diff --git a/intakebuilder/CSVwriter.py b/intakebuilder/CSVwriter.py
deleted file mode 100644
index 9a6a33f..0000000
--- a/intakebuilder/CSVwriter.py
+++ /dev/null
@@ -1,98 +0,0 @@
-import os.path
-import csv
-from csv import writer
-from intakebuilder import builderconfig, configparser 
-
-def getHeader(configyaml):
-    '''
-    returns header that is the first line in the csv file, refers builderconfig.py
-    :return: headerlist with all columns
-    '''
-    if configyaml:
-        return configyaml.headerlist
-    else:
-        return builderconfig.headerlist
-
-def writeHeader(csvfile):
-  '''
-  writing header for the csv
-  :param csvfile: pass csvfile absolute path
-  :return: csv writer object
-  '''
-  # list containing header values
-  # inputting these headers into a csv
-  with open(csvfile, "w+", newline="") as f:
-        writerobject = csv.writer(f)
-        writerobject.writerow(builderconfig.headerlist)
-
-def file_appender(dictinputs, csvfile):
-    '''
-    creating function that puts values in dictionary into the csv
-    :param dictinputs:
-    :param csvfile:
-    :return:
-    '''
-    # opening file in append mode
-    with open(csvfile, 'a', newline='') as write_obj:
-        # Create a writer object from csv module
-        csv_writer = writer(write_obj)
-        # add contents of list as last row in the csv file
-        csv_writer.writerow(dictinputs)
-
-def listdict_to_csv(dict_info,headerlist, csvfile, overwrite, append):
-    try:
-        #Open the CSV file in write mode and add any data with atleast 3 values associated with it
-        if overwrite:
-            with open(csvfile, 'w') as csvfile:
-                writer = csv.DictWriter(csvfile, fieldnames=headerlist)
-                print("writing..")
-                writer.writeheader()
-                for data in dict_info:
-                    if len(data.keys()) > 2:
-                        writer.writerow(data)
-        #Open the CSV file in append mode and add any data with atleast 3 values associated with it
-        if append:
-            with open(csvfile, 'a') as csvfile:
-                writer = csv.DictWriter(csvfile, fieldnames=headerlist)
-                print("writing (without header)..")
-                for data in dict_info:
-                    if len(data.keys()) > 2:
-                        writer.writerow(data)
-        #If neither overwrite nor append flags are found, check if a csv file already exists. If so, prompt user on what to do. If not, write to the file. 
-        if not any((overwrite, append)):
-            if os.path.isfile(csvfile):
-                user_input = ''
-                while True:
-                    user_input = input('Found existing file! Overwrite? (y/n)')
-
-                    if user_input.lower() == 'y':
-                        with open(csvfile, 'w') as csvfile:
-                            writer = csv.DictWriter(csvfile, fieldnames=headerlist)
-                            print("writing..")
-                            writer.writeheader()
-                            for data in dict_info:
-                                if len(data.keys()) > 2:
-                                    writer.writerow(data)
-                        break
-                    
-                    elif user_input.lower() == 'n':
-                        with open(csvfile, 'a') as csvfile:
-                            writer = csv.DictWriter(csvfile, fieldnames=headerlist)
-                            print("appending (without header) to existing file...")
-                            for data in dict_info:
-                                if len(data.keys()) > 2:
-                                    writer.writerow(data)
-                        break
-                    #If the user types anything besides y/n, keep asking
-                    else:
-                        print('Type y/n')
-            else:
-                with open(csvfile, 'w') as csvfile:
-                    writer = csv.DictWriter(csvfile, fieldnames=headerlist)
-                    print("writing..")
-                    writer.writeheader()
-                    for data in dict_info:
-                        if len(data.keys()) > 2:
-                            writer.writerow(data)
-    except IOError:
-        print("I/O error")
diff --git a/intakebuilder/builderconfig.py b/intakebuilder/builderconfig.py
deleted file mode 100644
index 2eb95ef..0000000
--- a/intakebuilder/builderconfig.py
+++ /dev/null
@@ -1,50 +0,0 @@
-#what kind of directory structure to expect? 
-#For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
-# the output_path_template is set as follows.
-#We have NA in those values that do not match up with any of the expected headerlist (CSV columns), otherwise we
-#simply specify the associated header name in the appropriate place. E.g. The third directory in the PP path example
-#above is the model (source_id), so the third list value in output_path_template is set to 'source_id'. We make sure
-#this is a valid value in headerlist as well.
