def __init__(self):
#super(SearchParser, self).__init__(self)
if badhtml:
HTMLParser.__init__(self, NullFormatter())
else:
HTMLParser.__init__(self)
self.urls = []
def __init__(self, attr=None, tags=None):
if attr is None: attr = 'href'
if tags is None: tags = ('a', )
self.__attr = attr
self.__tags = tags
self.__P = HTMLParser(NullFormatter())
self.__saved = []
self.__tagHandlers = {}
def compactor(dev_filename, rel_filename):
# Use compactor to generate release version.
echo('Compacting: %s -> %s' % (dev_filename, rel_filename))
source_data = open(dev_filename, 'r').read()
try:
# Verify that the html file is correct
htmlparser = HTMLParser(NullFormatter())
htmlparser.feed(source_data)
htmlparser.close()
# Now try to minify
output_file = open(rel_filename, 'wb')
compactor = HTMLMinifier(output_file.write, True)
compactor.feed(source_data)
compactor.close()
output_file.close()
except HTMLParseError as e:
error(str(e))
exit(1)
#coding:utf-8
import urllib2
from htmllib import HTMLParser
from formatter import NullFormatter
import os
import re
url_name = "http://b.hatena.ne.jp/hotentry"
html_data = urllib2.urlopen(url_name)
parser = HTMLParser(NullFormatter())
try:
parser.feed(html_data.read())
except TypeError:
print "type error"
pat = re.compile("^http.*")
for link in parser.anchorlist:
x = pat.search(link)
if x is not None:
print x.group(0)
def __init__(self):
HTMLParser.__init__(self, NullFormatter())
self.clear_serv()
def __init__(self):
HTMLParser.__init__(self, NullFormatter())
def __init__ (self):
HTMLParser.__init__(self, NullFormatter())
self.reg = re.compile(r'.+/(?P<name>.+\.(?:' + "|".join(_IMAGE_EXT) + ')).*$')
self.links = []
def __init__(self):
NullFormatter.__init__(self)
self.result = []