laurel.py

laurel.py

"""
Convert https://laurelhillphl.comtch/app/uploads/2024/07/Laurel-Hill-Trees-as-of-7.2.2024.pdf to CSV.
"""
import re
import tabula
import pandas as pd
import logging

FORMAT = "%(message)s"
logging.basicConfig(level=logging.INFO, format=FORMAT, datefmt="[%X]")
logger = logging.getLogger("laurel")

dfs = tabula.read_pdf("laurel-hill-trees.pdf", pages="all")

real_dfs = []

columns = ['Tag Number', 'Section', 'Species']

for idx, df in enumerate(dfs):
    try:
        diff = set(df.columns).difference(columns)

        if len(diff) == 0:
            real_dfs.append(df)
            continue

        df2 = df.copy()
        df2.loc['-1'] = df.columns
        df2.columns = columns

        df2['Tag Number'] = df2['Tag Number'].astype(int)
        df2 = df2.sort_values(by='Tag Number').reset_index(drop=True)

        real_dfs.append(df2)
    except ValueError as err:
        logger.error(f'Err {err} on idx {idx}')
        import pdb; pdb.set_trace()

combined_df = pd.concat(real_dfs, ignore_index=True)

def extract_names(row):
    pattern = r'^(.*?)\s*\((.*?)\)$'
    match = re.findall(pattern, row['Species'])

    if match:
        match = match[0]
        scientific_name = match[0]
        common_name = match[1]
        return {
            'scientific_name': scientific_name,
            'common_name ': common_name ,
        }

    logger.error(f'No match found for {row["Species"]}')
    return {
        'scientific_name': None,
        'common_name ': None,
    }


final_df = combined_df.apply(extract_names, axis='columns', result_type='expand')
out_df = pd.concat([combined_df, final_df], axis='columns')

out_df.to_csv("laurel-hill-trees.csv", index=False)