import re
import csv

with open("bigHtmlFile.html", "r") as infile:
    html_dump = infile.read()

# Define the regular expressions with negative lookbehind
regex_title = r"(?<!{)\"title\":\"(.*?)\","
regex_counterpart = r"(?<!{)\"description\":\"(.*?)\","
regex_fraction = r"(?<!{)\"fraction\":\"(-?\d+(?:\.\d+)?)\","
regex_date = r"(?<!{)\"moneyReleaseDate\":\"(.*?)\""

# Compile the regular expressions
pattern_title = re.compile(regex_title)
pattern_counterpart = re.compile(regex_counterpart)
pattern_fraction = re.compile(regex_fraction)
pattern_date = re.compile(regex_date)

# Find all matches for each field
titles = pattern_title.findall(html_dump)
counterparts = pattern_counterpart.findall(html_dump)
fractions = pattern_fraction.findall(html_dump)
dates = pattern_date.findall(html_dump)

# Process the counterparts to remove "a " or "de " (esto es cosmético)
counterparts = [re.sub(r"^(a |de )", "", counterpart) for counterpart in counterparts]

# Combine the titles and processed counterparts
combined_columns = [title + " " + counterpart for title, counterpart in zip(titles, counterparts)]

# Prepare the data for CSV writing (esto no sé si lo usa...)
data = zip(combined_columns, counterparts, fractions, dates)

# Process the data and write to the CSV file
with open('output.csv', 'w', newline='') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['Title', 'Counterpart', 'Credit column', 'Debit column', 'Date'])

    for title, counterpart, fraction, date in zip(titles, counterparts, fractions, dates):
        # Convert fraction to float and remove thousands separator
        fraction = float(fraction.replace('.', '').replace(',', '.'))

        # Determine if it's a credit or debit
        credit = fraction if fraction >= 0 else 0
        debit = -fraction if fraction < 0 else 0

        # Format the date
        formatted_date = date[:10].replace('-', '/')

        # Write the row to the CSV file
        writer.writerow([title + ' ' + counterpart, counterpart, credit, debit, formatted_date])