def extract_education_section(file_path, actual_file_name):
"""
Opens the converted pdf to text file & tries to extract the work information with different unicodes.
"""
reload(sys)
sys.setdefaultencoding('latin-1')
with open(file_path, 'r') as fp:
try:
pdf_text = str(fp.read())
return extract_text_from_pdf(pdf_text, actual_file_name)
except Exception:
print traceback.print_exc()
utility.write_to_text_file(CODEC_FAILURE, file_path + "','")
def extract_bold_header_section(file_path, actual_file_name):
"""
Opens the html file path & tries to extract the bold sections with different unicodes.
"""
reload(sys)
sys.setdefaultencoding('latin-1')
with open(file_path, 'r') as fp:
try:
html_text = str(fp.read())
return utility.fetch_bold_header_contents(html_text,
actual_file_name)
except Exception:
print traceback.print_exc()
utility.write_to_text_file(CODEC_FAILURE, file_path + "','")
def categorize_work_info(data, logic_code):
"""
Master function for parsing the different work category.
"""
parsed_data_result = list()
try:
work_content = str(data["work"])
file_name = str(data["file_name"])
word_list = work_content.split("|")
forward_processed = work_parsing(word_list, file_name, logic_code)
if not forward_processed:
raise Exception("No data parsed from work ********************")
parsed_data_result.extend(forward_processed)
except Exception:
print traceback.print_exc()
utility.write_to_text_file(FAILED_WORK_JSON_PARSE,
data["file_name"] + "','")
parsed_data = utility.convert_to_df(parsed_data_result)
put_parse_data_to_db(parsed_data)