4grab/htmlparser.py

31 lines
860 B
Python
Raw Normal View History

import sgmllib
import re
class MyParser(sgmllib.SGMLParser):
def __init__(self, verbose=0):
sgmllib.SGMLParser.__init__(self, verbose)
self.hyperlinks = []
self.url_reg = re.compile('res/\d+\Z')
self.prev = ""
def parse(self, s):
self.feed(s)
self.close()
def start_a(self, attributes):
for name, value in attributes:
if name == "href":
if self.url_reg.search(value) != None:
if self.prev != value:
self.hyperlinks.append(value)
self.prev = value
def get_hyperlinks(self):
return self.hyperlinks
class MySubParser(MyParser):
def __init__(self, verbose=0):
MyParser.__init__(self, verbose)
self.url_reg = re.compile('/src/\d+\.\w{3,4}\Z')