pdf_parser/complaints/parse_pdf_utils.py

import re


def extract_patent_number(content):
    """
    Returns the list of unique patent_numbers in the document
    """
    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_case_number(content):
    """
    Returns the lisr of unique case_numbers
    """
    regex = r"(\d{1,})\:(\d{1,}\-\w{1,}\-\d{5,}\-\w+)+"
    try:
        return re.search(regex, content).groups()[1]
    except:
        return "None"


def extract_hourly_compensation(content):
    """
    Returns hourly compensation.
    """
    results = []
    hourly_comp_re = re.compile("\$\d{1,20}", re.IGNORECASE)
    for current in hourly_comp_re.finditer(content):
        results.append(current.group().replace(",", ""))
    return list(set(results))


def extract_expert_name(content):
    """
    Returns the name of the expert
    """
    results = []
    exp_name = re.compile(r"\b(REPORT OF ).*\S[.]")
    for current in exp_name.finditer(content):
        results.append(current.group().replace(",", ""))
    return list(set(results))


def extract_plaintiff(content):
    """
    Returns the name of the plaintiff
    previous = (OF\s\w{1,})(.*)Plaintiff[s]?,
    """
    regex = r"OF\s\w+(\s.*?\,).*?Plaintiff"
    try:
        return re.search(regex, content).groups()[0]
    except:
        return "None"


def extract_defendent(content):
    """
    Returns the name of the defendant
    Plaintiff[s]?.*v[s]?\.(.*?)Defendant[s]?\.
    """
    regex = r"Plaintiff[s]?\,.*?[v|V]\.(.*?)Defendant[s]?\.?"
    try:
        return re.search(regex, content).groups()[0]
    except:
        return "None"


def extract_acronyms(content):
    """
    Returns the list of all the acronyms present
    """
    regex = r"\(“(\w{3})”\)"
    results = []
    plaintiff = re.compile(regex, re.IGNORECASE)
    for current in plaintiff.finditer(content):
        results.append(current.group().replace(",", ""))
    return list(set(results))


def extract_firm_name(content):
    """
    Returns the list of firm names present in the documents.
    """
    regex = r"(\(Firm\sName\,\sAddress\,\sand\sTelephone\sNumber\))([\r\n]+([^\r\n]+))"
    results = []
    firm = re.compile(regex, re.IGNORECASE)
    for current in firm.finditer(content):
        results.append(current.group().replace(",", ""))
    return list(set(results))


def extract_filing_date(content):
    """
    Returns the filing date.
    """
    try:
        return re.search(r"(Filed)\s(\d{2}\/\d{2}\/\d{2})", content).groups()[1]
    except:
        return "None"