def convert2(self, doc, encoding, mimetype):
# convert to unicode
if not isinstance(doc, unicode):
doc = unicode(doc, encoding, 'replace')
doc = convert_entities(doc)
result = self.convert(doc)
# convert back to utf-8
return result.encode('utf-8'), 'utf-8'
def convert2(self, doc, encoding, mimetype):
# Use encoding from XML preamble if present
mo = encoding_reg.search(doc)
if mo:
encoding = mo.group(1)
if not isinstance(doc, unicode):
doc = unicode(doc, encoding, 'replace')
doc = convert_entities(doc)
doc = doc.encode('utf-8')
return self.convert(doc), 'utf-8'
def convert(self, doc, encoding=None, mimetype=None,
logError=False, raiseException=False):
# convert to unicode
if not isinstance(doc, unicode):
if not encoding:
mo = charset_reg.search(doc)
if mo is not None:
encoding = mo.group(1)
else:
encoding = 'ascii' # guess
doc = unicode(doc, encoding, 'replace')
doc = convert_entities(doc)
result = html2text(doc)
# convert back to utf-8
return result.encode('utf-8'), 'utf-8'
def convert(self, doc, encoding, mimetype,
logError=False, raiseException=False):
# Use encoding from XML preamble if present
mo = encoding_reg.search(doc)
if mo:
encoding = mo.group(1)
if not encoding:
encoding = default_encoding
if not isinstance(doc, unicode):
doc = unicode(doc, encoding, 'replace')
doc = convert_entities(doc)
doc = doc.encode('utf-8')
p = StripTagParser()
p.feed(doc)
p.close()
return str(p), 'utf-8'
def convert(self,
doc,
encoding=None,
mimetype=None,
logError=False,
raiseException=False):
# convert to unicode
if not isinstance(doc, unicode):
if not encoding:
mo = charset_reg.search(doc)
if mo is not None:
encoding = mo.group(1)
else:
encoding = 'ascii' # guess
doc = unicode(doc, encoding, 'replace')
doc = convert_entities(doc)
result = html2text(doc)
# convert back to utf-8
return result.encode('utf-8'), 'utf-8'
def convert(self,
doc,
encoding,
mimetype,
logError=False,
raiseException=False):
# Use encoding from XML preamble if present
mo = encoding_reg.search(doc)
if mo:
encoding = mo.group(1)
if not encoding:
encoding = default_encoding
if not isinstance(doc, unicode):
doc = unicode(doc, encoding, 'replace')
doc = convert_entities(doc)
doc = doc.encode('utf-8')
p = StripTagParser()
p.feed(doc)
p.close()
return str(p), 'utf-8'