Add support for HTML file (#973)

### What problem does this PR solve?

Add support for HTML file

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

deepdoc/parser/__init__.py

@@ -4,3 +4,4 @@ from .pdf_parser import RAGFlowPdfParser as PdfParser, PlainParser
 from .docx_parser import RAGFlowDocxParser as DocxParser
 from .excel_parser import RAGFlowExcelParser as ExcelParser
 from .ppt_parser import RAGFlowPptParser as PptParser
+from .html_parser import RAGFlowHtmlParser as HtmlParser

deepdoc/parser/html_parser.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+from rag.nlp import find_codec
+import readability
+import html_text
+import chardet
+
+def get_encoding(file):
+    with open(file,'rb') as f:
+        tmp = chardet.detect(f.read())
+        return tmp['encoding']
+    
+class RAGFlowHtmlParser:
+    def __call__(self, fnm, binary=None):
+        txt = ""
+        if binary:
+            encoding = find_codec(binary)
+            txt = binary.decode(encoding, errors="ignore")
+        else:
+            with open(fnm, "r",encoding=get_encoding(fnm)) as f:
+                txt = f.read()
+            
+        html_doc = readability.Document(txt)
+        title = html_doc.title()
+        content = html_text.extract_text(html_doc.summary(html_partial=True))
+        txt = f'{title}\n{content}'
+        sections = txt.split("\n")
+        return sections