Das deutsche Python-Forum

Code: Alles auswählen

MetaTyp = "name"
MetaTypDesc = "Keywords"
regex='(?i)<meta *%(typ)s=["%(X)s]%(desc)s["%(X)s] *content=["%(X)s](.+)["%(X)s]' % {
    "typ"  : MetaTyp,
    "desc" : MetaTypDesc,
    "X"    : "'"
}
print re.findall(regex, text)

Code: Alles auswählen

regex='''(?i)<meta *%(typ)s=["']%(desc)s["'] *content=["'](.+)["']'''

Code: Alles auswählen

from sgmllib import SGMLParser
import urllib

class MetaContentParser(SGMLParser):
	def start_meta(self, eigenschaften):
                print eigenschaften

Fp = urllib.urlopen("http://www.drweb.de/verwaltung/index.shtml")
Parser = MetaContentParser()
Parser.feed(Fp.read())
Fp.close()
Parser.close()

Code: Alles auswählen

import sgmllib

class MetaContentParser(sgmllib.SGMLParser):

    from htmlentitydefs import entitydefs # replace entitydefs from sgmllib

    def __init__(self):
        self.inBody = False
        sgmllib.SGMLParser.__init__(self, 0)
        self.metaData = []
        self.data = ""
        self.hrefData = []

    def start_a( self, hrefInfo ):
        self.hrefData.append( hrefInfo )

    def start_meta(self, metaData):
        self.metaData.append(metaData)

    def handle_data( self, data ) :
        if data=="\n": return
        self.data = self.data + data

    def handle_entityref(self, name):
        if self.entitydefs.has_key(name):
            self.data += self.entitydefs[name]
        else:
            self.data += "&"+name+";"

    def get_meta( self ):
        return self.metaData

    def get_a( self ):
        return self.hrefData

    def get_data( self ):
        return self.data

f = open("index.html")

Parser = MetaContentParser()
Parser.feed(f.read())
f.close()
print Parser.get_data()

for i in Parser.get_meta(): print i

for i in Parser.get_a(): print i
Parser.close()