Python: Extracting specific data with html parser
I started using the HTMLParser in Python to extract data from a website. I get everything I wanted, except the text within two tags of HTML. Here is an example of the HTML tag:
<a href="http://wold.livingsources.org/vocabulary/1" title="Swahili" class="Vocabulary">Swahili</a>
There are also other tags starting with . They have other attributes and values and therefore I do not want to have their data:
<a href="http://wold.livingsources.org/contributor#schadebergthilo" title="Thilo Schadeberg" class="Contributor">Thilo Schadeberg</a>
The tag is an embedded tag within a table. I don't know if this makes any difference between other tags. I only want the information in some of the tags called 'a' with the attribute class="Vocabulary" and I want the data within the tag, in the example it would be "Swahili". So what I did is:
class AllLanguages(HTMLParser):
'''
classdocs
'''
#counter for the languages
#countLanguages = 0
def __init__(self):
HTMLParser.__init__(self)
self.inLink = False
self.dataArray = []
self.countLanguages = 0
self.lasttag = None
self.lastname = None
self.lastvalue = None
#self.text = ""
def handle_starttag(self, tag, attr):
#print "Encountered a start tag:", tag
if tag == 'a':
for name, value in attr:
if name == 'class' and value == 'Vocabulary':
self.countLanguages += 1
self.inLink = True
self.lasttag = tag
#self.lastname = name
#self.lastvalue = value
print self.lasttag
#print self.lastname
#print self.lastvalue
#return tag
print self.countLanguages
def handle_endtag(self, tag):
if tag == "a":
self.inlink = False
#print "".join(self.data)
def handle_data(self, data):
if self.lasttag == 'a' and self.inLink and data.strip():
#self.dataArray.append(data)
#
print data
The programm prints every data which is included in an tag, but I only want the one included in the tag with the right attributes. How do I get this specific data?
Answer
Looks like you forgot to set self.inLink = False in handle_starttag by default:
from HTMLParser import HTMLParser
class AllLanguages(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.inLink = False
self.dataArray = []
self.countLanguages = 0
self.lasttag = None
self.lastname = None
self.lastvalue = None
def handle_starttag(self, tag, attrs):
self.inLink = False
if tag == 'a':
for name, value in attrs:
if name == 'class' and value == 'Vocabulary':
self.countLanguages += 1
self.inLink = True
self.lasttag = tag
def handle_endtag(self, tag):
if tag == "a":
self.inlink = False
def handle_data(self, data):
if self.lasttag == 'a' and self.inLink and data.strip():
print data
parser = AllLanguages()
parser.feed("""
<html>
<head><title>Test</title></head>
<body>
<a href="http://wold.livingsources.org/vocabulary/1" title="Swahili" class="Vocabulary">Swahili</a>
<a href="http://wold.livingsources.org/contributor#schadebergthilo" title="Thilo Schadeberg" class="Contributor">Thilo Schadeberg</a>
<a href="http://wold.livingsources.org/vocabulary/2" title="English" class="Vocabulary">English</a>
<a href="http://wold.livingsources.org/vocabulary/2" title="Russian" class="Vocabulary">Russian</a>
</body>
</html>""")
prints:
Swahili
English
Russian
Also, take a look at:
Hope that helps.