def parsing_jd(jd_file_name):
path = file_loc + jd_file_name + '.txt'
for file in glob.glob(path, recursive=True):
if not file in job_desc_files:
job_desc_files.append(file)
with open(path, 'rt') as file:
jd = file.read()
jd = summarize(jd, word_count=200)
file.close()
jd = text_process.normalize(jd)
df = pd.DataFrame(columns=['Path', 'File Name', 'Text'])
df.loc[0] = [path, jd_file_name, jd]
return df
def extract_text_from_pdf(files_list):
resumes = [] # Stores final processed resume files
for pdf_path in files_list:
text = ''
with open(pdf_path, 'rb') as fh:
# iterate over all pages of PDF document
for page in PDFPage.get_pages(fh, caching=True, check_extractable=True):
# creating a resoure manager
resource_manager = PDFResourceManager()
# create a file handle
fake_file_handle = StringIO()
# creating a text converter object
converter = TextConverter(
resource_manager,
fake_file_handle,
codec='utf-8',
laparams=LAParams()
)
# creating a page interpreter
page_interpreter = PDFPageInterpreter(
resource_manager,
converter
)
# process current page
page_interpreter.process_page(page)
# extract text
text += fake_file_handle.getvalue()
text = text.replace('\n', ' ')
# close open handles
converter.close()
fake_file_handle.close()
resumes.append(text_process.normalize(text))
for name in resume_list:
#print(name)
temp = name.split('.')[0]
temp = temp.split('/')[1]
file_names.append(temp)
df = {'Path':resume_list, 'File Name': file_names, 'Text':resumes}
data = pd.DataFrame(df)
data.to_csv('out.csv')
return data