Added HTML Parser based on TidyHTMLTreeBuilder.

[bookmarks_db.git] / Robots / parse_html.py

diff --git a/Robots/parse_html.py b/Robots/parse_html.py
index 8ffca5c81bde3a095d57d697a0b8b234cd6f7fb7..cc7655bfa950770d3f092ad7c32d387f2f65bd8b 100755 (executable)
--- a/Robots/parse_html.py
+++ b/Robots/parse_html.py
@@ -11,6 +11,14 @@ universal_charset = "utf-8"
 DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic
 
 parsers = []
+
+try:
+   import parse_html_etreetidy
+except ImportError:
+   pass
+else:
+   parsers.append(parse_html_etreetidy.parse_html)
+
 try:
    import parse_html_beautifulsoup
    parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET