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}|(Filed\:.+?)\w.+\d{1,2}\,\s\d{4}([\s\S].*?Paper))"
    pattern = r"\w+\.?\s\d{1,2}\,\s\d{4}|\d{2}\/\d{2}\/\d{4}"
    try:
        return re.search(pattern, content).group(0)
    except:
        return "None"


def address_extraction(content):
    """
    extracts address from the documents.
    """
    regex = r"(OfficeAddress\:\s([\s\S].*)www|(A|a)ddress.+?\sof.+?Fax\:\s\(\d{3}\)\s\d{3}\-\d+\s)"
    try:
        re.search(regex, content).groups()[0]
    except:
        return "None"


def refer_exteraction(content):
    """
    extract referals from the documents.
    """
    regex = r"((by\sreference\sU\.S\.\sPatent\sNo.\s\d{1,2}\,\d{3}\,\d{3})|(In\sre\s\w+.+?\,?\s\d{2,3}\sF\.\dd\s\d{0,4}\,?\s?\d{0,4}\s?\(?.+?\)))"  # |In\sre.+?\)|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):
    """
    Extracts emails from a document.
    """
    regex = r"(\w+\-)?\w+@[a-z]+\.[a-z]{2,3}"
    result = []
    emails = re.compile(regex, re.IGNORECASE)
    for email in emails.finditer(content):
        result.append(email.group())
    return result


def telephone_number_extraction(content):
    """
    Extracts telephone number[s?] from a document
    """
    # regex = r"Telephone\:.+?\(\d{3}\)\s\d{3}\-\d{4}"
    regex = r"\(?\d{3}\)?[\-|\s]\d{3}[\s|\-]\d{4}"
    numbers = re.compile(regex, re.IGNORECASE)
    result = []
    for number in numbers.finditer(content):
        result.append(number)
    return result