chm15ksession.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Sep 15 09:22:30 2021

@author: spirrobe
"""

import os
import datetime
import requests
import json


class chm15ksession(requests.Session):
    """
    A class for interacting with the CHM-15k data server.

    This class inherits from the requests.Session class and is designed to
    facilitate downloading netCDF and zipped netCDF files from the CHM-15k.
    To use this class, you must have a valid password for accessing the
    server.

    Parameters
    ----------
    url : str
        The URL of the CHM-15k ceilometer. Can be local ip or http URl
    password : str, optional
        The password for accessing the CHM-15k.
        Default is "15k-Nimbus".
    outpath : str, optional
        The path to save downloaded files to. Default is the current directory.
    download2subdirs : bool, optional
        Whether to put files into a subdirectory as outpath/{year}/{month}/{day} 
        where year, month, day are inferred for each file based on the filename
    quiet : bool, optional
        Whether to print information about the download progress.
        Default is True.

    Attributes
    ----------
    url : str
        The URL of the CHM-15k.
    session : requests.Session
        The requests session object used to communicate with the server.
    password : str
        The password for accessing the CHM-15k data server.
    outpath : str
        The path to save downloaded files to.
    filecount : bool
        The number of files available on the server.
    quiet : bool
        Whether to print information about the download progress.
    sessionid : str
        The ID of the current session with the server.
    zipfiles : list of str
        The names of the zipped netCDF files available on the server.
    zipsizes : list of int
        The sizes of the zipped netCDF files available on the server, in bytes.
    ncfiles : list of str
        The names of the netCDF files available on the server.
    ncsizes : list of int
        The sizes of the netCDF files available on the server, in bytes.

    Methods
    -------
    connect()
        Connects to the CHM-15k data server and establishes a session.
    getfilelist()
        Returns a dictionary of available netCDF and zipped netCDF files on the
        CHM-15k data server.
    getncfiles(overwrite=False)
        Downloads all available netCDF files from the CHM-15k to the
        local file system.
    getzipfiles(overwrite=False)
        Downloads all available zipped netCDF files from the CHM-15k
        to the local file system.
    """

    def __init__(self,
                 url,
                 password="15k-Nimbus",
                 outpath='./',
                 download2subdirs=False,
                 timeout=20,
                 quiet=True,
                 *args, **kwargs,
                 ):
        """
        Initialize a new instance of the chm15ksession class.

        Parameters
        ----------
        url : str
            The URL of the CHM-15k.
        password : str, optional
            The password for accessing the CHM-15k data server. Default is
            "15k-Nimbus".
        outpath : str, optional
            The path to save downloaded files to.
            Default is the current directory.
        timeout : bool, optional
            The timeout in seconds for the get calls, adjust if on low bandwidth/slow network.
        quiet : bool, optional
            Whether to print information about the download progress.
            Default is True.
        """
        super().__init__(*args, **kwargs)
        # assert url, str, 'url must be a str'
        self.timeout = timeout
        self.url = url

        if not self.url.endswith('/'):
            self.url += '/'

        if not self.url.startswith('http'):
            self.url = 'http://' + self.url

        self.__cgi = "cgi-bin/chm-cgi"
        self.__cgiurl = self.url + self.__cgi
        #self.session = requests.Session()
        #self = requests.Session()
        self.password = password
        self.outpath = outpath
        self.__subpath = ''
        self.download2subdirs = download2subdirs
        if not self.outpath.endswith(os.sep):
            self.outpath += os.sep

        self.filecount = None
        self.sessionid = None
        self.zipfiles = []
        self.zipsizes = []
        self.ncfiles = []
        self.ncsizes = []
        self.quiet = quiet

    def _filename2date(self, filename):
        # pattern is YYYYMMDD
        _ = filename.split(os.sep)[-1].split('_')[0]
        if len(_) == 8:
            # typical netcdf files
            return _[:4], _[4:4+2], _[4+2:4+2+2]
        elif len(_) == 6:
            # zipfiles do not have a day as they are for the month
            return _[:4], _[4:4+2]
        else:
            print(f'Date could not be inferred from {filename}')
            return '', '', ''

    def _filename2datefolder(self, filename):
       date = self._filename2date(filename)
       if date[0]:
           date = [s + i for s, i in zip(['Y','M','D'], date)]
           date = os.sep.join(date) + os.sep

           if not self.outpath.endswith(os.sep):
               date = os.sep + date
           return date
       else:
           return ''

    def connect(self):
        """
        Connect to the CHM-15k using the provided password.

        This method sends a validation request to the CHM-15k data server
        with the provided passwordand obtains a session ID that can be
        used for subsequent requests.

        Raises
        ------
        requests.exceptions.RequestException
            If the request fails.

