How can I use the HTMLParser python library to retrieve data from a specific div tag?

Question

I am trying to get the value from an HTML page using the HTML-Python library. The value I want to get is inside this html element:

...
<div id="remository">20</div>
...

This is my HTMLParser class:

class LinksParser(HTMLParser.HTMLParser):
  def __init__(self):
    HTMLParser.HTMLParser.__init__(self)
    self.seen = {}

  def handle_starttag(self, tag, attributes):
    if tag != 'div': return
    for name, value in attributes:
    if name == 'id' and value == 'remository':
      #print value
      return

  def handle_data(self, data):
    print data


p = LinksParser()
f = urllib.urlopen("http://domain.com/somepage.html")
html = f.read()
p.feed(html)
p.close()

Can someone point me in the right direction? I want the functionality of the class to get a value of 20.

Answer 1

class LinksParser(HTMLParser.HTMLParser):
  def __init__(self):
    HTMLParser.HTMLParser.__init__(self)
    self.recording = 0
    self.data = []

  def handle_starttag(self, tag, attributes):
    if tag != 'div':
      return
    if self.recording:
      self.recording += 1
      return
    for name, value in attributes:
      if name == 'id' and value == 'remository':
        break
    else:
      return
    self.recording = 1

  def handle_endtag(self, tag):
    if tag == 'div' and self.recording:
      self.recording -= 1

  def handle_data(self, data):
    if self.recording:
      self.data.append(data)

self.recordingcounts the number of nested tags div, starting with the "trigger". When we are in a subtree embedded in a trigger tag, we accumulate data in self.data.

self.data ( , , , ). , .

, 'div', 'id' 'remository', self.tag, self.attname self.attvalue, __init__ - , ( , ).

Answer 2

BeautifulSoup?

from bs4 import BeautifulSoup
soup = BeautifulSoup('<div id="remository">20</div>')
tag=soup.div
print(tag.string)

20 .

Answer 3

3

HTMLParser.HTMLParser.__init__(self)

HTMLParser.__init__(self)

,

import urllib2 

from HTMLParser import HTMLParser  

class MyHTMLParser(HTMLParser):

  def __init__(self):
    HTMLParser.__init__(self)
    self.recording = 0 
    self.data = []
  def handle_starttag(self, tag, attrs):
    if tag == 'required_tag':
      for name, value in attrs:
        if name == 'somename' and value == 'somevale':
          print name, value
          print "Encountered the beginning of a %s tag" % tag 
          self.recording = 1 


  def handle_endtag(self, tag):
    if tag == 'required_tag':
      self.recording -=1 
      print "Encountered the end of a %s tag" % tag 

  def handle_data(self, data):
    if self.recording:
      self.data.append(data)

 p = MyHTMLParser()
 f = urllib2.urlopen('http://www.someurl.com')
 html = f.read()
 p.feed(html)
 print p.data
 p.close()

`

Answer 4

:

print (soup.find('the tag').text)