-#The fourth directory is am5f3b1r0 which does not map to an existing header value. So we simply NA in output_path_template
-#for the fourth value.
-
-#catalog headers
-#The headerlist is expected column names in your catalog/csv file. This is usually determined by the users in conjuction
-#with the ESM collection specification standards and the appropriate workflows.
-
-headerlist = ["activity_id", "institution_id", "source_id", "experiment_id",
-                  "frequency", "realm", "table_id",
-                  "member_id", "grid_label", "variable_id",
-                  "temporal_subset", "chunk_freq","grid_label","platform","dimensions","cell_methods","path"]
-
-#what kind of directory structure to expect?
-#For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
-# the output_path_template is set as follows.
-#We have NA in those values that do not match up with any of the expected headerlist (CSV columns), otherwise we
-#simply specify the associated header name in the appropriate place. E.g. The third directory in the PP path example
-#above is the model (source_id), so the third list value in output_path_template is set to 'source_id'. We make sure
-#this is a valid value in headerlist as well.
-#The fourth directory is am5f3b1r0 which does not map to an existing header value. So we simply NA in output_path_template
-#for the fourth value.
-
-
-output_path_template = ['NA','NA','source_id','NA','experiment_id','platform','custom_pp','realm','cell_methods','frequency','chunk_freq']
-output_file_template = ['realm','temporal_subset','variable_id']
-
-#OUTPUT FILE INFO is currently passed as command-line argument.
-#We will revisit adding a csvfile, jsonfile and logfile configuration to the builder configuration file in the future.
-#csvfile =  #jsonfile =  #logfile =
-
-#######################################################
-
-input_path = ""  #   ENTER INPUT PATH HERE" #Example: /Users/ar46/archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp/"
-output_path = "" # ENTER NAME OF THE CSV AND JSON, THE SUFFIX ALONE. e.g catalog (the builder then generates catalog.csv and catalog.json. This can also be an absolute path)
-
-######### ADDITIONAL SEARCH FILTERS ###########################
-
-dictFilter = {}
-dictFilterIgnore = {}
-dictFilter["realm"]= 'atmos_cmip'
-dictFilter["frequency"] = "monthly"
-dictFilter["chunk_freq"] = "5yr"
-dictFilterIgnore["remove"]= 'DO_NOT_USE'
diff --git a/intakebuilder/catalogcols.py b/intakebuilder/catalogcols.py
deleted file mode 100644
index 6064a4c..0000000
--- a/intakebuilder/catalogcols.py
+++ /dev/null
@@ -1,4 +0,0 @@
-headerlist = ["activity_id", "institution_id", "source_id", "experiment_id",
-                  "frequency", "realm", "table_id",
-                  "member_id", "grid_label", "variable_id",
-                  "temporal_subset", "chunk_freq","grid_label","platform","dimensions","cell_methods","path"]
diff --git a/intakebuilder/config.yaml b/intakebuilder/config.yaml
deleted file mode 100644
index a964aca..0000000
--- a/intakebuilder/config.yaml
+++ /dev/null
@@ -1,41 +0,0 @@
-#what kind of directory structure to expect? 
-#For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
-# the output_path_template is set as follows.
-#We have NA in those values that do not match up with any of the expected headerlist (CSV columns), otherwise we
-#simply specify the associated header name in the appropriate place. E.g. The third directory in the PP path example
-#above is the model (source_id), so the third list value in output_path_template is set to 'source_id'. We make sure
-#this is a valid value in headerlist as well.
-#The fourth directory is am5f3b1r0 which does not map to an existing header value. So we simply NA in output_path_template
-#for the fourth value.
-
-#catalog headers
-#The headerlist is expected column names in your catalog/csv file. This is usually determined by the users in conjuction
-#with the ESM collection specification standards and the appropriate workflows.
-
-headerlist: ["activity_id", "institution_id", "source_id", "experiment_id",
-                  "frequency", "realm", "table_id",
-                  "member_id", "grid_label", "variable_id",
-                  "temporal_subset", "chunk_freq","grid_label","platform","dimensions","cell_methods","path"]
-
-#what kind of directory structure to expect?
-#For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
-# the output_path_template is set as follows.
-#We have NA in those values that do not match up with any of the expected headerlist (CSV columns), otherwise we
-#simply specify the associated header name in the appropriate place. E.g. The third directory in the PP path example
-#above is the model (source_id), so the third list value in output_path_template is set to 'source_id'. We make sure
-#this is a valid value in headerlist as well.