        """
        validationurl = self.__cgiurl+f"?validatetoken&code={self.password}"
        # this url could be used to check if the connection worked
        # checkurl = self.__cgiurl+"?checkvalidation"
        try:
            resp = self.get(validationurl, timeout=self.timeout)
        except requests.exceptions.RequestException:
            now = datetime.datetime.now(datetime.UTC)
            print(f'{now}: Connection failed, check url {self.url} and '
                  f'password {self.password}')
            return
        sessionid = resp.text.strip().split('{')[1].split('}')[0]
        resp.close()
        sessionid = sessionid.split(':')[1].split(',')[0]
        self.sessionid = sessionid
        self.cookies.set("session", self.sessionid,
                                 domain=self.url.split(':')[1][2:])
        if not self.quiet:
            now = datetime.datetime.now(datetime.UTC)
            print(f'{now}: Connection successful to {self.url}')
        self.sessionid = True

    def getfilelist(self):
        """
        Get a list of files from the CHM-15k.

        If the connection to the server has not been established,
        this method will establish a connection. Sets attributes of the
        object to contain the return values as well.

        Returns
        -------
        dict
            A dictionary containing the following keys:
            - 'zipfiles': A list of the names of zipped netCDF files.
            - 'netcdffiles': A list of the names of netCDF files.
            - 'zipsizes': A list of the sizes of zipped netCDF files.
            - 'ncsizes': A list of the sizes of netCDF files.
        """
        if self.sessionid:
            pass
        else:
            self.connect()
        resp = self.get(self.__cgiurl + '?filelist', timeout=self.timeout)
        filelist = resp.text
        resp.close()
        filelist = ''.join(filelist.split('\r\n')[1::2])

        try:
            filelist = json.loads(filelist)
        except json.JSONDecodeError:
            if not self.quiet:
                now = datetime.datetime.now(datetime.UTC)
                print(f'{now}: Issue with getting proper filelist, aborting getfilelist and potential callers')
            return None
        self.filecount = filelist['count']
        self.zipfiles = [i[0] for i in filelist["ncfiles"] if 'zip' in i[0]]
        self.zipsizes = [i[1] for i in filelist["ncfiles"] if 'zip' in i[0]]

        self.ncfiles = [i[0] for i in filelist["ncfiles"] if 'zip' not in i[0]]
        self.ncsizes = [i[1] for i in filelist["ncfiles"] if 'zip' not in i[0]]

        if not self.quiet:
            now = datetime.datetime.now(datetime.UTC)
            print(f'{now}: Found {filelist["count"]} files in total to be checked')
            print(f'{now}: Found {len(self.ncfiles)} netCDF files')
            print(f'{now}: Found {len(self.zipfiles)} zipped netCDF files')

        return {'zipfiles': self.zipfiles, 'netcdffiles': self.ncfiles,
                'zipsizes': self.zipsizes, 'ncsizes': self.ncsizes}

    def getsinglefile(self, filename, overwrite=True):
        """
        Download a single file from the CHM15k to the specified output path.

        Parameters
        ----------
        filename : str
            Name of the file to be downloaded. Can be either zip or nc file.
        overwrite : bool, optional
            Flag indicating whether to overwrite the file if it already
            exists in the output path and has the same size.
            Defaults to True.

        Returns
        -------
        None
            If the file is not available on the server or
            if the file transfer fails.

        Raises
        ------
        None

        Notes
        -----
        This method uses the requests library to download the file
        from the server, and saves it to the output path using
        the same filename as on the device.

        """
        if self.filecount:
            pass
        else:
            self.getfilelist()

        if filename not in self.ncfiles or filename in self.zipfiles:
            print(f'File {filename} not available')
            return
        else:
            if filename in self.ncfiles:
                filesize = self.ncsizes[self.ncfiles.index(filename)]
            elif filename in self.zipfiles:
                filesize = self.zipsizes[self.zipfiles.index(filename)]
            else:
                print(f'File {filename} not available')
                return

        if self.download2subdirs:
            self.__subpath = self._filename2datefolder(filename)

        os.makedirs(self.outpath + self.__subpath, exist_ok=True)

        # check if the file exists, and if it does has the same size
        # if so continue
        if os.path.exists(self.outpath + self.__subpath + filename):
            fs = os.path.getsize(self.outpath + self.__subpath + filename) // 1024
            if fs == filesize and not overwrite:
                if not self.quiet:
                    print(f'File {filename} already exists and has the same '
                          'size as the file on the CHM15k. Pass overwrite to',
                          'download anyway')

                return

        filecontent = self.get(self.__cgiurl+'/'+filename+"?getfile", timeout=self.timeout)
        # check if the transfer worked in the firstplace, if not continue
        if filecontent.status_code != 200:
            if not self.quiet:
                now = datetime.datetime.now(datetime.UTC)
                print(f'{now}: Filetransfer failed for {filename}')
            return

        with open(self.outpath + self.__subpath + filename, 'wb') as fo:
            fo.write(filecontent.content)

        if not self.quiet:
            now = datetime.datetime.now(datetime.UTC)
            print(f'{now}: Successfully downloaded {filename}')

        self.__subpath = ''

    def getncfiles(self, overwrite=False):
        """
        Download netCDF files from the CHM-15k to the specified `outpath`.

        Parameters
        ----------
        overwrite : bool, optional
            Whether to overwrite existing files with the same name and size
            in the `outpath`.
            Default is False.

        Raises
        ------
        ValueError
            If `filecount` attribute is False.

