waternsw-grabber/waternsw_grabber/waternsw_grabber.py

"""waternsw_grabber.py
Download bore records from the WaterNSW data portal.
"""

import os
import re
import time
import shutil
import logging
import warnings
import requests
import pandas as pd
from tqdm import tqdm
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait, Select
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import (
    TimeoutException, StaleElementReferenceException, NoSuchElementException)


def has_admin():
    """Check if current user has admin rights.
    https://stackoverflow.com/questions/2946746
    """
    if os.name == 'nt':
        try:
            # Check if C:/Windows/temp is readable for current user
            os.listdir(os.path.join(os.environ.get('systemroot'), 'temp'))
        except PermissionError:
            return False
        else:
            return True
    else:
        if 'SUDO_USER' in os.environ and os.geteuid() == 0:
            return True
        else:
            return False


def wait_for_element(driver, by, x, timeout=180):
    """Wait for element on page to load.

    Args:
        driver:   selenium webdriver object
        by:       locator strategy (e.g. By.ID)
        x:        locator string
        timeout:  maximum wait time (seconds)

    Raises
        TimeoutException if element does not load within timeout period
    """
    element_present = EC.presence_of_element_located((by, x))
    WebDriverWait(driver, timeout).until(element_present)


def get_telemetered_bore(driver, bore_id, start_date, end_date):
    """Download single record from telemetered bore.

    Args:
        driver:      selenium webdriver object
        bore_id:     bore ID (string)
        start_date:  start date (string in YYYY-MM-DD format)
        end_date:    end date (string in YYYY-MM-DD format)
    """

    url = 'https://realtimedata.waternsw.com.au/water.stm'
    driver.get(url)

    driver.switch_to.default_content()
    webhyd = driver.find_element_by_id('webhyd')
    driver.switch_to.frame(webhyd)

    # Load site specific page
    driver.execute_script("go('{}','gw', 1)".format(bore_id))

    # Wait for results frame to load
    wait_for_element(driver, By.ID, 'gwgwlf_org')
    driver.switch_to.frame('gwgwlf_org')

    # Wait until body text of iframe has loaded
    body_text = None
    while not body_text:
        try:
            # Get contents of body text
            body_text = driver.find_element_by_xpath('//*/body').text
        except (StaleElementReferenceException, NoSuchElementException):
            pass
        time.sleep(0.5)

    # Detect if bore record does not exist
    if 'No SITE record found for site' in body_text:
        raise ValueError('No SITE record found for site {}'.format(bore_id))
    elif 'No variables data found for this site.' in body_text:
        raise ValueError('No variables data found for site {}'.format(bore_id))

    # Wait for navigation tabs
    wait_for_element(driver, By.XPATH, '//*[@id="tabstext"]')

    # Activate outputs tab, and wait for 'Get Output' button
    driver.execute_script("menuloc.display_frame('gw', 'gwcf_org', '1')")
    driver.switch_to.parent_frame()
    wait_for_element(driver, By.ID, 'gwgwcf_org')
    driver.switch_to.frame('gwgwcf_org')
    wait_for_element(driver, By.ID, 'submit')

    # Get output select controls
    selects = driver.find_elements_by_xpath('//*/select')
    for select in selects:
        s = Select(select)
        label = s.options[0].get_attribute('label')
        if label == 'All data':
            period = s
        elif label == 'Plot':
            output = s
        elif label == 'Annual':
            interval = s

    # Change period dropdown to 'Custom'
    period.select_by_visible_text('Custom')

    # Get date input fields
    fields = driver.find_elements_by_xpath('//*[starts-with(@id,"cdate")]')

    # Parse dates
    start_date = pd.to_datetime(start_date)
    end_date = pd.to_datetime(end_date)

    # Update fields with specified dates
    for field, date in zip(fields, [start_date, end_date]):
        field.clear()
        field.send_keys(pd.datetime.strftime(date, '%H:%M_%d/%m/%Y'))

    # Set output dropdown to 'Download'
    output.select_by_visible_text('Download')

    # Set interval dropdown to 'All points'
    interval.select_by_visible_text('All points')

    # Make sure 'Groundwater Level - AHD' is selected as an output
    try:
        checkbox = driver.find_element_by_xpath(
            '//*/input[contains(@name, "sel__110.00_115.00")]')
        if not checkbox.get_attribute('selected'):
            checkbox.click()
    except NoSuchElementException:
        pass

    # Download data
    driver.execute_script("get_output()")
    driver.execute_script("hide_object('confirm');co(level,tab,1)")

    # Close popup
    wait_for_element(
        driver,
        By.XPATH,
        "//div[contains(@class, 'lity-container')]",
        timeout=60)
    webdriver.ActionChains(driver).send_keys(Keys.ESCAPE).perform()


def open_browser(download_dir):
    """Opens an automated Firefox browser instance.

