Copy third-party modules to the source tree.

[bookmarks_db.git] / Robots / parse_html.py

diff --git a/Robots/parse_html.py b/Robots/parse_html.py
index 23f53e49cae938701e02a6b39db4538080ef5ffb..228a3ceaddff6c0fe1acc8af64a374f348c5bb27 100755 (executable)
--- a/Robots/parse_html.py
+++ b/Robots/parse_html.py
@@ -13,19 +13,19 @@ DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic
 parsers = []
 
 try:
-   import parse_html_html5
+   import parse_html_beautifulsoup
+   parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET
 except ImportError:
    pass
 else:
-   parsers.append(parse_html_html5.parse_html)
+   parsers.append(parse_html_beautifulsoup.parse_html)
 
 try:
-   import parse_html_beautifulsoup
-   parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET
+   from parse_html_lxml import parse_html
 except ImportError:
    pass
 else:
-   parsers.append(parse_html_beautifulsoup.parse_html)
+    parsers.append(parse_html)
 
 try:
    from parse_html_htmlparser import parse_html
@@ -34,6 +34,13 @@ except ImportError:
 else:
     parsers.append(parse_html)
 
+try:
+   import parse_html_html5
+except ImportError:
+   pass
+else:
+   parsers.append(parse_html_html5.parse_html)
+
 
 import re
 from htmlentitydefs import name2codepoint
@@ -94,6 +101,9 @@ def parse_html(filename, charset=None, log=None):
       else:
          if log: log("Parser %s.%s failed, trying next one." % (p.__module__, p.__name__))
 
+   if not parser:
+       return None
+
    converted_title = title = parser.title
    if title and (not parser.charset):
       try: