In [1]:
from pathlib import Path
import sys
notebook_directory_parent = Path.cwd().resolve().parent
if str(notebook_directory_parent) not in sys.path:
sys.path.append(str(notebook_directory_parent))
In [2]:
from T1000.utilities.configure_paths import (DataPaths, NISTChemistryWebbookPaths)
from T1000.NistChemBook import species_list
from bs4 import BeautifulSoup
import csv
import requests
In [3]:
csv_as_list = species_list.ReadAndClean.to_list()
In [6]:
csv_as_list[:5]
Out[6]:
[['Electron', 'e-', 'N/A'],
['Iron(2) oxide anion', 'FeO-', 'N/A'],
['AsF3..Cl anion', 'AsClF3-', 'N/A'],
['AgH2-', 'H2Ag-', 'N/A'],
['HAg(H2)', 'H3Ag', 'N/A'],
['AgNO+', 'AgNO+', 'N/A'],
['AgNO', 'AgNO', 'N/A'],
['AgNO-', 'AgNO-', 'N/A'],
['AgOO-', 'AgO2-', 'N/A'],
['AgAgH', 'HAg2', 'N/A'],
['AgAgH-', 'HAg2-', 'N/A'],
['AgOAg', 'Ag2O', 'N/A'],
['Ag4', 'Ag4', 'N/A'],
['Ag5', 'Ag5', 'N/A'],
['Ag8', 'Ag8', 'N/A'],
['HAlClBr', 'HAlBrCl', 'N/A'],
['AlCl2Br', 'AlBrCl2', 'N/A'],
['HAlFBr', 'HAlBrF', 'N/A'],
['AlF2Br', 'AlBrF2', 'N/A'],
['Br(cyc-AlO2)', 'AlBrO2', 'N/A'],
['BrAlO2', 'AlBrO2', 'N/A'],
['BrAl(O2)2', 'AlBrO4', 'N/A'],
['AlClBr2', 'AlBr2Cl', 'N/A'],
['AlFBr2', 'AlBr2F', 'N/A'],
['HAlBr2', 'HAlBr2', 'N/A'],
['HAlFCl', 'HAlClF', 'N/A'],
['AlF2Cl', 'AlClF2', 'N/A'],
['AlH2Cl', 'H2AlCl', 'N/A'],
['Cl(cyc-AlO2)', 'AlClO2', 'N/A'],
['ClAlO2', 'AlClO2', 'N/A'],
['ClAl(O2)2', 'AlClO4', 'N/A'],
['AlFCl2', 'AlCl2F', 'N/A'],
['F(cyc-AlO2)', 'AlFO2', 'N/A'],
['FAlO2', 'AlFO2', 'N/A'],
['FAl(O2)2', 'AlFO4', 'N/A'],
['AlNH2', 'H2AlN', 'N/A'],
['AlNH3+', 'H3AlN+', 'N/A'],
['AlNH3', 'H3AlN', 'N/A'],
['HAlNH2', 'H3AlN', 'N/A'],
['AlPH3', 'H3AlP', 'N/A'],
['HAlPH2', 'H3AlP', 'N/A'],
['H2AlPH', 'H3AlP', 'N/A'],
['AlSiH3', 'H3AlSi', 'N/A'],
['H2AlNH2', 'H4AlN', 'N/A'],
['AlSiH4', 'H4AlSi', 'N/A'],
['AlI2', 'AlI2', 'N/A'],
['NAlO', 'AlNO', 'N/A'],
['AlNO', 'AlNO', 'N/A'],
['AlON', 'AlNO', 'N/A'],
['AlNO-', 'AlNO-', 'N/A'],
['NAlN', 'AlN2', 'N/A'],
['AlNNN', 'AlN3', 'N/A'],
['AlOSi', 'AlOSi', 'N/A'],
['cyc-AlO2', 'AlO2', 'N/A'],
['OAlOO', 'AlO3', 'N/A'],
['cyc-AlP2', 'AlP2', 'N/A'],
['cyc-AlP2-', 'AlP2-', 'N/A'],
['(BrAlO)2', 'Al2Br2O2', 'N/A'],
['(ClAlO)2', 'Al2Cl2O2', 'N/A'],
['(FAlO)2', 'Al2F2O2', 'N/A'],
['cyc-Al2H2', 'H2Al2', 'N/A'],
['H(cyc-AlHAl)', 'H2Al2', 'N/A'],
['Al2H4', 'H4Al2', 'N/A'],
['HAl(H)3Al', 'H4Al2', 'N/A'],
['Al2H6', 'H6Al2', 'N/A'],
['AlNAl', 'Al2N', 'N/A'],
['Al2N2', 'Al2N2', 'N/A'],
['(AlO)2', 'Al2O2', 'N/A'],
['(AlO)2-', 'Al2O2-', 'N/A'],
['Al2O3-', 'Al2O3-', 'N/A'],
['Al2O4', 'Al2O4', 'N/A'],
['Al2O4-', 'Al2O4-', 'N/A'],
['Al2O5', 'Al2O5', 'N/A'],
['Al2O5-', 'Al2O5-', 'N/A'],
['Al2P', 'Al2P', 'N/A'],
['Al2P-', 'Al2P-', 'N/A'],
['Al2P2', 'Al2P2', 'N/A'],
['Al2P2-', 'Al2P2-', 'N/A'],
['cyc-GeAl3', 'Al3Ge', 'N/A'],
['cyc-GeAl3-', 'Al3Ge-', 'N/A'],
['Al3Ge2', 'Al3Ge2', 'N/A'],
['Al3Ge2-', 'Al3Ge2-', 'N/A'],
['NAl3', 'Al3N', 'N/A'],
['Al3N-', 'Al3N-', 'N/A'],
['Al3O', 'Al3O', 'N/A'],
['Al3O-', 'Al3O-', 'N/A'],
['Al3O2', 'Al3O2', 'N/A'],
['Al3O2-', 'Al3O2-', 'N/A'],