        Notes
        -----
        This method first checks whether the `filecount` attribute is set.
        If not, it calls the `getfilelist` method to obtain a list of files
        available for download. Then, for each netCDF file in the list,
        it checks whether the file already exists in the `outpath` and has
        the same size as the file.
        If not, it downloads the file using a GET request and saves it
        to the `outpath`.

        """
        if self.filecount:
            pass
        else:
            self.getfilelist()

        dlcount = 0
        for fileno, (filename, filesize) \
                in enumerate(zip(self.ncfiles, self.ncsizes)):
            if self.download2subdirs:
                self.__subpath = self._filename2datefolder(filename)
            # check if the file exists, and if it does has the same size
            # if so continue
            if os.path.exists(self.outpath + self.__subpath + filename):
                fs = os.path.getsize(self.outpath + self.__subpath + filename) // 1024
                if fs == filesize and not overwrite:
                    if not self.quiet:
                        now = datetime.datetime.now(datetime.UTC)
                        print(f'Not downloading {filename} as it exists and has the same size')
                        print(f'{now}: Progress at ',
                             f'{round((fileno+1)/len(self.ncfiles) * 100,1)} %')

                    continue
            else:
                os.makedirs(self.outpath + self.__subpath, exist_ok=True)

            filecontent = self.get(
                self.__cgiurl+'/'+filename+"?getfile", timeout=self.timeout)
            # check if the transfer worked in the firstplace, if not continue

            if filecontent.status_code != 200:
                if not self.quiet:
                    print(f'Filetransfer failed for {filename}')
                continue

            with open(self.outpath + self.__subpath + filename, 'wb') as fo:
                fo.write(filecontent.content)

            if not self.quiet:
                now = datetime.datetime.now(datetime.UTC)
                print(f'{now}: Successfully downloaded {filename}, the {dlcount+1} file')
                print(f'{now}: Progress at '
                      f'{round((fileno+1)/len(self.ncfiles) * 100,1)} %')
            dlcount += 1
        now = datetime.datetime.now(datetime.UTC)
        print(f'{now}: Downloaded all {dlcount} files that contained new data '
              f'to {self.outpath + self.__subpath}')
        self.__subpath = ''

    def getzipfiles(self, overwrite=False):
        """
        Download zip files from the CHM-15k to the specified `outpath`.

        Parameters
        ----------
        overwrite : bool, optional
            Whether to overwrite existing files with the same name and size
            in the `outpath`.
            Default is False.

        Raises
        ------
        ValueError
            If `filecount` attribute is False.

        Notes
        -----
        This method first checks whether the `filecount` attribute is set.
        If not, it calls the `getfilelist` method to obtain a list of files
        available for download. Then, for each zip file in the list,
        it checks whether the file already exists in the `outpath` and has
        the same size as the file.
        If not, it downloads the file using a GET request and saves it
        to the `outpath`.

        """
        if self.filecount:
            pass
        else:
            self.getfilelist()

        os.makedirs(self.outpath, exist_ok=True)

        for fileno, (filename, filesize) \
                in enumerate(zip(self.zipfiles, self.zipsizes)):
            if self.download2subdirs:
                self.__subpath =  self._filename2datefolder(filename)
            # check if the file exists, and if it does has the same size
            # if so continue
            if os.path.exists(self.outpath + self.__subpath + filename):
                fs = os.path.getsize(self.outpath + self.__subpath + filename) // 1024
                if fs == filesize and not overwrite:
                    if not self.quiet:
                        print('File already exists and has '
                              f'the same size ({filename})')
                    continue
            else:
                os.makedirs(self.outpath + self.__subpath, exist_ok=True)

            filecontent = self.get(
                self.__cgiurl+'/'+filename+"?getfile", timeout=self.timeout)
            # check if the transfer worked in the firstplace, if not continue
            if filecontent.status_code != 200:
                if not self.quiet:
                    print(f'Filetransfer failed for {filename}')
                continue

            with open(self.outpath + self.__subpath + filename, 'wb') as fo:
                fo.write(filecontent.content)

            if not self.quiet:
                now = datetime.datetime.now(datetime.UTC)
                print(f'{now}: Successfully downloaded {filename}')
                print(f'{now}: Progress at '
                      f'{round((fileno+1)/len(self.zipfiles) * 100,1)} %')
        now = datetime.datetime.now(datetime.UTC)
        print(f'{now}: Downloaded all {len(self.zipfiles)} available '
              f'zip files at {self.outpath + self.__subpath}')
        self.__subpath = ''


if __name__ == '__main__':
    url = ''  # the url to connect to, either http/s or ip directly of the chm15k
    a = chm15ksession(url
                      outpath='./',
                      quiet=False)
                      
    # establish a connection, setting up a session, this wil be done automatically
    # upon calling other get functions
    a.connect()
    
    # get the available files in case you want to download only one file
    a.getfilelist()
    
    # usually, one is interested only in the netcdf files that are available,
    # especially in an operational setting where other files have already
    # been downloaded. 
    # per default, existing files are not downloaded again
    # a.getncfiles()
    
    # zipfiles are created by the device for each month and can be downloaded as well
    # per default, existing files are not downloaded again
    # a.getzipfiles()