-#The fourth directory is am5f3b1r0 which does not map to an existing header value. So we simply NA in output_path_template
-#for the fourth value.
-
-output_path_template: ['NA','NA','source_id','NA','experiment_id','platform','custom_pp','realm','cell_methods','frequency','chunk_freq']
-
-output_file_template: ['realm','temporal_subset','variable_id']
-
-#OUTPUT FILE INFO is currently passed as command-line argument.
-#We will revisit adding a csvfile, jsonfile and logfile configuration to the builder configuration file in the future.
-#csvfile =  #jsonfile =  #logfile =
-
-#######################################################
-
-input_path: "/Users/ar46/archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp/" #"ENTER INPUT PATH HERE" #Example: /Users/ar46/archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp/"
-output_path: "catalog" # ENTER NAME OF THE CSV AND JSON, THE SUFFIX ALONE. e.g catalog (the builder then generates catalog.csv and catalog.json. This can also be an absolute path)
diff --git a/intakebuilder/configparser.py b/intakebuilder/configparser.py
deleted file mode 100644
index e64bedc..0000000
--- a/intakebuilder/configparser.py
+++ /dev/null
@@ -1,33 +0,0 @@
-import yaml
-import os
-class Config:
-    def __init__(self, config):
-        self.config = config
-        with open(self.config, 'r') as file:
-            configfile = yaml.safe_load(file)
-        try:
-            self.input_path = configfile['input_path']
-            print("input_path :",self.input_path)
-        except:
-            raise KeyError("input_path does not exist in config")
-        try:
-            self.output_path = configfile['output_path']
-            print("output_path :",self.output_path)
-        except:
-            raise KeyError("output_path does not exist in config")
-        try:
-            self.headerlist = configfile['headerlist']
-            print("headerlist :",self.headerlist)
-        except:
-            raise KeyError("headerlist does not exist in config")
-        try:
-            self.output_path_template = configfile['output_path_template']
-            print("output_path_template :",self.output_path_template)
-        except:
-            raise KeyError("output_path_template does not exist in config")
-        try:
-            self.output_file_template = configfile['output_file_template']
-            print("output_file_template :", self.output_file_template)
-        except:
-            raise KeyError("output_file_template does not exist in config")
-
diff --git a/intakebuilder/getinfo.py b/intakebuilder/getinfo.py
deleted file mode 100644
index d974c29..0000000
--- a/intakebuilder/getinfo.py
+++ /dev/null
@@ -1,206 +0,0 @@
-import sys
-import pandas as pd
-import csv
-from csv import writer
-import os
-import xarray as xr
-from intakebuilder import builderconfig, configparser 
-
-
-'''
-getinfo.py provides helper functions to get information (from filename, DRS, file/global attributes) needed to populate the catalog
-'''
-def getProject(projectdir,dictInfo):
-    '''
-    return Project name from the project directory input
-    :type dictInfo: object
-    :param drsstructure:
-    :return: dictionary with project key
-    '''
-    if ("archive" in projectdir or "pp" in projectdir): 
-       project = "dev" 
-       dictInfo["activity_id"]=project
-    return dictInfo
-
-def getinfoFromYAML(dictInfo,yamlfile,miptable=None):
-    import yaml
-    with open(yamlfile) as f:
-        mappings = yaml.load(f, Loader=yaml.FullLoader)
-        #print(mappings)
-        #for k, v in mappings.items():
-              #print(k, "->", v)
-        if(miptable):
-            try:
-                dictInfo["frequency"] = mappings[miptable]["frequency"]
-            except KeyError:
-                dictInfo["frequency"] = "NA"
-            try:
-                dictInfo["realm"] = mappings[miptable]["realm"]
-            except KeyError:
