pdf_parser/expert_resume/parse_resume_utils.py

import re


def extract_email(content):
    """
    Extracts email id of the expert
    """
    try:
        pattern = r"([a-z0-9]+@[a-z]+\.[a-z]{2,3})"
        return re.search(pattern, content).group()
    except:
        return "None"


def extract_zipcode(content):
    """
    Extracts zipcode from the resume
    """
    try:
        pattern = r"(\w{2}\s\d{5})"
        return re.search(pattern, content).groups()[0]
    except:
        return "None"


def extract_phone(content):
    """
    Extracts phone number of the expert.
    """
    try:
        pattern = r"(\(?\d{3}\)?\-?\s?\d{3}\-\d{4})"
        return re.search(pattern, content).group()
    except:
        return "None"


def extract_case_numbers(content):
    """
    Extracts all the case numbers associated with resume
    """
    results = []
    case_numbers = re.compile(r"\d{2}\-\w+\-\d+\-\w+\-?\w+", re.IGNORECASE)
    for current in case_numbers.finditer(content):
        results.append(current.group().replace(",", ""))
    return list(set(results))


def extract_litigation_experience(content):
    """
    Extracts the litigation experience of the expert
    """
    try:
        pattern = r"(\d+|\w+)\s?years"
        return re.search(pattern, content).group()
    except:
        return "None"


def extract_patents_issued(content):
    """
    Returns the patents issued by the expert
    """
    regex = r"\d{1,3}\,\d{1,3}\,\d{3}\,?"
    results = []
    patent = re.compile(regex, re.IGNORECASE)
    for current in patent.finditer(content):
        results.append(current.group().replace(",", ""))
    return list(set(results))


def extract_name(content):
    """
    Returns the name of the expert
    """
    # pattern = r"(\w+\s\w+.*?)Resume" Old pattern
    pattern = r"(RESUME|\SResume)\s(\w+\s\w+\.?\s\w+)|\-(\s.*?)Resume"
    try:
        return re.search(pattern, content).group()
    except:
        return "None"