Archive for July 18th, 2009

Can be run from the command line or in another application. Built for Python 2.4 with pyCURL

View Code PYTHON

import sys, pycurl, re, time, string, urllib from datetime import date import xml.dom.minidom   class WordZe:   def __init__(self, key='ADD YOUR KEY HERE'): self.apiKey = key self.caretakerObj = WordZeCaretaker() self.userAgent = 'Mozilla/5.0 (Windows; U; Windows NT 6.1; es-ES; rv:1.9.1) Gecko/20090624 Firefox/3.5 (.NET CLR 3.5.30729)'   def singleKeywordLookup(self, keyList = []): if len(keyList) == 0: raise Error('You need to pass a list to the singleKeywordLookup to perform a request.') else: # TODO: DB CHECK FOR VALUE PULLED WITHIN LAST 30 DAYS keyString = string.join(keyList, ',')   requestObj = pycurl.Curl()   requestObj.setopt(pycurl.USERAGENT, self.userAgent) requestObj.setopt(pycurl.FOLLOWLOCATION, 1) requestObj.setopt(pycurl.WRITEFUNCTION, self.caretakerObj.remotecallback) requestObj.setopt(pycurl.HTTPGET, 1)   keyString = str(keyString).replace(' ','+') requestObj.setopt(pycurl.URL, str('http://api.wordze.com/KeywordSingle?ApiKey=' + str(self.apiKey) + '&Query=' + str(keyString))) requestObj.perform() requestObj.close()   return self.caretakerObj.getDict()   class WordZeCaretaker:   def __init__(self): self.contents = ''   def getDict(self): docMod = xml.dom.minidom.parseString(self.contents) return self.handleKeywords(docMod)   def handleKeywords(self, docMod): returnDict = [] keywords = docMod.getElementsByTagName("Keyword") for keyword in keywords: keyDict = { 'keyword':self.getText(keyword.childNodes), 'count':int(keyword.attributes['Count'].value), 'estimated':int(keyword.attributes['Estimated'].value) } returnDict.append(keyDict) # TODO: DB INSERT   return returnDict   def getText(self,nodelist): rc = "" for node in nodelist: if node.nodeType == node.TEXT_NODE: rc = rc + node.data return rc   def remotecallback(self, buf): self.contents = self.contents + buf   if __name__ == '__main__': lookupObj = WordZe() keywords = raw_input('Comma sep, no spaces list of terms: ') termList = str(keywords).split(',') cleanList = [] for term in termList: cleanList.append(str(term)) lookupObj.singleKeywordLookup(cleanList)