-                dictInfo["realm"]  = "NA"
-    return(dictInfo)
-
-def getStem(dirpath,projectdir):
-    '''
-    return stem from the project directory passed and the files crawled within
-    :param dirpath:
-    :param projectdir:
-    :param stem directory:
-    :return:
-    '''
-    stemdir = dirpath.split(projectdir)[1].split("/")  # drsstructure is the root
-    return stemdir
-
-
-def getInfoFromFilename(filename,dictInfo,logger):
-    # 5 AR: WE need to rework this, not being used in gfdl set up  get the following from the netCDF filename e.g.rlut_Amon_GFDL-ESM4_histSST_r1i1p1f1_gr1_195001-201412.nc
-    #print(filename)
-    if(filename.endswith(".nc")):
-        ncfilename = filename.split(".")[0].split("_")
-        varname = ncfilename[0]
-        dictInfo["variable"] = varname
-        miptable = ncfilename[1]
-        dictInfo["mip_table"] = miptable
-        modelname = ncfilename[2]
-        dictInfo["model"] = modelname
-        expname = ncfilename[3]
-        dictInfo["experiment_id"] = expname
-        ens = ncfilename[4]
-        dictInfo["ensemble_member"] = ens
-        grid = ncfilename[5]
-        dictInfo["grid_label"] = grid
-        try:
-           tsubset = ncfilename[6]
-        except IndexError:
-           tsubset = "null" #For fx fields
-        dictInfo["temporal_subset"] = tsubset
-    else:
-        logger.debug("Filename not compatible with this version of the builder:"+filename)
-    return dictInfo
-
-#adding this back to trace back some old errors
-def getInfoFromGFDLFilename(filename,dictInfo,logger):
-    # 5 AR: get the following from the netCDF filename e.g. atmos.200501-200912.t_ref.nc
-    if(filename.endswith(".nc")): #and not filename.startswith(".")):
-        ncfilename = filename.split(".")
-        varname = ncfilename[-2]
-        dictInfo["variable_id"] = varname
-        #miptable = "" #ncfilename[1]
-        #dictInfo["mip_table"] = miptable
-        #modelname = ncfilename[2]
-        #dictInfo["model"] = modelname
-        #expname = ncfilename[3]
-        #dictInfo["experiment_id"] = expname
-        #ens = ncfilename[4]
-        #dictInfo["ensemble_member"] = ens
-        #grid = ncfilename[5]
-        #dictInfo["grid_label"] = grid
-        try:
-           tsubset = ncfilename[1]
-        except IndexError:
-           tsubset = "null" #For fx fields
-        dictInfo["temporal_subset"] = tsubset
-    else:
-        logger.debug("Filename not compatible with this version of the builder:"+filename)
-    return dictInfo
-
-def getInfoFromGFDLDRS(dirpath,projectdir,dictInfo,configyaml):
-    '''
-    Returns info from project directory and the DRS path to the file
-    :param dirpath:
-    :param drsstructure:
-    :return:
-    '''
-   # we need thise dict keys "project", "institute", "model", "experiment_id",
-   #               "frequency", "realm", "mip_table",
-   #               "ensemble_member", "grid_label", "variable",
-   #               "temporal subset", "version", "path"]
- 
-   #Grab values based on their expected position in path 
-    stemdir = dirpath.split("/")
-   # adding back older versions to ensure we get info from builderconfig
-    stemdir = dirpath.split("/")
-
-    #lets go backwards and match given input directory to the template, add things to dictInfo
-    j = -1
-    cnt = 1
-    if configyaml:
-        output_path_template = configyaml.output_path_template
-    else:
-        try:
-            output_path_template = builderconfig.output_path_template 
-        except:
-            sys.exit("No output_path_template found in builderconfig.py. Check configuration.")
-
-    nlen = len(output_path_template) 
-    for i in range(nlen-1,0,-1):
-      try:
-          if(output_path_template[i] != "NA"):
-              try:
-                  dictInfo[output_path_template[i]] = stemdir[(j)]
-              except IndexError:
-                  print("Check configuration. Is output path template set correctly?")