    Args:
        download_dir:  path to where downloaded files will be saved

    Returns:
        A selenium web browser object
    """

    # Make download directory absolute
    download_dir = os.path.abspath(download_dir)

    # Set up Firefox to silently download files to specified folder
    profile = webdriver.FirefoxProfile()
    profile.set_preference('browser.download.folderList', 2)
    profile.set_preference('browser.download.manager.showWhenStarting', False)
    profile.set_preference('browser.download.dir', download_dir)
    profile.set_preference('browser.helperApps.neverAsk.saveToDisk',
                           ('application/zip,'
                            'application/octet-stream,'
                            'application/x-zip-compressed,'
                            'multipart/x-zip'))

    # Create download folder if it does not exist
    os.makedirs(download_dir, exist_ok=True)

    # Open browser
    driver = webdriver.Firefox(firefox_profile=profile)

    return driver


def telemetered_bore_downloader(bore_ids, start_date, end_date, download_dir):
    """Download multiple records from telemetered bore.

    Args:
        bore_ids:      bore ID values (array-like)
        start_date:    start date (string YYYY-MM-DD format)
        end_date:      end date (string YYYY-MM-DD format)
        download_dir:  path to where downloaded files will be saved

    Raises:
        ValueError when bore ID is invalid
    """
    driver = open_browser(download_dir)

    # Set up log File
    log_name = os.path.join(download_dir, 'errors.log')
    logging.basicConfig(filename=log_name, level=logging.ERROR)

    # Download bore logs
    pbar = tqdm(bore_ids)
    for bore_id in pbar:
        pbar.set_description(bore_id)
        try:
            get_telemetered_bore(driver, bore_id, start_date, end_date)
        except ValueError as e:
            logging.error(e)
        except TimeoutException:
            e = 'Request timed out on {}. Try again later?'.format(bore_id)
            logging.error(e)

    # Tidy up console after tqdm
    print('\n')

    # Stop logging
    logging.shutdown()
    with open(log_name, 'r') as f:
        log_data = f.read()

    # Check contents of log file
    if log_data:
        warnings.warn(
            'Some files failed to download. See log for details.',
            stacklevel=2)
    else:
        os.remove(log_name)

    driver.quit()


def extract_definitions(input_dir, output_dir):
    """Extract variable and quality metadata from bore records.

    Args:
        input_dir:   path to downloaded zip archives
        output_dir:  path to save csv files
    """

    # Get basin info for telemetered site data
    csv_name = os.path.join(
        os.path.dirname(os.path.dirname(__file__)), 'data',
        'telemetered-sites.csv')
    basins = pd.read_csv(csv_name, index_col=0)

    # Find zip files
    zip_names = [f for f in os.listdir(input_dir) if f.endswith('.zip')]

    # Prepare output directory
    os.makedirs(output_dir, exist_ok=True)

    for zip_name in tqdm(zip_names):
        # Skip duplicate downloads
        if re.search(r'\([0-9]+\)', zip_name):
            continue

        # Rename '.part' file if zip was not correctly downloaded
        if os.path.getsize(os.path.join(input_dir, zip_name)) == 0:
            shutil.move(
                os.path.join(input_dir, zip_name) + '.part',
                os.path.join(input_dir, zip_name))

        # Read csv file inside zip archive
        df = pd.read_csv(
            os.path.join(input_dir, zip_name),
            header=2,
            skiprows=[3],
            parse_dates=['Date'],
            compression='zip',
            dayfirst=True,
            nrows=100)

        # Extract metadata from last column
        keys = ['Sites:', 'Variables:', 'Qualities:']
        meta = {k: [] for k in keys}
        for i, row in df.iterrows():
            line = row.values[-1]
            if line in keys:
                header = True
                var = line
            elif line == ' ':
                continue
            else:
                meta[var].append(line)

        # Get bore specifics
        site_data = meta['Sites:'][0]
        lat = float(re.search(r'(?<=Lat:)\S+', site_data).group())
        lon = float(re.search(r'(?<=Long:)\S+', site_data).group())
        elev = float(re.search(r'(?<=Elev:).+(?=m)', site_data).group())
        address = re.search(r'(?<=\d\.\d\.\d - ).+(?=\sLat)',
                            site_data).group()
        bore_id = re.search(r'^\S+', site_data).group()
        site, hole, pipe = bore_id.split('.')

        sites = pd.DataFrame()
        sites['ID'] = [bore_id]
        sites['Site'] = [site]
        sites['Hole'] = [hole]
        sites['Pipe'] = [pipe]
        sites['Lat'] = [lat]
        sites['Lon'] = [lon]
        sites['Elev'] = [elev]
        sites['Address'] = [address]
        sites = sites.set_index('ID')

