Function _stripDoctype

pattern/web/feed/feedparser.py:3749–3779

Strips DOCTYPE from XML document, returns (rss_version, stripped_data) rss_version may be 'rss091n' or None stripped_data is the same XML document, minus the DOCTYPE

(data)

    return newdata.encode('utf-8')

def _stripDoctype(data):
    '''Strips DOCTYPE from XML document, returns (rss_version, stripped_data)

    rss_version may be 'rss091n' or None
    stripped_data is the same XML document, minus the DOCTYPE
    '''
    start = re.search(_s2bytes('<\w'), data)
    start = start and start.start() or -1
    head,data = data[:start+1], data[start+1:]

    entity_pattern = re.compile(_s2bytes(r'^\s*<!ENTITY([^>]*?)>'), re.MULTILINE)
    entity_results=entity_pattern.findall(head)
    head = entity_pattern.sub(_s2bytes(''), head)
    doctype_pattern = re.compile(_s2bytes(r'^\s*<!DOCTYPE([^>]*?)>'), re.MULTILINE)
    doctype_results = doctype_pattern.findall(head)
    doctype = doctype_results and doctype_results[0] or _s2bytes('')
    if doctype.lower().count(_s2bytes('netscape')):
        version = u'rss091n'
    else:
        version = None

    # only allow in 'safe' inline entity definitions
    replacement=_s2bytes('')
    if len(doctype_results)==1 and entity_results:
        safe_pattern=re.compile(_s2bytes('\s+(\w+)\s+"(&#\w+;|[^&"]*)"'))
        safe_entities=filter(lambda e: safe_pattern.match(e),entity_results)
        if safe_entities:
            replacement=_s2bytes('<!DOCTYPE feed [\n  <!ENTITY') + _s2bytes('>\n  <!ENTITY ').join(safe_entities) + _s2bytes('>\n]>')
    data = doctype_pattern.sub(replacement, head) + data

    return version, data, dict(replacement and [(k.decode('utf-8'), v.decode('utf-8')) for k, v in safe_pattern.findall(replacement)])

def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=None, request_headers=None, response_headers=None):
    ''&#x27;Parse a feed from a URL, file, stream, or string.