-                  exit()
-      except IndexError:
-          sys.exit("oops in getInfoFromGFDLDRS"+str(i)+str(j)+output_path_template[i]+stemdir[j])
-      j = j - 1
-    cnt = cnt + 1
-    # WE do not want to work with anythi:1
-    # ng that's not time series
-    #TODO have verbose option to print message
-    if "cell_methods" in dictInfo.keys():
-      if (dictInfo["cell_methods"] != "ts"):
-         #print("Skipping non-timeseries data")
-         return {}
-    return dictInfo
-
-def getInfoFromDRS(dirpath,projectdir,dictInfo):
-    '''
-    Returns info from project directory and the DRS path to the file
-    :param dirpath:
-    :param drsstructure:
-    :return:
-    '''
-    #stemdir = getStem(dirpath, projectdir)
-    stemdir = dirpath.split(projectdir)[1].split("/")  # drsstructure is the root
-    try:
-        institute = stemdir[2]
-    except:
-        institute = "NA"
-    try:
-        version = stemdir[9]
-    except:
-        version = "NA"
-    dictInfo["institute"] = institute
-    dictInfo["version"] = version
-    return dictInfo
-def return_xr(fname):
-    filexr = (xr.open_dataset(fname))
-    filexra = filexr.attrs
-    return filexra
-def getInfoFromGlobalAtts(fname,dictInfo,filexra=None):
-    '''
-    Returns info from the filename and xarray dataset object
-    :param fname: DRS compliant filename
-    :param filexr: Xarray dataset object
-    :return: dictInfo with institution_id version realm frequency and product
-    '''
-    filexra = return_xr(fname)
-    if dictInfo["institute"] == "NA":
-      try:
-          institute = filexra["institution_id"]
-      except KeyError:
-          institute = "NA"
-      dictInfo["institute"] = institute
-    if dictInfo["version"] == "NA":
-        try:
-            version = filexra["version"]
-        except KeyError:
-            version = "NA"
-        dictInfo["version"] = version
-    realm = filexra["realm"]
-    dictInfo["realm"] = realm
-    frequency = filexra["frequency"]
-    dictInfo["frequency"] = frequency
-    return dictInfo
-
diff --git a/intakebuilder/gfdlcrawler.py b/intakebuilder/gfdlcrawler.py
deleted file mode 100644
index dd81c04..0000000
--- a/intakebuilder/gfdlcrawler.py
+++ /dev/null
@@ -1,78 +0,0 @@
-import os
-from intakebuilder import getinfo, builderconfig
-import sys
-import re
-import operator as op
-'''
-localcrawler crawls through the local file path, then calls helper functions in the package to getinfo.
-It finally returns a list of dict. eg {'project': 'CMIP6', 'path': '/uda/CMIP6/CDRMIP/NCC/NorESM2-LM/esm-pi-cdr-pulse/r1i1p1f1/Emon/zg/gn/v20191108/zg_Emon_NorESM2-LM_esm-pi-cdr-pulse_r1i1p1f1_gn_192001-192912.nc', 'variable': 'zg', 'mip_table': 'Emon', 'model': 'NorESM2-LM', 'experiment_id': 'esm-pi-cdr-pulse', 'ensemble_member': 'r1i1p1f1', 'grid_label': 'gn', 'temporal subset': '192001-192912', 'institute': 'NCC', 'version': 'v20191108'}
-
-'''
-def crawlLocal(projectdir, dictFilter,dictFilterIgnore,logger,configyaml):
-    '''
-    Craw through the local directory and run through the getInfo.. functions
-    :param projectdir:
-    :return:listfiles which has a dictionary of all key/value pairs for each file to be added to the csv
-    '''
-    listfiles = []
-    pat = None
-    if("realm" in dictFilter.keys()) & (("frequency") in dictFilter.keys()):
-        pat = re.compile('({}/{}/{}/{})'.format(dictFilter["realm"],"ts",dictFilter["frequency"],dictFilter["chunk_freq"]))
-    
-    orig_pat = pat
-
-    #TODO INCLUDE filter in traversing through directories at the top
-    for dirpath, dirs, files in os.walk(projectdir):
-        searchpath = dirpath
-        if (orig_pat is None):
-            pat = dirpath  #we assume matching entire path
-        if(pat is not None):
-            m = re.search(pat, searchpath)
-            for filename in files:
-               # get info from filename
-               filepath = os.path.join(dirpath,filename)  # 1 AR: Bugfix: this needs to join dirpath and filename to get the full path to the file
-
-               #if filename.startswith("."):
-               #    logger.debug("Skipping hidden file", filepath)
-               #    continue
-               if not filename.endswith(".nc"):
-                   logger.debug("FILE does not end with .nc. Skipping", filepath)
-                   continue
-               logger.info(dirpath+"/"+filename)
-               dictInfo = {}