['Al3O3', 'Al3O3', 'N/A'],
['Al3O3-', 'Al3O3-', 'N/A'],
['Al3O4', 'Al3O4', 'N/A'],
['Al3O4-', 'Al3O4-', 'N/A'],
['cyc-PbAl3', 'Al3Pb', 'N/A'],
['cyc-PbAl3-', 'Al3Pb-', 'N/A'],
['cyc-SiAl3', 'Al3Si', 'N/A'],
['cyc-SiAl3-', 'Al3Si-', 'N/A'],
['Al3Si2', 'Al3Si2', 'N/A'],
['Al3Si2-', 'Al3Si2-', 'N/A'],
['cyc-SnAl3', 'Al3Sn', 'N/A'],
['cyc-SnAl3-', 'Al3Sn-', 'N/A'],
['Al4Ge', 'Al4Ge', 'N/A'],
['Al4Ge-', 'Al4Ge-', 'N/A'],
['Al4N', 'Al4N', 'N/A'],
['Al4N- (D4h)', 'Al4N-', 'N/A'],
['Al4N- (C2v)', 'Al4N-', 'N/A'],
['Al4Si', 'Al4Si', 'N/A'],
['Al4Si-', 'Al4Si-', 'N/A'],
['Al5', 'Al5', 'N/A'],
['Al5-', 'Al5-', 'N/A'],
['ArBeO2', 'ArBeO2', 'N/A'],
['HArF', 'HArF', 'N/A'],
['ArXeH', 'HArXe', 'N/A'],
['ArNN+', 'ArN2+', 'N/A'],
['Ga2As-', 'AsGa2-', 'N/A'],
['In2As', 'AsIn2', 'N/A'],
['cyc-GaAs2-', 'As2Ga-', 'N/A'],
['As3', 'As3', 'N/A'],
['Ga2As3', 'As3Ga2', 'N/A'],
['Ga2As3-', 'As3Ga2-', 'N/A'],
['As5', 'As5', 'N/A'],
['As5-', 'As5-', 'N/A'],
['AuH2', 'H2Au', 'N/A'],
['AuH2-', 'H2Au-', 'N/A'],
['HAu(H2)', 'H3Au', 'N/A'],
['AuH4-', 'H4Au-', 'N/A'],
['(H2)AuH3', 'H5Au', 'N/A'],
['AuNO+', 'AuNO+', 'N/A'],
['AuNO', 'AuNO', 'N/A'],
['Au(NO)2+', 'AuN2O2+', 'N/A'],
['Au(NO)2', 'AuN2O2', 'N/A'],
['AuOO', 'AuO2', 'N/A'],
['OAuO', 'AuO2', 'N/A'],
['AuAuH', 'HAu2', 'N/A'],
['AuAuH-', 'HAu2-', 'N/A'],
['HBBr+', 'HBBr+', 'N/A'],
['NH2BBr2+', 'H2BBr2N+', 'N/A'],
['HBCl+', 'HBCl+', 'N/A'],
['(cyc-NNB)Cl', 'BClN2', 'N/A'],
['NH2BCl2+', 'H2BCl2N+', 'N/A'],
['ClBNCl', 'BCl2N', 'N/A'],
['BF2OH', 'HBF2O', 'N/A'],
['GaBH6+', 'H6BGa+', 'N/A'],
['GaBH6', 'H6BGa', 'N/A'],
['H2NB', 'H2BN', 'N/A'],
['HBNH2', 'H3BN', 'N/A'],
['BH4', 'H4B', 'N/A'],
['KBH4', 'H4BK', 'N/A'],
['NBO', 'BNO', 'N/A'],
['OBON', 'BNO2', 'N/A'],
['BNSi', 'BNSi', 'N/A'],
['NBN', 'BN2', 'N/A'],
['BNN', 'BN2', 'N/A'],
['OBNNO', 'BN2O2', 'N/A'],
['NNBN', 'BN3', 'N/A'],
['OBSO', 'BO2S', 'N/A'],
['HBNB', 'HB2N', 'N/A'],
['HNBBNH', 'H2B2N2', 'N/A'],
['BNB', 'B2N', 'N/A'],
['BNB-', 'B2N-', 'N/A'],
['BBNO', 'B2NO', 'N/A'],
['BNBO', 'B2NO', 'N/A'],
['BNBO-', 'B2NO-', 'N/A'],
['BBNN', 'B2N2', 'N/A'],
['BNBN', 'B2N2', 'N/A'],
['cyc-(BN)2', 'B2N2', 'N/A'],
['BOB', 'B2O', 'N/A'],
['cyc-B3-', 'B3-', 'N/A'],
['BNBB', 'B3N', 'N/A'],
['BNBB-', 'B3N-', 'N/A'],
['BBBNO', 'B3NO', 'N/A'],
['BNBBO', 'B3NO', 'N/A'],
['B4', 'B4', 'N/A'],
['B4-', 'B4-', 'N/A'],
['B5', 'B5', 'N/A'],
['B5-', 'B5-', 'N/A'],
['B6', 'B6', 'N/A'],
['B6-', 'B6-', 'N/A'],
['cyc-(BaO)2', 'Ba2O2', 'N/A'],
['BaOBaO', 'Ba2O2', 'N/A'],
['BeNO', 'BeNO', 'N/A'],
['NNBeO2', 'BeN2O2', 'N/A'],
['NNBeNN', 'BeN4', 'N/A'],
['NN(cyc-BeN2)', 'BeN4', 'N/A'],
['BeO3', 'BeO3', 'N/A'],
['O2BeO2', 'BeO4', 'N/A'],
['HBeOBeH', 'H2Be2O', 'N/A'],
['HBeHBeH', 'H3Be2', 'N/A'],
['BeOBeNO', 'Be2NO2', 'N/A'],
['BeBeNN', 'Be2N2', 'N/A'],
['BeNNBe', 'Be2N2', 'N/A'],
['(BeN)2', 'Be2N2', 'N/A'],
['NNBeBeNN', 'Be2N4', 'N/A'],
['cyc-(BeO)2', 'Be2O2', 'N/A'],
['BeOBeO', 'Be2O2', 'N/A'],
['BiOH', 'HBiO', 'N/A'],
['BiH2', 'H2Bi', 'N/A'],
['BiH3', 'H3Bi', 'N/A'],
['Bi5', 'Bi5', 'N/A'],
['Bi5-', 'Bi5-', 'N/A'],
['BrOCl', 'BrClO', 'N/A'],
['BrClO2', 'BrClO2', 'N/A'],
['BrOClO', 'BrClO2', 'N/A'],
['ClOBrO', 'BrClO2', 'N/A'],
['ClSBr', 'BrClS', 'N/A'],
['GaH2Br', 'H2BrGa', 'N/A'],
['HXeBr', 'HBrXe', 'N/A'],
['H2PBr', 'H2BrP', 'N/A'],
['BrON', 'BrNO', 'N/A'],
['c-BrONO', 'BrNO2', 'N/A'],
['CuBr2', 'Br2Cu', 'N/A'],
['HGaBr2', 'HBr2Ga', 'N/A'],
['HBrBrH+', 'H2Br2+', 'N/A'],
['BrLiBr', 'Br2Li', 'N/A'],
['BrNaBr', 'Br2Na', 'N/A'],
['AgCN', 'CAgN', 'N/A'],
['AgCN-', 'CAgN-', 'N/A'],
['AgCO+', 'CAgO+', 'N/A'],
['SAgCS', 'CAgS2', 'N/A'],
['AlCN', 'CAlN', 'N/A'],
['AlNC', 'CAlN', 'N/A'],
['AlCO-', 'CAlO-', 'N/A'],
['AlCSi', 'CAlSi', 'N/A'],
['AlCSi-', 'CAlSi-', 'N/A'],
['CAlSi2', 'CAlSi2', 'N/A'],
['cis-CAlSi2-', 'CAlSi2-', 'N/A'],
['CAl3', 'CAl3', 'N/A'],
['CAl3-', 'CAl3-', 'N/A'],
['CAl3Ge', 'CAl3Ge', 'N/A'],
['CAl3Ge-', 'CAl3Ge-', 'N/A'],
['CAl3Si', 'CAl3Si', 'N/A'],
['CAl3Si-', 'CAl3Si-', 'N/A'],
['Al4C', 'CAl4', 'N/A'],
['Al4C-', 'CAl4-', 'N/A'],
['Al5C', 'CAl5', 'N/A'],
['Al5C-', 'CAl5-', 'N/A'],
['ArCUO', 'CArOU', 'N/A'],
['AsCO', 'CAsO', 'N/A'],
['AsCO-', 'CAsO-', 'N/A'],
['AuCO+', 'CAuO+', 'N/A'],
['AuCO', 'CAuO', 'N/A'],
['SAuCS', 'CAuS2', 'N/A'],
['BCN', 'CBN', 'N/A'],
['BNC', 'CBN', 'N/A'],
['NNBCO', 'CBN2O', 'N/A'],
['cyc-B2C', 'CB2', 'N/A'],
['BBCO', 'CB2O', 'N/A'],
['BaNC', 'CBaN', 'N/A'],
['BeCN', 'CBeN', 'N/A'],
['BeNC', 'CBeN', 'N/A'],
['BeBeCO', 'CBe2O', 'N/A'],
['CF3BrF', 'CBrF4', 'N/A'],
['CBr2-', 'CBr2-', 'N/A'],
['CF3ClF', 'CClF4', 'N/A'],
['ClCNO+', 'CClNO+', 'N/A'],
['ClC(O)S', 'CClOS', 'N/A'],
['SiCCl', 'CClSi', 'N/A'],
['CCl3ONO', 'CCl3NO2', 'N/A'],
['Cl2CCl-Cl', 'CCl4', 'N/A'],
['Cl2CCl-Cl-', 'CCl4-', 'N/A'],
['CCl4-', 'CCl4-', 'N/A'],
['CoCO+', 'CCoO+', 'N/A'],
['CoCO-', 'CCoO-', 'N/A'],
['OCoCO', 'CCoO2', 'N/A'],
['OCoCO-', 'CCoO2-', 'N/A'],
['CoCO2-', 'CCoO2-', 'N/A'],
['CoCS2+', 'CCoS2+', 'N/A'],
['cyc-(CoSC)S', 'CCoS2', 'N/A'],
['CoCS2', 'CCoS2', 'N/A'],
['SCoCS', 'CCoS2', 'N/A'],
['Co2CO', 'CCo2O', 'N/A'],
['CrCO+', 'CCrO+', 'N/A'],
['CrCO-', 'CCrO-', 'N/A'],
['OCrCO+', 'CCrO2+', 'N/A'],
['OCrCO', 'CCrO2', 'N/A'],
['CrOCO', 'CCrO2', 'N/A'],
['OCrCO-', 'CCrO2-', 'N/A'],
['CuCN', 'CCuN', 'N/A'],
['CuCN-', 'CCuN-', 'N/A'],
['CuNC-', 'CCuN-', 'N/A'],
['CuCO+', 'CCuO+', 'N/A'],
['CuCO-', 'CCuO-', 'N/A'],
['OCuCO-', 'CCuO2-', 'N/A'],
['CuCO2-', 'CCuO2-', 'N/A'],
['CuCS', 'CCuS', 'N/A'],
['CuSCS+', 'CCuS2+', 'N/A'],
['SCuCS', 'CCuS2', 'N/A'],
['Cu2CS', 'CCu2S', 'N/A'],
['FC(O)OONO2', 'CFNO5', 'N/A'],
['c-FC(O)OO', 'CFO3', 'N/A'],
['CF3N', 'CF3N', 'N/A'],
['CF3OOO', 'CF3O3', 'N/A'],
['CF3OSO2', 'CF3O3S', 'N/A'],
['CF3IF', 'CF4I', 'N/A'],
['FeNC', 'CFeN', 'N/A'],
['FeCO+', 'CFeO+', 'N/A'],
['OFeCO', 'CFeO2', 'N/A'],
['OFeCO-', 'CFeO2-', 'N/A'],
['Fe2CO', 'CFe2O', 'N/A'],
['GaCN', 'CGaN', 'N/A'],
['GaNC', 'CGaN', 'N/A'],
['GeCO-', 'CGeO-', 'N/A'],
['HCBBr', 'CHBBr', 'N/A'],
['HCBCl', 'CHBCl', 'N/A'],
['HCBF', 'CHBF', 'N/A'],
['HBCN', 'CHBN', 'N/A'],
['HBNC', 'CHBN', 'N/A'],
['cyc-HB(CN)', 'CHBN', 'N/A'],
