Untitled

In [1]: import py_streamhtmlparser
    parser = py_streamhtmlparser.HtmlParser()
    html = """<html><body><a href='http://google.com'>link</a></body></html>"""
    for index, character in enumerate(html):
       parser.Parse(character)
       print index, character, parser.Tag(), parser.Attribute(), parser.Value(), parser.ValueIndex()


In [2]:    ...:    ...:    ...:    ...:    ...: Out[2]: 1
0 < None None None None
Out[2]: 1
1 h None None None None
Out[2]: 1
2 t None None None None
Out[2]: 1
3 m None None None None
Out[2]: 1
4 l None None None None
Out[2]: 0
5 > html None None None
Out[2]: 1
6 < html None None None
Out[2]: 1
7 b None None None None
Out[2]: 1
8 o None None None None
Out[2]: 1
9 d None None None None
Out[2]: 1
10 y None None None None
Out[2]: 0
11 > body None None None
Out[2]: 1
12 < body None None None
Out[2]: 1
13 a None None None None
Out[2]: 1
14   a None None None
Out[2]: 2
15 h a  None None
Out[2]: 2
16 r a  None None
Out[2]: 2
17 e a  None None
Out[2]: 2
18 f a  None None
Out[2]: 3
19 = a href href 0
Out[2]: 3
20 ' a href href 0
Out[2]: 3
21 h a href h 1
Out[2]: 3
22 t a href ht 2
Out[2]: 3
23 t a href htt 3
Out[2]: 3
24 p a href http 4
Out[2]: 3
25 : a href http: 5
Out[2]: 3
26 / a href http:/ 6
Out[2]: 3
27 / a href http:// 7
Out[2]: 3
28 g a href http://g 8
Out[2]: 3
29 o a href http://go 9
Out[2]: 3
30 o a href http://goo 10
Out[2]: 3
31 g a href http://goog 11
Out[2]: 3
32 l a href http://googl 12
Out[2]: 3
33 e a href http://google 13
Out[2]: 3
34 . a href http://google. 14
Out[2]: 3
35 c a href http://google.c 15
Out[2]: 3
36 o a href http://google.co 16
Out[2]: 3
37 m a href http://google.com 17
Out[2]: 1
38 ' a None None None
Out[2]: 0
39 > a None None None
Out[2]: 0
40 l a None None None
Out[2]: 0
41 i a None None None
Out[2]: 0
42 n a None None None
Out[2]: 0
43 k a None None None
Out[2]: 1
44 < a None None None
Out[2]: 1
45 / None None None None
Out[2]: 1
46 a None None None None
Out[2]: 0
47 > None None None None
Out[2]: 1
48 < None None None None
Out[2]: 1
49 / None None None None
Out[2]: 1
50 b None None None None
Out[2]: 1
51 o None None None None
Out[2]: 1
52 d None None None None
Out[2]: 1
53 y None None None None
Out[2]: 0
54 > None None None None
Out[2]: 1
55 < None None None None
Out[2]: 1
56 / None None None None
Out[2]: 1
57 h None None None None
Out[2]: 1
58 t None None None None
Out[2]: 1
59 m None None None None
Out[2]: 1
60 l None None None None
Out[2]: 0
61 > None None None None