Пример #1
0
def keyWordExtraction():
  description = {'Title': 'Software Engineer', 'Skill': ['Microsoft Office', 'Data Mining', 'Image Processing','Android','MySQL'], 'Certification': 'Random value', 'Volunteering': 'Random value'}
  resumesInput = []
  resumes = []

  decorators = {'Skill':ex.skills_dec , 'Language':ex.language_dec , 'Experience':ex.experience_dec}
  extractor = ex.get_base
  decorator = ex.experience_dec
  extractor = decorator(extractor)
  for key in job_description:
    decorator = decorators.get(key)
    if decorator!= None:
      extractor = decorator(extractor)

  # decorator = decorators["Language"]
  # extractor = decorator(extractor)
  # decorator = decorators["Experience"]
  # extractor = decorator(extractor)

  resumesInput.append('static/IsenNg.pdf')
  resumesInput.append('static/DonnabelleEmbodo.pdf')
  resumesInput.append('static/DesmondLim.pdf')
  resumesInput.append('static/JinYuanTeo.pdf')
 
  for resumeInput in resumesInput:
    forExtractorInput = convertPDF.convertWithCoordinatesPara(resumeInput)
    resume = extractor(forExtractorInput['pdfText'])
    resume = "{" + resume +"}"
    resumes.append(resume)

  first = True
  output = "["
  for resume in resumes:
    if first:
      output = output + resume
      first = False
    else:
      output = output + "," + resume

  output = output + "]"

  forAnalyzer = ast.literal_eval(output)
  #print forAnalyzer
  result = analyzer.process_analyzer(description, forAnalyzer)

  return output
Пример #2
0
def analyzeCV():

  #setup extractor with base and decorators
  decorators = {'Skill':ex.skills_dec , 'Language':ex.language_dec , 'Experience':ex.experience_dec}
  extractor = ex.get_base
  decorator = decorators["Skill"]
  extractor = decorator(extractor)
  decorator = decorators["Experience"]
  extractor = decorator(extractor)
  decorator = decorators["Language"]
  extractor = decorator(extractor)

  #retrieve files from static
  resumesDir = os.listdir('static')
  resumeFiles = []
  resumes = []

  for resumeFile in resumesDir:
    if resumeFile.endswith(".pdf"):
      resumeFiles.append('static/'+ resumeFile)
  
  for resumeFile in resumeFiles:
    forExtractorInput = convertPDF.convertWithCoordinatesPara(resumeFile)
    resume = extractor(forExtractorInput['pdfText'])
    resume = "{" + resume +"}"
    resumes.append(resume)

  first = True
  analyzerResumesInput = "["
  for resume in resumes:
    if first:
      analyzerResumesInput = analyzerResumesInput + resume
      first = False
    else:
      analyzerResumesInput = analyzerResumesInput + "," + resume

  print job_description
  analyzerResumesInput = analyzerResumesInput + "]"
  analyzerDictResumesInput = ast.literal_eval(analyzerResumesInput)
  result = analyzer.process_analyzer(job_description, analyzerDictResumesInput)
  return json.dumps(result)