['HBeCN', 'CHBeN', 'N/A'],
['HBeNC', 'CHBeN', 'N/A'],
['HCCl+', 'CHCl+', 'N/A'],
['CHCl2OONO2', 'CHCl2NO4', 'N/A'],
['CCl3OH', 'CHCl3O', 'N/A'],
['FCNH', 'CHFN', 'N/A'],
['CF2=NH+', 'CHF2N+', 'N/A'],
['CF2=NH', 'CHF2N', 'N/A'],
['HCGe', 'CHGe', 'N/A'],
['HKrCN', 'CHKrN', 'N/A'],
['HXeNCO', 'CHNOXe', 'N/A'],
['HPCN', 'CHNP', 'N/A'],
['HSCN', 'CHNS', 'N/A'],
['HSNC', 'CHNS', 'N/A'],
['HCNSi', 'CHNSi', 'N/A'],
['cyc-(HCSiN)', 'CHNSi', 'N/A'],
['HSiNC', 'CHNSi', 'N/A'],
['HSiCN', 'CHNSi', 'N/A'],
['HXeCN', 'CHNXe', 'N/A'],
['HXeNC', 'CHNXe', 'N/A'],
['HCNN-', 'CHN2-', 'N/A'],
['HNCN-', 'CHN2-', 'N/A'],
['HNiCO', 'CHNiO', 'N/A'],
['HNiCO-', 'CHNiO-', 'N/A'],
['HOCS+', 'CHOS+', 'N/A'],
['t-HSCO', 'CHOS', 'N/A'],
['HCS2', 'CHS2', 'N/A'],
['HCSi', 'CHSi', 'N/A'],
['WCH', 'CHW', 'N/A'],
['H2CBBr', 'CH2BBr', 'N/A'],
['H2CBCl', 'CH2BCl', 'N/A'],
['H2CBF', 'CH2BF', 'N/A'],
['BH2CN', 'CH2BN', 'N/A'],
['CH2NB', 'CH2BN', 'N/A'],
['CH2BO', 'CH2BO', 'N/A'],
['HCBeH', 'CH2Be', 'N/A'],
['H2CCl-Br', 'CH2BrCl', 'N/A'],
['H2CBr-I', 'CH2BrI', 'N/A'],
['CH2MgBr', 'CH2BrMg', 'N/A'],
['H2CBr-Br', 'CH2Br2', 'N/A'],
['H2CCl-I', 'CH2ClI', 'N/A'],
['CH2MgCl', 'CH2ClMg', 'N/A'],
['CH2ClOONO2', 'CH2ClNO4', 'N/A'],
['H2CCl-Cl', 'CH2Cl2', 'N/A'],
['CHCl2OOH', 'CH2Cl2O2', 'N/A'],
['CH2MgF', 'CH2FMg', 'N/A'],
['H2CGe', 'CH2Ge', 'N/A'],
['H2CI-I', 'CH2I2', 'N/A'],
['MgCH2', 'CH2Mg', 'N/A'],
['HCNH', 'CH2N', 'N/A'],
['H2NCO', 'CH2NO', 'N/A'],
['HCNNH', 'CH2N2', 'N/A'],
['H2CSS', 'CH2S2', 'N/A'],
['cyc-H2CS2', 'CH2S2', 'N/A'],
['CH3BBr', 'CH3BBr', 'N/A'],
['CH3BCl', 'CH3BCl', 'N/A'],
['CH2BNH', 'CH3BN', 'N/A'],
['CH3NB', 'CH3BN', 'N/A'],
['CH3BO', 'CH3BO', 'N/A'],
['CH2BOH', 'CH3BO', 'N/A'],
['BeCH3', 'CH3Be', 'N/A'],
['CH2BeH', 'CH3Be', 'N/A'],
['H2CBrH+', 'CH3Br+', 'N/A'],
['CH3MgBr', 'CH3BrMg', 'N/A'],
['CH3BrSi', 'CH3BrSi', 'N/A'],
['CH3SiBr', 'CH3BrSi', 'N/A'],
['CH2=SiHBr', 'CH3BrSi', 'N/A'],
['CdCH3+', 'CH3Cd+', 'N/A'],
['ClCr(O)2SCH3', 'CH3ClCrO2S', 'N/A'],
['ClCrO2OCH3', 'CH3ClCrO3', 'N/A'],
['CH3MgCl', 'CH3ClMg', 'N/A'],
['HMgCH2Cl', 'CH3ClMg', 'N/A'],
['CH3SCl+', 'CH3ClS+', 'N/A'],
['CH3SCl', 'CH3ClS', 'N/A'],
['CH3ClSi', 'CH3ClSi', 'N/A'],
['Cl2V(O)SCH3', 'CH3Cl2OSV', 'N/A'],
['Cl2V(O)OCH3', 'CH3Cl2O2V', 'N/A'],
['Cl3TiOCH3', 'CH3Cl3OTi', 'N/A'],
['CH3MgF', 'CH3FMg', 'N/A'],
['HMgCH2F', 'CH3FMg', 'N/A'],
['CH3FSi', 'CH3FSi', 'N/A'],
['CH3SiF', 'CH3FSi', 'N/A'],
['CH2=SiHF', 'CH3FSi', 'N/A'],
['GaCH3', 'CH3Ga', 'N/A'],
['CH3MgI', 'CH3IMg', 'N/A'],
['CH3SiI', 'CH3ISi', 'N/A'],
['CH2=SiHI', 'CH3ISi', 'N/A'],
['InCH3', 'CH3In', 'N/A'],
['LiCH3', 'CH3Li', 'N/A'],
['MgCH3+', 'CH3Mg+', 'N/A'],
['CH3O+', 'CH3O+', 'N/A'],
['CH3O2-', 'CH3O2-', 'N/A'],
['CH3S2+', 'CH3S2+', 'N/A'],
['CH3Si-', 'CH3Si-', 'N/A'],
['ZnCH3+', 'CH3Zn+', 'N/A'],
['HAl(Cl)CH3', 'CH4AlCl', 'N/A'],
['CH3BNH', 'CH4BN', 'N/A'],
['CH3NBH', 'CH4BN', 'N/A'],
['CH2BNH2', 'CH4BN', 'N/A'],
['CH3BeH', 'CH4Be', 'N/A'],
['CH3CdH', 'CH4Cd', 'N/A'],
['CH3CoH', 'CH4Co', 'N/A'],
['CH3GeH', 'CH4Ge', 'N/A'],
