pdf_parser/pdfs/utils.py

import re


def extract_filing_date(content):
    """
    extracts filing date from the documents.
    """
    pattern = r"((FILING\sDATE.*?)\d{1,2}\/\d{1,2}\/\d{2,4}|(Date\:\s)\w{1,9}\s\d{1,2}\,\s\d{4}|(Entered\:\s.*?)\w.*?\d{1,2}\,\s\d{4}|(Filed.*?)\d{1,2}\/\d{1,2}\/\d{1,2})"  # "((FILING\sDATE.*?)\d{1,2}\/\d{1,2}\/\d{2,4}|(Date\:\s)\w{1,9}\s\d{1,2}\,\s\d{4})"
    try:
        return re.search(pattern, content).groups()[0]
    except:
        return "None"


def address_extraction(content):
    """
    extracts address from the documents.
    """
    regex = r"OfficeAddress\:\s([\s\S].*)www"
    try:
        print(re.search(regex, content).groups()[0])
    except:
        return "None"


def refer_exteraction(content):
    """
    extract referals from the documents.
    """
    regex = r"by\sreference.+?\d{1,2}\,\d{3}\,\d{3}|In\sre.+?\)"
    # 1. by reference
    # 2. In re
    # 3. in qoutes ""
    try:
        data1 = re.findall(regex, content)
        print(list(set(data1)))
    except:
        return "None"


def email_extraction(content):
    regex = r"(\w+\-)?\w+@[a-z]+\.[a-z]{2,3}"
    expert_name = re.compile(regex, re.IGNORECASE)
    for current in expert_name.finditer(content):
        print(current.group())


def telephone_number_extraction(content):
    regex = r"Telephone\:.+?\(\d{3}\)\s\d{3}\-\d{4}"
    expert_name = re.compile(regex, re.IGNORECASE)
    for current in expert_name.finditer(content):
        print(current.group())