
+        "highlight_style": args.highlight_style,
+    }
+
+    # Add streaming parameters only if streaming is enabled
+    if args.stream_processing:
+        base_args["stream_processing"] = True
+        base_args["chunk_size"] = args.chunk_size
+
+        # Progress callback for CLI
+        if args.show_progress:
+
+            def progress_callback(processed: int, total: int) -> None:
+                if total > 0:
+                    percent = (processed / total) * 100
+                    # Use sys.stderr to avoid ruff T201 error for progress output
+                    sys.stderr.write(f"\rProgress: {percent:.1f}% ({processed}/{total} bytes)")
+                    sys.stderr.flush()
+
+            base_args["progress_callback"] = progress_callback
+
+    return convert_to_markdown(args.html.read(), **base_args)

html_to_markdown/constants.py

@@ -16,3 +16,4 @@ BACKSLASH: Final = "backslash"
 UNDERLINED: Final = "underlined"
 SPACES: Final = "spaces"
 UNDERSCORE: Final = "_"
+DOUBLE_EQUAL: Final = "double-equal"