['CH3InH', 'CH4In', 'N/A'],
['CH3MgH', 'CH4Mg', 'N/A'],
['CH2NH2', 'CH4N', 'N/A'],
['CH3NH', 'CH4N', 'N/A'],
['CH3NH-', 'CH4N-', 'N/A'],
['t-CH3OSiH', 'CH4OSi', 'N/A'],
['c-CH3OSiH', 'CH4OSi', 'N/A'],
['CH3ZnH', 'CH4Zn', 'N/A'],
['CH5+', 'CH5+', 'N/A'],
['H2BSCH3', 'CH5BS', 'N/A'],
['CH3GaH2', 'CH5Ga', 'N/A'],
['GaNH2CH3+', 'CH5GaN+', 'N/A'],
['GaNH2CH3', 'CH5GaN', 'N/A'],
['HfCO', 'CHfO', 'N/A'],
['CI2', 'CI2', 'N/A'],
['CI2-', 'CI2-', 'N/A'],
['InCN', 'CInN', 'N/A'],
['InNC', 'CInN', 'N/A'],
['InCO', 'CInO', 'N/A'],
['IrCO+', 'CIrO+', 'N/A'],
['IrCO', 'CIrO', 'N/A'],
['IrCO-', 'CIrO-', 'N/A'],
['KrCUO', 'CKrOU', 'N/A'],
['MgNC', 'CMgN', 'N/A'],
['MnCO', 'CMnO', 'N/A'],
['MnCO-', 'CMnO-', 'N/A'],
['OMnCO+', 'CMnO2+', 'N/A'],
['OMnCO', 'CMnO2', 'N/A'],
['OMnCO-', 'CMnO2-', 'N/A'],
['MoCO+', 'CMoO+', 'N/A'],
['MoCO', 'CMoO', 'N/A'],
['OMoCO', 'CMoO2', 'N/A'],
['NCPO', 'CNOP', 'N/A'],
['O2CNO-', 'CNO3-', 'N/A'],
['PdCN-', 'CNPd-', 'N/A'],
['SiCN', 'CNSi', 'N/A'],
['SiNC', 'CNSi', 'N/A'],
['SnCN', 'CNSn', 'N/A'],
['SnCN-', 'CNSn-', 'N/A'],
['TlCN', 'CNTl', 'N/A'],
['TlNC', 'CNTl', 'N/A'],
['ZnCN', 'CNZn', 'N/A'],
['NCN-', 'CN2-', 'N/A'],
['CNN-', 'CN2-', 'N/A'],
['NOCN', 'CN2O', 'N/A'],
['CNNO', 'CN2O', 'N/A'],
['CNbO', 'CNbO', 'N/A'],
['NbCO', 'CNbO', 'N/A'],
['CNbO-', 'CNbO-', 'N/A'],
['ONbCO (I)', 'CNbO2', 'N/A'],
['ONbCO (II)', 'CNbO2', 'N/A'],
['NiCO+', 'CNiO+', 'N/A'],
['ONiCO', 'CNiO2', 'N/A'],
['ONiCO-', 'CNiO2-', 'N/A'],
['NiCO2-', 'CNiO2-', 'N/A'],
['NiCS2+', 'CNiS2+', 'N/A'],
['cyc-(NiSC)S', 'CNiS2', 'N/A'],
['NiCS2', 'CNiS2', 'N/A'],
['SNiCS', 'CNiS2', 'N/A'],
['OsCO+', 'COOs+', 'N/A'],
['OsCO', 'COOs', 'N/A'],
['OsCO-', 'COOs-', 'N/A'],
['PdCO+', 'COPd+', 'N/A'],
['PdCO-', 'COPd-', 'N/A'],
['PtCO+', 'COPt+', 'N/A'],
['PtCO-', 'COPt-', 'N/A'],
['ReCO+', 'CORe+', 'N/A'],
['ReCO', 'CORe', 'N/A'],
['ReCO-', 'CORe-', 'N/A'],
['RhCO+', 'CORh+', 'N/A'],
['RhCO', 'CORh', 'N/A'],
['RhCO-', 'CORh-', 'N/A'],
['RuCO+', 'CORu+', 'N/A'],
['RuCO', 'CORu', 'N/A'],
['RuCO-', 'CORu-', 'N/A'],
['OCS-', 'COS-', 'N/A'],
['ScCO+', 'COSc+', 'N/A'],
['ScCO-', 'COSc-', 'N/A'],
['SiCO-', 'COSi-', 'N/A'],
['SnCO-', 'COSn-', 'N/A'],
['TaCO', 'COTa', 'N/A'],
['CTaO-', 'COTa-', 'N/A'],
['TaCO-', 'COTa-', 'N/A'],
['OCTe', 'COTe', 'N/A'],
['ThCO', 'COTh', 'N/A'],
['CThO', 'COTh', 'N/A'],
['CThO-', 'COTh-', 'N/A'],
['TiCO+', 'COTi+', 'N/A'],
['TiCO-', 'COTi-', 'N/A'],
['CUO-', 'COU-', 'N/A'],
['UCO-', 'COU-', 'N/A'],
['XeCUO', 'COUXe', 'N/A'],
['VCO-', 'COV-', 'N/A'],
['WCO+', 'COW+', 'N/A'],
['WCO', 'COW', 'N/A'],
['WCO-', 'COW-', 'N/A'],
['YCO+', 'COY+', 'N/A'],
['YCO', 'COY', 'N/A'],
['ZrCO', 'COZr', 'N/A'],
['OOsCO', 'CO2Os', 'N/A'],
['OOsCO-', 'CO2Os-', 'N/A'],
['OReCO', 'CO2Re', 'N/A'],
['OReCO-', 'CO2Re-', 'N/A'],
['ORuCO', 'CO2Ru', 'N/A'],
['ORuCO-', 'CO2Ru-', 'N/A'],
['OScCO+', 'CO2Sc+', 'N/A'],
['OScOC+', 'CO2Sc+', 'N/A'],
['ScOCO+', 'CO2Sc+', 'N/A'],
['OScCO', 'CO2Sc', 'N/A'],
['cyc-(ScOC)O', 'CO2Sc', 'N/A'],
['cyc-(COSc)O', 'CO2Sc', 'N/A'],
['OTaCO', 'CO2Ta', 'N/A'],