        # Get basin from master site dataframe
        sites['Basin name'] = basins.loc[sites.index, 'Basin name']
        sites['Basin code'] = basins.loc[sites.index, 'Basin code']

        # Save variable definitions
        variables = pd.DataFrame(
            [v.split(' - ', 1) for v in meta['Variables:']])
        variables.columns = ['Code', 'Description']
        variables['Code'] = variables['Code'].astype(int)
        variables = variables.set_index('Code')

        # Save quality definitions
        qualities = pd.DataFrame(
            [q.split(' - ', 1) for q in meta['Qualities:']])
        qualities.columns = ['Code', 'Description']
        qualities['Code'] = qualities['Code'].astype(int)
        qualities = qualities.set_index('Code')

        # Update existing values
        csv_name_s = os.path.join(output_dir, 'sites.csv')
        csv_name_v = os.path.join(output_dir, 'variables.csv')
        csv_name_q = os.path.join(output_dir, 'qualities.csv')

        try:
            sites = sites.append(pd.read_csv(csv_name_s, index_col=0))
            sites = sites.drop_duplicates().sort_index()
        except FileNotFoundError:
            pass

        try:
            variables = variables.append(pd.read_csv(csv_name_v, index_col=0))
            variables = variables.drop_duplicates().sort_index()
        except FileNotFoundError:
            pass

        try:
            variables = variables.append(pd.read_csv(csv_name_q, index_col=0))
            qualities = qualities.drop_duplicates().sort_index()
        except FileNotFoundError:
            pass

        # Export updated tables
        sites.to_csv(csv_name_s)
        variables.to_csv(csv_name_v)
        qualities.to_csv(csv_name_q)


def extract_records(input_dir, output_dir, clean_up=False):
    """Extract downloaded bore records.

    Args:
        input_dir:   path to downloaded zip archives
        output_dir:  path to save csv files
        clean_up:    delete original zip archive after extracting it
    """

    # Get basin info for telemetered site data
    csv_name = os.path.join(
        os.path.dirname(os.path.dirname(__file__)), 'data',
        'telemetered-sites.csv')
    basins = pd.read_csv(csv_name, index_col=0)

    # Find zip files
    zip_names = [f for f in os.listdir(input_dir) if f.endswith('.zip')]

    # Prepare output directory
    os.makedirs(output_dir, exist_ok=True)

    # Create master dataframe
    periods = ['all', 'daily', 'weekly']
    master = {}
    for period in periods:
        master[period] = pd.DataFrame()

    for zip_name in tqdm(zip_names):
        # Skip duplicate downloads
        if re.search(r'\([0-9]+\)', zip_name):
            continue

        # Rename '.part' file if zip was not correctly downloaded
        if os.path.getsize(os.path.join(input_dir, zip_name)) == 0:
            shutil.move(
                os.path.join(input_dir, zip_name) + '.part',
                os.path.join(input_dir, zip_name))

        # Read header
        header = pd.read_csv(
            os.path.join(input_dir, zip_name), compression='zip', nrows=3)

        # Remove comments
        header = header.iloc[:, 1:-1].T

        # Apply product codes to all columns
        header.iloc[1::2, 0] = header.iloc[::2, 0].values
        header[0] = header[0].astype(float).astype(int).astype(str)

        # Move quality label
        header.iloc[1::2, 1] = header.iloc[1::2, 2]

        # Combine labels
        columns = [' '.join(c) for c in header.iloc[:, :-1].values]

        # Read csv file inside zip archive
        df = pd.read_csv(
            os.path.join(input_dir, zip_name),
            header=2,
            skiprows=[3],
            parse_dates=['Date'],
            compression='zip',
            dayfirst=True)

        # Update column names
        df.columns = ['Date time'] + columns + ['Metadata']

        # Get bore specifics
        meta = df['Metadata'].iloc[1]
        bore_id = re.search(r'^\S+', meta).group()
        site, hole, pipe = bore_id.split('.')
        df.drop(columns='Metadata')

        # Set date index for resampling
        df.index = df['Date time']

        # Append to master dataframe
        for period in periods:
            if period == 'daily':
                # Resample to daily timestamps
                df = df.resample('1d').mean()
                df['Date time'] = df.index

            elif period == 'weekly':
                # Resample to weekly timestamps
                df = df.resample('1w').mean()
                df['Date time'] = df.index

            master[period] = pd.concat([master[period], df])

        if clean_up:
            # Remove original zip archive
            os.remove(os.path.join(input_dir, zip_name))

    for period in periods:
        # Get latest date from dataframe
        latest_date = master[period]['Date time'].iloc[-1].strftime('%Y-%m-%d')
        csv_name = os.path.join(
            output_dir, '{}-{}-{}.csv'.format(basin_id, latest_date, period))

        # Export to csv
        master[period].to_csv(csv_name, index=False, float_format='%0.3f')