Scrape PDFs programmatically site with Python3 and Tika library

pappers_pdf_parser_with_python_and_tika.py

from tika import parser
import re
import csv

HEADERS = ['numero_gestion', 'a_jour_au', 'numero_rcs', 'date_immatriculation', 'raison_sociale', 'forme_juridique', 'capital_social', 'adresse_siege', 'activites_principals']

def parse_pdf(filename): 

    # request
    raw = parser.from_file(filename)
    # print(raw)
    assert isinstance(raw, dict)
    status = raw['status']
    assert status == 200

    # json parsing
    metadata = raw['metadata']
    content_type = metadata['Content-Type']
    creation_date = metadata['Creation-Date']
    last_modified = metadata['Last-Modified']
    name = metadata['resourceName']

    content = str(raw)
    numero_gestion = "".join(re.findall(r'(?<=N° de gestion )\w+', content))
    a_jour_au = "".join(re.findall(r'(?<=à jour au )[\w\s]+', content))
    numero_rcs = "".join(re.findall(r'(?<=Immatriculation au RCS, numéro )[\w\s\.]+', content))
    date_immatriculation = "".join(re.findall(r'(?<=Date d\'immatriculation )[\d\/]+', content))
    raison_sociale = "".join(re.findall(r'(?<=Dénomination ou raison sociale )\w+', content))
    forme_juridique = "".join(re.findall(r'(?<=Forme juridique )[^\\]+', content))
    capital_social = "".join(re.findall(r'(?<=Capital social )[^\\]+', content))
    adresse_siege = "".join(re.findall(r'(?<=Adresse du siège )[^\\]+', content))
    activites_principals = "".join(re.findall(r'(?<=Activités principales )[^\\]+', content))


    values = [numero_gestion, a_jour_au, numero_rcs, date_immatriculation, raison_sociale, forme_juridique, capital_social, adresse_siege, activites_principals]

    assert all(values)
    row_dict = dict(zip(HEADERS, values))
    return row_dict

def write_csv(rows): 
    assert rows
    with open('parsed_pdf.csv', 'w') as f: 

        writer = csv.DictWriter(f, fieldnames=HEADERS)
        writer.writeheader()
        for row in rows: 
            writer.writerow(row)



if __name__ == "__main__": 
    assert HEADERS
    filenames = [
        "/Users/sashabouloudnine/Desktop/LOBSTR - Extrait d'immatriculation.pdf",
        "/Users/sashabouloudnine/Desktop/VOSTOKINC - Extrait d'immatriculation.pdf", 
        "/Users/sashabouloudnine/Desktop/CAPTAIN DATA - Extrait d'immatriculation.pdf", 
        "/Users/sashabouloudnine/Desktop/PHANTOMBUSTER - Extrait d'immatriculation.pdf", 
    ]
    rows = []
    for filename in filenames: 
        row_dict = parse_pdf(filename)
        rows.append(row_dict)
    write_csv(rows)