Get a value of a place in web page

exchange.py

#!/usr/bin/env python
# coding: utf-8

class Exchange( object ):
    def __init__( self, url ):
        '''
        External Dependencies: Pycurl and BeautifulSoup
        '''
        output = False
        try:
            import pycurl
            import StringIO
            
            self.curl = pycurl
            self.StringIO = StringIO
            self.url = url
            self.soup = ''
            self.soupJSON = ''
            self._cobweb = ''
        except ImportError:
            return output

    def getContentUrl( self ):
        '''
        Go to url and get content
        '''
        output = False
        try:
            curl = self.curl
            StringIO = self.StringIO
            url = self.url
            
            if url:
                cinit = curl.Curl()
                cinit.setopt( curl.URL, url )
                cinit.setopt( curl.HTTPHEADER, ['Accepted:'] )
                IO = StringIO.StringIO()
                cinit.setopt( curl.WRITEFUNCTION, IO.write )
                cinit.setopt( curl.FOLLOWLOCATION, 1 )
                cinit.setopt( curl.MAXREDIRS, 5 )
                cinit.perform()

                output = IO.getvalue()
            
            return output
        except Exception:
            return output

    def setSoup( self ):
        '''
        Set soup in the instance

        >>> Exchange('www.google.com').setSoup()
        True
        >>> Exchange('').setSoup()
        False
        '''
        output = False
        try:
            import BeautifulSoup

            contentUrl = self.getContentUrl()
            soup = BeautifulSoup.BeautifulSoup( contentUrl )
            
            if soup:
                self.soup = soup
                output = True

            return output
        except Exception:
            return output
        except ImportError:
            return output

    def getSoup( self ):
        '''
        Make a soup of content was setted
        '''
        output = False
        try:
            if self.soup:
                output = self.soup
            elif not self.soup:
                if self.setSoup():
                    if self.soup:
                        output = self.soup
            return output
        except Exception:
            return output

    def getJSON( self ):
        '''
        Make a JSON soup decoded
        '''
        output = False
        try:
            import json

            if self.soup or not self.soup:
                if self.setSoup() and self.soupJSON or not self.soupJSON:
                    self.soupJSON = json.loads( self.soup.string )
                    
                    if self.soupJSON:
                        output = True
            return output
        except Exception:
            return output
        except ImportError:
            return output

    def getIdentifier( self, pattern='' ):
        '''
        Select using the pattern of tag, tag#id or tag.class
        '''
        # Identifier tag and attribute
        output = False
        try:
            # Html tags and html attributes identifiers
            ids = {
                'id': '#',
                'class': '.',
            }
        
            if pattern:
                if ids['id'] in pattern:
                    output = pattern.split( ids['id'] )
                if ids['class'] in pattern:
                    output = pattern.split( ids['class'] )
                else:
                    output = [ pattern ]

            return output
        except Exception:
            return output

    def getSpidering( self, pattern='' ):
        '''
        Surround the content of url into the mark pattern

        >>> emptyTest = Exchange('')
        >>> emptyTest.getSpidering()
        False
        >>> notEmptyTest = Exchange('http://economia.uol.com.br/cotacoes/cambio.jhtm')
        >>> notEmptyTest.getSpidering('div.col-mod1')
        True
        >>> notEmptyTest = Exchange('http://economia.uol.com.br/cotacoes/cambio.jhtm')
        >>> notEmptyTest.getSpidering('div.col-mod1>table>tbody')
        True
        '''
        output = False
        try:
            if pattern:
                if self.setSoup():
                    soup = self.soup
                    pattern = pattern.split('>')
                    cobweb = ''

                    for topLevel in pattern:
                        level = self.getIdentifier( topLevel )

                        if not cobweb:
                            if len( level ) == 1:
                                cobweb = soup.find( level[0] )
                            if len( level ) > 1:
                                cobweb = soup.find( level[0], level[1] )

                    self._cobweb = cobweb
                    if self._cobweb:
                        output = True

            return output
        except Exception:
            return output

    def getChilds( self, pattern='' ):
        '''
        Get deep selection
        '''
        output = False
        try:
            if pattern:
                if self._cobweb:
                    if len( self.getIdentifier( pattern ) ) == 1:
                        output = self._cobweb
                        output = output.findAll( pattern )
            return output
        except Exception:
            return output
    
if __name__ == '__main__':
    import doctest; doctest.testmod()