['OTaCO-', 'CO2Ta-', 'N/A'],
['OThCO+', 'CO2Th+', 'N/A'],
['OThCO', 'CO2Th', 'N/A'],
['OTiCO+', 'CO2Ti+', 'N/A'],
['OTiOC+', 'CO2Ti+', 'N/A'],
['OTiCO', 'CO2Ti', 'N/A'],
['cyc-(COTi)O', 'CO2Ti', 'N/A'],
['OUCO+', 'CO2U+', 'N/A'],
['OVCO+', 'CO2V+', 'N/A'],
['OVOC+', 'CO2V+', 'N/A'],
['OVCO', 'CO2V', 'N/A'],
['cyc-(COV)O', 'CO2V', 'N/A'],
['OWCO', 'CO2W', 'N/A'],
['OYCO+', 'CO2Y+', 'N/A'],
['OYOC+', 'CO2Y+', 'N/A'],
['YOCO+', 'CO2Y+', 'N/A'],
['OYCO', 'CO2Y', 'N/A'],
['cyc-(YOC)O', 'CO2Y', 'N/A'],
['cyc-(COY)O', 'CO2Y', 'N/A'],
['OZnCO-', 'CO2Zn-', 'N/A'],
['OZrCO', 'CO2Zr', 'N/A'],
['O2OsCO', 'CO3Os', 'N/A'],
['O2ReCO', 'CO3Re', 'N/A'],
['O2RuCO', 'CO3Ru', 'N/A'],
['O2SiCO', 'CO3Si', 'N/A'],
['O2TiCO', 'CO3Ti', 'N/A'],
['O2UCO', 'CO3U', 'N/A'],
['SiCO4', 'CO4Si', 'N/A'],
['cyc-CS2', 'CS2', 'N/A'],
['Ag(CO)2+', 'C2AgO2+', 'N/A'],
['Ag(CO)2', 'C2AgO2', 'N/A'],
['AlCC', 'C2Al', 'N/A'],
['AlCC-', 'C2Al-', 'N/A'],
['Al(CO)2', 'C2AlO2', 'N/A'],
['Al(CO)2-', 'C2AlO2-', 'N/A'],
['AlCCAl-', 'C2Al2-', 'N/A'],
['cyc-Al2C2-', 'C2Al2-', 'N/A'],
['Al2(CO)2', 'C2Al2O2', 'N/A'],
['Al3C2', 'C2Al3', 'N/A'],
['Al3C2-', 'C2Al3-', 'N/A'],
['Au(CO)2+', 'C2AuO2+', 'N/A'],
['Au(CO)2', 'C2AuO2', 'N/A'],
['BCC-', 'C2B-', 'N/A'],
['FB(NCO)2', 'C2BFN2O2', 'N/A'],
['B(CO)2', 'C2BO2', 'N/A'],
['BCCB', 'C2B2', 'N/A'],
['OCBBCO', 'C2B2O2', 'N/A'],
['B4(CO)2', 'C2B4O2', 'N/A'],
['BrCNC', 'C2BrN', 'N/A'],
['ClCNC', 'C2ClN', 'N/A'],
['CoCC', 'C2Co', 'N/A'],
['CoCC-', 'C2Co-', 'N/A'],
['Co(CO)2+', 'C2CoO2+', 'N/A'],
['Co(CO)2', 'C2CoO2', 'N/A'],
['Co(CO)2-', 'C2CoO2-', 'N/A'],
['CrCC', 'C2Cr', 'N/A'],
['CrCC-', 'C2Cr-', 'N/A'],
['Cr(CO)2+', 'C2CrO2+', 'N/A'],
['Cr(CO)2', 'C2CrO2', 'N/A'],
['Cr(CO)2-', 'C2CrO2-', 'N/A'],
['Cu(CO)2+', 'C2CuO2+', 'N/A'],
['Cu(CO)2', 'C2CuO2', 'N/A'],
['Cu(CO)2-', 'C2CuO2-', 'N/A'],
['Cu(CS)2', 'C2CuS2', 'N/A'],
['FeCCD', 'C2DFe', 'N/A'],
['F2CCO', 'C2F2O', 'N/A'],
['FC(O)OC(O)F', 'C2F2O3', 'N/A'],
['FC(O)OOOC(O)F', 'C2F2O5', 'N/A'],
['t-CF3OCO', 'C2F3O2', 'N/A'],
['t,t,t-CF3OC(O)OO', 'C2F3O4', 'N/A'],
['t,t,c-CF3OC(O)OO', 'C2F3O4', 'N/A'],
['FeCC-', 'C2Fe-', 'N/A'],
['Fe(CO)2+', 'C2FeO2+', 'N/A'],
['Fe(CO)2', 'C2FeO2', 'N/A'],
['Fe(CO)2-', 'C2FeO2-', 'N/A'],
['Ga(CO)2', 'C2GaO2', 'N/A'],
['Ge(CO)2', 'C2GeO2', 'N/A'],
['HCC+', 'C2H+', 'N/A'],
['HBCC', 'C2HB', 'N/A'],
['HCCB', 'C2HB', 'N/A'],
['cyc-HBC2', 'C2HB', 'N/A'],
['BeCCH', 'C2HBe', 'N/A'],
['c-CHClCFO', 'C2HClFO', 'N/A'],
['c-CHFCFO', 'C2HF2O', 'N/A'],
['t-CHFCFO', 'C2HF2O', 'N/A'],
['HFC=C:-', 'C2HF-', 'N/A'],
['FeCCH-', 'C2HFe-', 'N/A'],
['LiCCH', 'C2HLi', 'N/A'],
['MgCCH', 'C2HMg', 'N/A'],
['HCNC', 'C2HN', 'N/A'],
['cyc-HC=NC:', 'C2HN', 'N/A'],
['HCCN-', 'C2HN-', 'N/A'],
['HCNC-', 'C2HN-', 'N/A'],
['O=C=C=NOH', 'C2HNO2', 'N/A'],
['PdCCNH', 'C2HNPd', 'N/A'],
['PdCCNH-', 'C2HNPd-', 'N/A'],
['HCSCN+', 'C2HNS+', 'N/A'],
['HNCCN+', 'C2HN2+', 'N/A'],
['NaCCH', 'C2HNa', 'N/A'],
['HCCO-', 'C2HO-', 'N/A'],
['PdCCH', 'C2HPd', 'N/A'],
['PdCCH-', 'C2HPd-', 'N/A'],
['PtCCH-', 'C2HPt-', 'N/A'],
