-
Notifications
You must be signed in to change notification settings - Fork 64
/
Copy pathregex_htmlparser1.py
147 lines (111 loc) · 4.37 KB
/
regex_htmlparser1.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
"""
HTML
Hypertext Markup Language is a standard markup language used for creating World Wide Web pages.
Parsing
Parsing is the process of syntactic analysis of a string of symbols. It involves resolving a string into its component parts and describing their syntactic roles.
HTMLParser
An HTMLParser instance is fed HTML data and calls handler methods when start tags, end tags, text, comments, and other markup elements are encountered.
Example (based on the original Python documentation):
Code
from HTMLParser import HTMLParser
# create a subclass and override the handler methods
class MyHTMLParser(HTMLParser):
def handle_starttag(self, tag, attrs):
print "Found a start tag :", tag
def handle_endtag(self, tag):
print "Found an end tag :", tag
def handle_startendtag(self, tag, attrs):
print "Found an empty tag :", tag
# instantiate the parser and fed it some HTML
parser = MyHTMLParser()
parser.feed("<html><head><title>HTML Parser - I</title></head>"
+"<body><h1>HackerRank</h1><br /></body></html>")
Output
Found a start tag : html
Found a start tag : head
Found a start tag : title
Found an end tag : title
Found an end tag : head
Found a start tag : body
Found a start tag : h1
Found an end tag : h1
Found an empty tag : br
Found an end tag : body
Found an end tag : html
.handle_starttag(tag, attrs)
This method is called to handle the start tag of an element. (For example: <div class='marks'>)
The tag argument is the name of the tag converted to lowercase.
The attrs argument is a list of (name, value) pairs containing the attributes found inside the tag’s <> brackets.
.handle_endtag(tag)
This method is called to handle the end tag of an element. (For example: </div>)
The tag argument is the name of the tag converted to lowercase.
.handle_startendtag(tag,attrs)
This method is called to handle the empty tag of an element. (For example: <br />)
The tag argument is the name of the tag converted to lowercase.
The attrs argument is a list of (name, value) pairs containing the attributes found inside the tag’s <> brackets.
Task
You are given an HTML code snippet of lines.
Your task is to print start tags, end tags and empty tags separately.
Format your results in the following way:
Start : Tag1
End : Tag1
Start : Tag2
-> Attribute2[0] > Attribute_value2[0]
-> Attribute2[1] > Attribute_value2[1]
-> Attribute2[2] > Attribute_value2[2]
Start : Tag3
-> Attribute3[0] > None
Empty : Tag4
-> Attribute4[0] > Attribute_value4[0]
End : Tag3
End : Tag2
Here, the -> symbol indicates that the tag contains an attribute. It is immediately followed by the name of the attribute and the attribute value.
The > symbol acts as a separator of the attribute and the attribute value.
If an HTML tag has no attribute then simply print the name of the tag.
If an attribute has no attribute value then simply print the name of the attribute value as None.
Note: Do not detect any HTML tag, attribute or attribute value inside the HTML comment tags (<!-- Comments -->).Comments can be multiline as well.
Input Format
The first line contains integer , the number of lines in a HTML code snippet.
The next lines contain HTML code.
Constraints
Output Format
Print the HTML tags, attributes and attribute values in order of their occurrence from top to bottom in the given snippet.
Use proper formatting as explained in the problem statement.
Sample Input
2
<html><head><title>HTML Parser - I</title></head>
<body data-modal-target class='1'><h1>HackerRank</h1><br /></body></html>
Sample Output
Start : html
Start : head
Start : title
End : title
End : head
Start : body
-> data-modal-target > None
-> class > 1
Start : h1
End : h1
Empty : br
End : body
End : html
"""
# Enter your code here. Read input from STDIN. Print output to STDOUT
from HTMLParser import HTMLParser
# create a subclass and override the handler methods
class MyHTMLParser(HTMLParser):
def handle_starttag(self, tag, attrs):
print "Start :", tag
#print attrs
for i in attrs:
print "-> %s > %s"%(i[0],i[1])
def handle_endtag(self, tag):
print "End :", tag
def handle_startendtag(self, tag, attrs):
print "Empty :", tag
for i in attrs:
print "-> %s > %s"%(i[0],i[1])
data = [ raw_input() for _ in xrange(input())]
moddata = ''.join(data)
parser = MyHTMLParser()
parser.feed(moddata)