python解析html/xml

解析html

from HTMLParser import HTMLParser
import sys

class TestParser(HTMLParser):
    def __init__(self):
        self.title = ''
        self.readingtitle = 0
        self.body = ''
        self.readingbody = 0
        HTMLParser.__init__(self)


    def handle_starttag(self, tag, attrs):
        if self.readingbody:
            self.body += '<'+tag+'>'
        if tag == 'title':
            self.readingtitle = 1
        elif tag == 'body':
            self.readingbody = 1


    def handle_data(self, data):
        if self.readingtitle:
            self.title += data
        elif self.readingbody:
            self.body += data


    def handle_endtag(self, tag):
        if tag == 'title':
            self.readingtitle = 0
        elif tag == 'body':
            self.readingbody = 0
        if self.readingbody:
            self.body += '<'+tag+'>'
            
    def gettitle(self):
        return self.title


    def getbody(self):
        return self.body

# testparser.py test.html
#fd = open(sys.argv[1])
fd = open("test.html");
tp = TestParser()
tp.feed(fd.read())
print "Title is:", tp.gettitle()
print "Body is:", tp.getbody()

对于不严格的html（比如缺少关闭tag），可以使用TidyLib。

<html>
<head>
    <title>Document Title</title>
</head>
<body>
    <p>This is a text</p>
</body>
</html>

输出

>>> 
Title is: Document Title
Body is: 
    <p>This is a text<p>

解析xml

from xml.dom import minidom, Node
import sys

def scanNode(node, level = 0):
    msg = node.__class__.__name__
    if node.nodeType == Node.ELEMENT_NODE:
        msg += ", tag: " + node.tagName
    print level, msg
    if node.hasChildNodes:
        for child in node.childNodes:
            scanNode(child, level + 1)

# testparser.py test.xml
doc = minidom.parse("test.xml");
scanNode(doc)

test.xml

<?xml version="1.0" encoding="utf-8" standalone="no"?>
<books>
    <book author="moyan">
        <name>fengrufeitun</name>
        <price>12</price>
    </book>
</books>

输出

>>> 
0 Document
1 Element, tag: books
2 Text
2 Element, tag: book
3 Text
3 Element, tag: name
4 Text
3 Text
3 Element, tag: price
4 Text
3 Text
2 Text

猜你喜欢