['HCCSe', 'C2HSe', 'N/A'],
['YbCCH+', 'C2HYb+', 'N/A'],
['YbCCH', 'C2HYb', 'N/A'],
['HXeCC', 'C2HXe', 'N/A'],
['cyc-HC=CHAl', 'C2H2Al', 'N/A'],
['(C2H2)Al', 'C2H2Al', 'N/A'],
['Cl(H)AlCCH', 'C2H2AlCl', 'N/A'],
['cyc-HC=CHB', 'C2H2B', 'N/A'],
['cyc-HC=CBH', 'C2H2B', 'N/A'],
['HCCBH', 'C2H2B', 'N/A'],
['HBeCCH', 'C2H2Be', 'N/A'],
['t-CHClCHO', 'C2H2ClO', 'N/A'],
['c-CHClCHO', 'C2H2ClO', 'N/A'],
['HCrCCH', 'C2H2Cr', 'N/A'],
['cyc-C2H2Cr', 'C2H2Cr', 'N/A'],
['CH2=CF', 'C2H2F', 'N/A'],
['CH2CFO', 'C2H2FO', 'N/A'],
['(C2H2)Ga', 'C2H2Ga', 'N/A'],
['(C2H2)In', 'C2H2In', 'N/A'],
['HKrCCH', 'C2H2Kr', 'N/A'],
['HON=CHCNO', 'C2H2N2O2', 'N/A'],
['HON=CHNCO', 'C2H2N2O2', 'N/A'],
['cyc-H2COC:', 'C2H2O', 'N/A'],
['C2H2O2+', 'C2H2O2+', 'N/A'],
['cyc-C2H2Pd', 'C2H2Pd', 'N/A'],
['cyc-C2H2Pd2', 'C2H2Pd2', 'N/A'],
['PtCCH2', 'C2H2Pt', 'N/A'],
['HPtCCH', 'C2H2Pt', 'N/A'],
['cyc-C2H2Pt', 'C2H2Pt', 'N/A'],
['H2CCSe', 'C2H2Se', 'N/A'],
['HXeCCH', 'C2H2Xe', 'N/A'],
['HXeCCXeH', 'C2H2Xe2', 'N/A'],
['cyc-(CH)2BH', 'C2H3B', 'N/A'],
['H2BCCH', 'C2H3B', 'N/A'],
['HBCCH2', 'C2H3B', 'N/A'],
['CH2=CHBr+', 'C2H3Br+', 'N/A'],
['t,t-CH3C(O)OO', 'C2H3O3', 'N/A'],
['SiH2CCH', 'C2H3Si', 'N/A'],
['cyc-BHCHCH2', 'C2H4B', 'N/A'],
['H2BCCH2', 'C2H4B', 'N/A'],
['CH3CHO+', 'C2H4O+', 'N/A'],
['cyc-CHCHSiH2', 'C2H4Si', 'N/A'],
['cyc-CH2CH2Si', 'C2H4Si', 'N/A'],
['H2CCHSiH', 'C2H4Si', 'N/A'],
['H2CCSiH2', 'C2H4Si', 'N/A'],
['H3Si(cyc-CSiCH)', 'C2H4Si2', 'N/A'],
['HSiCCSiH3', 'C2H4Si2', 'N/A'],
['HCCSiSiH3', 'C2H4Si2', 'N/A'],
['H2Ti(C2H2)', 'C2H4Ti', 'N/A'],
['HTiC2H3', 'C2H4Ti', 'N/A'],
['H2BC2H3', 'C2H5B', 'N/A'],
['CH3B=CH2', 'C2H5B', 'N/A'],
['CaOC2H5', 'C2H5CaO', 'N/A'],
['CdC2H5', 'C2H5Cd', 'N/A'],
['C2H5IO2', 'C2H5IO2', 'N/A'],
['CH3CHOH+', 'C2H5O+', 'N/A'],
['CH3CH2O+', 'C2H5O+', 'N/A'],
['C2H5O-', 'C2H5O-', 'N/A'],
['C2H5O2-', 'C2H5O2-', 'N/A'],
['C2H5S+', 'C2H5S+', 'N/A'],
['ZnC2H5+', 'C2H5Zn+', 'N/A'],
['ZnC2H5', 'C2H5Zn', 'N/A'],
['CH3BNCH3', 'C2H6BN', 'N/A'],
['(CH3)2Ge=O', 'C2H6GeO', 'N/A'],
['(CH3)2N', 'C2H6N', 'N/A'],
['(CH3)2N-', 'C2H6N-', 'N/A'],
['CH3SiHOHCHO', 'C2H6O2Si', 'N/A'],
['C2H5ZnH', 'C2H6Zn', 'N/A'],
['C2H7+', 'C2H7+', 'N/A'],
['br-C2H7+', 'C2H7+', 'N/A'],
['H2BSC2H5', 'C2H7BS', 'N/A'],
['(CH3)2Si=NH', 'C2H7NSi', 'N/A'],
['CH3SiH2N=CH2', 'C2H7NSi', 'N/A'],
['(CH3)2GaH', 'C2H7Ga', 'N/A'],
['Hf(CO)2', 'C2HfO2', 'N/A'],
['OHfCCO', 'C2HfO2', 'N/A'],
['Hf(CO)2-', 'C2HfO2-', 'N/A'],
['In(CO)2', 'C2InO2', 'N/A'],
['Ir(CO)2+', 'C2IrO2+', 'N/A'],
['Ir(CO)2', 'C2IrO2', 'N/A'],
['Ir(CO)2-', 'C2IrO2-', 'N/A'],
['MnCC', 'C2Mn', 'N/A'],
['MnCC-', 'C2Mn-', 'N/A'],
['Mn(CO)2', 'C2MnO2', 'N/A'],
['Mn(CO)2-', 'C2MnO2-', 'N/A'],
['Mo(CO)2+', 'C2MoO2+', 'N/A'],
['Mo(CO)2', 'C2MoO2', 'N/A'],
['Mo(CO)2-', 'C2MoO2-', 'N/A'],
['CCN+', 'C2N+', 'N/A'],
['OCNNCO', 'C2N2O2', 'N/A'],
['Sn(CN)2', 'C2N2Sn', 'N/A'],
['Sn(CN)2-', 'C2N2Sn-', 'N/A'],
['NbCC', 'C2Nb', 'N/A'],
['NbCC-', 'C2Nb-', 'N/A'],
['Nb(CO)2', 'C2NbO2', 'N/A'],
['ONbCCO', 'C2NbO2', 'N/A'],
['Nb(CO)2-', 'C2NbO2-', 'N/A'],