-               dictInfo = getinfo.getProject(projectdir, dictInfo)
-               # get info from filename
-               #filepath = os.path.join(dirpath,filename)  # 1 AR: Bugfix: this needs to join dirpath and filename to get the full path to the file
-               dictInfo["path"]=filepath
-               if (op.countOf(filename,".") == 1):
-                 dictInfo = getinfo.getInfoFromFilename(filename,dictInfo, logger)
-               else:
-                 dictInfo = getinfo.getInfoFromGFDLFilename(filename,dictInfo, logger)
-               dictInfo = getinfo.getInfoFromGFDLDRS(dirpath, projectdir, dictInfo,configyaml)
-               list_bad_modellabel = ["","piControl","land-hist","piClim-SO2","abrupt-4xCO2","hist-piAer","hist-piNTCF","piClim-ghg","piClim-OC","hist-GHG","piClim-BC","1pctCO2"]
-               list_bad_chunklabel = ['DO_NOT_USE']
-               if "source_id" in dictInfo: 
-                   if(dictInfo["source_id"] in list_bad_modellabel):
-                       logger.debug("Found experiment name in model column, skipping this possibly bad DRS filename",filepath)
-                   #   continue
-               if "chunk_freq" in dictInfo:
-                   if(dictInfo["chunk_freq"] in list_bad_chunklabel):
-                       logger.debug("Found bad chunk, skipping this possibly bad DRS filename",filepath)
-                       continue     
- 
-               if configyaml:
-                   headerlist = configyaml.headerlist
-               else:
-                   headerlist = builderconfig.headerlist
-               # remove those keys that are not CSV headers 
-               # move it so its one time 
-               rmkeys = []
-               for dkeys in dictInfo.keys():
-                  if dkeys not in headerlist:
-                      rmkeys.append(dkeys) 
-               rmkeys = list(set(rmkeys))
-
-               for k in rmkeys: dictInfo.pop(k,None)
- 
-               listfiles.append(dictInfo)
-    return listfiles
diff --git a/intakebuilder/localcrawler.py b/intakebuilder/localcrawler.py
deleted file mode 100644
index ac43810..0000000
--- a/intakebuilder/localcrawler.py
+++ /dev/null
@@ -1,57 +0,0 @@
-import os
-from intakebuilder import getinfo
-import re
-'''
-localcrawler crawls through the local file path, then calls helper functions in the package to getinfo.
-It finally returns a list of dict
-'''
-def crawlLocal(projectdir, dictFilter,logger):
-    '''
-    Craw through the local directory and run through the getInfo.. functions
-    :param projectdir:
-    :return:listfiles which has a dictionary of all key/value pairs for each file to be added to the csv
-    '''
-    listfiles = []
-    pat = None
-    if("miptable" in dictFilter.keys()) & (("varname") in dictFilter.keys()):
-        pat = re.compile('({}/{}/)'.format(dictFilter["miptable"],dictFilter["varname"]))
-    elif("miptable" in dictFilter.keys()):
-        pat = re.compile('({}/)'.format(dictFilter["miptable"]))
-    elif(("varname") in dictFilter.keys()):
-        pat = re.compile('({}/)'.format(dictFilter["varname"]))
-    orig_pat = pat
-    #TODO INCLUDE filter in traversing through directories at the top
-    for dirpath, dirs, files in os.walk(projectdir):
-        #print(dirpath, dictFilter["source_prefix"])
-        if dictFilter["source_prefix"] in dirpath: #TODO improved filtering
-            searchpath = dirpath
-            if (orig_pat is None):
-                pat = dirpath  #we assume matching entire path
-          #  print("Search filters applied", dictFilter["source_prefix"], "and", pat)
-            if(pat is not None):
-                m = re.search(pat, searchpath)
-                for filename in files:
-                   logger.info(dirpath+"/"+filename)
-                   dictInfo = {}
-                   dictInfo = getinfo.getProject(projectdir, dictInfo)
-                   # get info from filename
-                   #print(filename)
-                   filepath = os.path.join(dirpath,filename)  # 1 AR: Bugfix: this needs to join dirpath and filename to get the full path to the file
-                   if not filename.endswith(".nc"):
-                        logger.debug("FILE does not end with .nc. Skipping", filepath)
-                        continue
-                   dictInfo["path"]=filepath
-#                  print("Callin:g getinfo.getInfoFromFilename(filename, dictInfo)..")
