Feat: Remove some HTML parsers

[bookmarks_db.git] / parse_html / bkmk_parse_html.py

diff --git a/parse_html/bkmk_parse_html.py b/parse_html/bkmk_parse_html.py
index 7764303a4e754715a86a3a12e5d0b48d1d5acb8c..4d5f9e6d11f06ef0b587acca2b608b6443007795 100644 (file)
--- a/parse_html/bkmk_parse_html.py
+++ b/parse_html/bkmk_parse_html.py
@@ -24,14 +24,6 @@ from compat import unicode, unichr
 DEFAULT_CHARSET = "cp1251"  # Stupid default for Russian Cyrillic
 parsers = []
 
-try:
-    from . import bkmk_ph_beautifulsoup4
-except ImportError:
-    pass
-else:
-    bkmk_ph_beautifulsoup4.DEFAULT_CHARSET = DEFAULT_CHARSET
-    parsers.append(bkmk_ph_beautifulsoup4.parse_html)
-
 try:
     from . import bkmk_ph_beautifulsoup
 except ImportError:
@@ -41,33 +33,26 @@ else:
     parsers.append(bkmk_ph_beautifulsoup.parse_html)
 
 try:
-    from . import bkmk_ph_html5
+    from . import bkmk_ph_beautifulsoup4
 except ImportError:
     pass
 else:
-    parsers.append(bkmk_ph_html5.parse_html)
+    bkmk_ph_beautifulsoup4.DEFAULT_CHARSET = DEFAULT_CHARSET
+    parsers.append(bkmk_ph_beautifulsoup4.parse_html)
 
 try:
-    from . import bkmk_ph_lxml
+    from . import bkmk_ph_htmlparser
 except ImportError:
     pass
 else:
-    parsers.append(bkmk_ph_lxml.parse_html)
+    parsers.append(bkmk_ph_htmlparser.parse_html)
 
 try:
-    from . import bkmk_ph_htmlparser
+    from . import bkmk_ph_lxml
 except ImportError:
     pass
 else:
-    parsers.append(bkmk_ph_htmlparser.parse_html)
-
-# ElementTidy often segfaults
-# try:
-#     from . import bkmk_ph_etreetidy
-# except ImportError:
-#     pass
-# else:
-#     parsers.append(bkmk_ph_etreetidy.parse_html)
+    parsers.append(bkmk_ph_lxml.parse_html)
 
 universal_charset = "utf-8"
 entity_re = re.compile("(&\\w+;)")