DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic
parsers = []
+
+try:
+ import parse_html_html5
+except ImportError:
+ pass
+else:
+ parsers.append(parse_html_html5.parse_html)
+
try:
import parse_html_beautifulsoup
parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET
else:
parsers.append(parse_html_beautifulsoup.parse_html)
-from parse_html_htmlparser import parse_html
-parsers.append(parse_html)
+try:
+ from parse_html_htmlparser import parse_html
+except ImportError:
+ pass
+else:
+ parsers.append(parse_html)
import re
def parse_html(filename, charset=None, log=None):
+ if not parsers:
+ return None
+
if charset:
try:
codecs.lookup(charset) # In case of unknown charset...
charsets = [universal_charset, DEFAULT_CHARSET]
if charset:
charset = charset.lower().replace("windows-", "cp")
- if charset not in charsets:
- charsets.insert(0, charset)
+ if charset in charsets:
+ charsets.remove(charset)
+ charsets.insert(0, charset)
for p in parsers:
parser = None