def extract_info(cv_dir):
extracted_info = []
files = os.listdir(cv_dir)
for file in files:
if file.endswith('.pdf'):
text = convert2txt.extract_text(cv_dir+file, '.pdf')
result = create_dic(file)
get_info(text, result)
extracted_info.append(result)
elif file.endswith('.doc'):
text = convert2txt.extract_text(cv_dir+file, '.doc')
result = create_dic(file)
get_info(text, result)
extracted_info.append(result)
elif file.endswith('.docx'):
text = convert2txt.extract_text(cv_dir+file, '.docx')
result = create_dic(file)
get_info(text, result)
extracted_info.append(result)
elif file.endswith('.txt'):
with open(cv_dir+file, encoding='utf-8-sig') as f:
text = f.read()
result = create_dic(file)
get_info(text, result)
extracted_info.append(result)
return extracted_info
def extract_mobile_numbers(cv_dir, word_limit):
extracted_mobile_numbers = {}
files = os.listdir(cv_dir)
pattern = re.compile(
r"\(?\+?[8]{2}?0?\)?\0?-?0?[0-9]{3}-?[0-9]{3}-?[0-9]{4}|[0-9]{4}-?[0-9]{3}-?[0-9]{4}|[0-9]{5}-[0-9]{6}"
)
for file in files:
if file.endswith('.pdf'):
text = convert2txt.extract_text(cv_dir + file, '.pdf')
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_mobile_numbers[file] = results
elif file.endswith('.doc'):
text = convert2txt.extract_text(cv_dir + file, '.doc')
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_mobile_numbers[file] = results
elif file.endswith('.docx'):
text = convert2txt.extract_text(cv_dir + file, '.docx')
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_mobile_numbers[file] = results
elif file.endswith('.txt'):
with open(cv_dir + file, encoding='utf-8') as f:
text = f.read()
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_mobile_numbers[file] = results
return extracted_mobile_numbers
def extract_emails(cv_dir, word_limit):
extracted_emails = {}
files = os.listdir(cv_dir)
pattern = re.compile(r'[\w\.-]+@[\w\.-]+')
for file in files:
if file.endswith('.pdf'):
text = convert2txt.extract_text(cv_dir + file, '.pdf')
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_emails[file] = results
elif file.endswith('.doc'):
text = convert2txt.extract_text(cv_dir + file, '.doc')
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_emails[file] = results
elif file.endswith('.docx'):
text = convert2txt.extract_text(cv_dir + file, '.docx')
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_emails[file] = results
elif file.endswith('.txt'):
with open(cv_dir + file, encoding='utf-8') as f:
text = f.read()
words = text.split()
text = ' '.join(words[:word_limit])
results = pattern.findall(text)
extracted_emails[file] = results
return extracted_emails
def wordcloud_a_dir(cv_dir, wc_dir):
files = os.listdir(cv_dir)
for file in files:
if file.endswith('.pdf'):
data = convert2txt.extract_text(cv_dir+file, '.pdf')
text_to_cloud(data, file, wc_dir)
elif file.endswith('.doc'):
data = convert2txt.extract_text(cv_dir+file, '.doc')
text_to_cloud(data, file, wc_dir)
elif file.endswith('.docx'):
data = convert2txt.extract_text(cv_dir+file, '.docx')
text_to_cloud(data, file, wc_dir)
elif file.endswith('.txt'):
with open(cv_dir+file, encoding='utf-8') as f:
data = f.read().replace('\n', '')
text_to_cloud(data, file, wc_dir)
def extract_names(cv_dir, word_limit):
extracted_names = {}
files = os.listdir(cv_dir)
for file in files:
if file.endswith('.pdf'):
text = convert2txt.extract_text(cv_dir + file, '.pdf')
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
extracted_names[file] = []
for e in nlp_text.ents:
extracted_names[file].append(e.text)
elif file.endswith('.doc'):
text = convert2txt.extract_text(cv_dir + file, '.doc')
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
extracted_names[file] = []
for e in nlp_text.ents:
extracted_names[file].append(e.text)
elif file.endswith('.docx'):
text = convert2txt.extract_text(cv_dir + file, '.docx')
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
extracted_names[file] = []
for e in nlp_text.ents:
extracted_names[file].append(e.text)
elif file.endswith('.txt'):
with open(cv_dir + file, encoding='utf-8') as f:
text = f.read()
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
extracted_names[file] = []
for e in nlp_text.ents:
extracted_names[file].append(e.text)
return extracted_names
def extract_info(cv_dir, word_limit):
extracted_info = []
files = os.listdir(cv_dir)
for file in files:
if file.endswith('.pdf'):
text = convert2txt.extract_text(cv_dir + file, '.pdf')
emails = extract_emails(text)
numbers = extract_mobile_numbers(text)
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
name = []
for e in nlp_text.ents:
name.append(e.text)
extracted_info.append({
'filename': file,
'name': ' '.join(name),
'number': numbers,
'email': emails
})
elif file.endswith('.doc'):
text = convert2txt.extract_text(cv_dir + file, '.doc')
emails = extract_emails(text)
numbers = extract_mobile_numbers(text)
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
name = []
for e in nlp_text.ents:
name.append(e.text)
extracted_info.append({
'filename': file,
'name': ' '.join(name),
'number': numbers,
'email': emails
})
elif file.endswith('.docx'):
text = convert2txt.extract_text(cv_dir + file, '.docx')
emails = extract_emails(text)
numbers = extract_mobile_numbers(text)
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
name = []
for e in nlp_text.ents:
name.append(e.text)
extracted_info.append({
'filename': file,
'name': ' '.join(name),
'number': numbers,
'email': emails
})
elif file.endswith('.txt'):
with open(cv_dir + file, encoding='utf-8') as f:
text = f.read()
emails = extract_emails(text)
numbers = extract_mobile_numbers(text)
words = text.split()
text = ' '.join(words[:word_limit])
text = preprocess.process(text)
nlp_text = nlp(text)
name = []
for e in nlp_text.ents:
name.append(e.text)
extracted_info.append({
'filename': file,
'name': ' '.join(name),
'number': numbers,
'email': emails
})
return extracted_info