two version of R2R are hereHEADmaster

1 files changed, 23 insertions, 0 deletions

diff --git a/R2R/r2r/parsers/text/md_parser.py b/R2R/r2r/parsers/text/md_parser.py
new file mode 100755
index 00000000..ada9ae57
--- /dev/null
+++ b/R2R/r2r/parsers/text/md_parser.py
@@ -0,0 +1,23 @@
+from typing import AsyncGenerator
+
+from bs4 import BeautifulSoup
+
+from r2r.base.abstractions.document import DataType
+from r2r.base.parsers.base_parser import AsyncParser
+
+
+class MDParser(AsyncParser[DataType]):
+    """A parser for Markdown data."""
+
+    def __init__(self):
+        import markdown
+
+        self.markdown = markdown
+
+    async def ingest(self, data: DataType) -> AsyncGenerator[str, None]:
+        """Ingest Markdown data and yield text."""
+        if isinstance(data, bytes):
+            data = data.decode("utf-8")
+        html = self.markdown.markdown(data)
+        soup = BeautifulSoup(html, "html.parser")
+        yield soup.get_text()