-                   dictInfo = getinfo.getInfoFromFilename(filename, dictInfo,logger)
-#                  print("Calling getinfo.getInfoFromDRS(dirpath, projectdir, dictInfo)")
-                   dictInfo = getinfo.getInfoFromDRS(dirpath, projectdir, dictInfo)
-#                  print("Calling getinfo.getInfoFromGlobalAtts(filepath, dictInfo)")
-#                  dictInfo = getinfo.getInfoFromGlobalAtts(filepath, dictInfo)
-                   #eliminate bad DRS filenames spotted
-                   list_bad_modellabel = ["","piControl","land-hist","piClim-SO2","abrupt-4xCO2","hist-piAer","hist-piNTCF","piClim-ghg","piClim-OC","hist-GHG","piClim-BC","1pctCO2"]
-                   if(dictInfo["model"] in list_bad_modellabel):
-                      logger.debug("Found experiment name in model column, skipping this possibly bad DRS filename", dictInfo["experiment"],filepath)
-                      continue
-                   listfiles.append(dictInfo)
-                   #print(listfiles)
-    return listfiles
diff --git a/intakebuilder/s3crawler.py b/intakebuilder/s3crawler.py
deleted file mode 100644
index e55d676..0000000
--- a/intakebuilder/s3crawler.py
+++ /dev/null
@@ -1,59 +0,0 @@
-import re
-import boto3
-import botocore
-from intakebuilder import getinfo
-
-'''
-s3 crawler crawls through the S3 bucket, passes the bucket path to the helper functions to getinfo.
-Finally it returns a list of dictionaries. 
-'''
-def sss_crawler(projectdir,dictFilter,project_root, logger):
-    region = 'us-west-2'
-    s3client = boto3.client('s3', region_name=region,
-                            config=botocore.client.Config(signature_version=botocore.UNSIGNED))
-
-    s3prefix = "s3:/"
-    filetype = ".nc"
-    project_bucket = projectdir.split("/")[2]
-    #######################################################
-    listfiles = []
-    pat = None
-    logger.debug(dictFilter.keys())
-    if("miptable" in dictFilter.keys()) & (("varname") in dictFilter.keys()):
-        pat = re.compile('({}/{}/)'.format(dictFilter["miptable"],dictFilter["varname"]))
-    elif("miptable" in dictFilter.keys()):
-        pat = re.compile('({}/)'.format(dictFilter["miptable"]))
-    elif(("varname") in dictFilter.keys()):
-        pat = re.compile('({}/)'.format(dictFilter["varname"]))
-    orig_pat = pat
-    paginator = s3client.get_paginator('list_objects')
-    for result in paginator.paginate(Bucket=project_bucket, Prefix=dictFilter["source_prefix"], Delimiter=filetype):
-        for prefixes in result.get('CommonPrefixes'):
-            dictInfo = {}
-            dictInfo = getinfo.getProject(project_root, dictInfo)
-            commonprefix = prefixes.get('Prefix')
-            searchpath = commonprefix
-            if (orig_pat is None):
-                pat = commonprefix #we assume matching entire path
-            #filepath = '{}/{}/{}'.format(s3prefix,project_bucket,commonprefix)
-          #  print("Search filters applied", dictFilter["source_prefix"], "and", pat)
-            if(pat is not None):
-                m = re.search(pat, searchpath)
-                if m is not None:
-                        #print(commonprefix)
-                        #print('{}/{}/{}'.format(s3prefix,project_bucket,commonprefix))
-                        filepath = '{}/{}/{}'.format(s3prefix,project_bucket,commonprefix)
-                        #TODO if filepath already exists in csv we skip
-                        dictInfo["path"]=filepath
-                        logger.debug(filepath)
-                        filename = filepath.split("/")[-1]
-                        dirpath = "/".join(filepath.split("/")[0:-1])
-                        #projectdird passed to sss_crawler should be s3://bucket/project
-                        dictInfo = getinfo.getInfoFromFilename(filename, dictInfo,logger)
-                        dictInfo = getinfo.getInfoFromDRS(dirpath, projectdir, dictInfo)
-                        #Using YAML instead of this to get frequency and modeling_realm  dictInfo = getinfo.getInfoFromGlobalAtts(filepath, dictInfo)
-                        #TODO YAML for all mip_tables
-                        dictInfo = getinfo.getinfoFromYAML(dictInfo,"table.yaml",miptable=dictInfo["mip_table"])
-                        listfiles.append(dictInfo)
-                        logger.debug(dictInfo)
-    return listfiles
diff --git a/intakebuilder/table.yaml b/intakebuilder/table.yaml
deleted file mode 100644
index bdae363..0000000
--- a/intakebuilder/table.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-Amon:
-    frequency: mon
-    realm: atmos
-Omon:
-    frequency: mon
-    realm: ocean
-3hr:
-    frequency: 3hr
-    realm: na