['Nb3C2+', 'C2Nb3+', 'N/A'],
['Nb3C2', 'C2Nb3', 'N/A'],
['Ni(CO)2+', 'C2NiO2+', 'N/A'],
['Ni(CO)2', 'C2NiO2', 'N/A'],
['Ni(CO)2-', 'C2NiO2-', 'N/A'],
['OCCS', 'C2OS', 'N/A'],
['Os(CO)2', 'C2O2Os', 'N/A'],
['Os(CO)2-', 'C2O2Os-', 'N/A'],
['Pd(CO)2+', 'C2O2Pd+', 'N/A'],
['Pd(CO)2', 'C2O2Pd', 'N/A'],
['Pd(CO)2-', 'C2O2Pd-', 'N/A'],
['Pt(CO)2+', 'C2O2Pt+', 'N/A'],
['Pt(CO)2', 'C2O2Pt', 'N/A'],
['Pt(CO)2-', 'C2O2Pt-', 'N/A'],
['Re(CO)2', 'C2O2Re', 'N/A'],
['Re(CO)2-', 'C2O2Re-', 'N/A'],
['Rh(CO)2+', 'C2O2Rh+', 'N/A'],
['Rh(CO)2', 'C2O2Rh', 'N/A'],
['Rh(CO)2-', 'C2O2Rh-', 'N/A'],
['Ru(CO)2', 'C2O2Ru', 'N/A'],
['Ru(CO)2-', 'C2O2Ru-', 'N/A'],
['Sc(CO)2+', 'C2O2Sc+', 'N/A'],
['Sc(CO)2', 'C2O2Sc', 'N/A'],
['Sn(CO)2', 'C2O2Sn', 'N/A'],
['Ta(CO)2', 'C2O2Ta', 'N/A'],
['OTaCCO', 'C2O2Ta', 'N/A'],
['Ta(CO)2-', 'C2O2Ta-', 'N/A'],
['Th(CO)2', 'C2O2Th', 'N/A'],
['OThCCO', 'C2O2Th', 'N/A'],
['Th(CO)2-', 'C2O2Th-', 'N/A'],
['Ti(CO)2', 'C2O2Ti', 'N/A'],
['Ti(CO)2-', 'C2O2Ti-', 'N/A'],
['U(CO)2', 'C2O2U', 'N/A'],
['OUCCO', 'C2O2U', 'N/A'],
['U(CO)2-', 'C2O2U-', 'N/A'],
['V(CO)2', 'C2O2V', 'N/A'],
['V(CO)2-', 'C2O2V-', 'N/A'],
['W(CO)2', 'C2O2W', 'N/A'],
['W(CO)2-', 'C2O2W-', 'N/A'],
['Zr(CO)2', 'C2O2Zr', 'N/A'],
['OZrCCO', 'C2O2Zr', 'N/A'],
['Zr(CO)2-', 'C2O2Zr-', 'N/A'],
['C2O3-', 'C2O3-', 'N/A'],
['O2CCO2+', 'C2O4+', 'N/A'],
['O2CCO2-', 'C2O4-', 'N/A'],
['CCS', 'C2S', 'N/A'],
['CCS-', 'C2S-', 'N/A'],
['SCCS-', 'C2S2-', 'N/A'],
['S2CCS2+', 'C2S4+', 'N/A'],
['ScCC', 'C2Sc', 'N/A'],
['ScCC-', 'C2Sc-', 'N/A'],
['Si3C2', 'C2Si3', 'N/A'],
['TiCC', 'C2Ti', 'N/A'],
['TiCC-', 'C2Ti-', 'N/A'],
['VCC', 'C2V', 'N/A'],
['VCC-', 'C2V-', 'N/A'],
['XeC2', 'C2Xe', 'N/A'],
['Y3C2+', 'C2Y3+', 'N/A'],
['Y3C2', 'C2Y3', 'N/A'],
['BCCC', 'C3B', 'N/A'],
['cyc-CoC3', 'C3Co', 'N/A'],
['cyc-CoC3-', 'C3Co-', 'N/A'],
['cyc-CrC3', 'C3Cr', 'N/A'],
['cyc-CrC3-', 'C3Cr-', 'N/A'],
['Cr(CO)3', 'C3CrO3', 'N/A'],
['Cr(CO)3-', 'C3CrO3-', 'N/A'],
['cyc-FeC3-', 'C3Fe-', 'N/A'],
['GeCCCSi', 'C3GeSi', 'N/A'],
['GeCCCGe', 'C3Ge2', 'N/A'],
['HC3-', 'C3H-', 'N/A'],
['FeC=C=CH', 'C3HFe', 'N/A'],
['FeCCCH', 'C3HFe', 'N/A'],
['FeC=C=CH-', 'C3HFe-', 'N/A'],
['FeCCCH-', 'C3HFe-', 'N/A'],
['HNCCC', 'C3HN', 'N/A'],
['HCNCC', 'C3HN', 'N/A'],
['NCCH=C=O', 'C3HNO', 'N/A'],
['cyc-(HC=CHN=C=N)', 'C3H2N2', 'N/A'],
['(cyc-HC=CHN)CN', 'C3H2N2', 'N/A'],
['H2C=C=NCN', 'C3H2N2', 'N/A'],
['cyc-(C=NCHNCH)', 'C3H2N2', 'N/A'],
['HC-N=CHCN', 'C3H2N2', 'N/A'],
['cyc-(HC=NCH)CN', 'C3H2N2', 'N/A'],
['HNC=C=CHCN', 'C3H2N2', 'N/A'],
['HOCH=C=C:', 'C3H2O', 'N/A'],
['t-HCCCHOO', 'C3H2O2', 'N/A'],
['c-HCCCHOO', 'C3H2O2', 'N/A'],
['HCC(cyc-CHOO)', 'C3H2O2', 'N/A'],
['cyc-(HOC=COHC)=O', 'C3H2O3', 'N/A'],
['cyc-C3H3+', 'C3H3+', 'N/A'],
['CH3CCCa', 'C3H3Ca', 'N/A'],
['H2C=(cyc-CN=CH)', 'C3H3N', 'N/A'],
['CH3CCSr', 'C3H3Sr', 'N/A'],
['CH3CCH+', 'C3H4+', 'N/A'],
['H2CCHCH:', 'C3H4', 'N/A'],
['HFeCH=C=CH2', 'C3H4Fe', 'N/A'],
['HCCCH2FeH', 'C3H4Fe', 'N/A'],
['HFeCCCH3', 'C3H4Fe', 'N/A'],
['CH3FeCCH', 'C3H4Fe', 'N/A'],
['CH3C(=NO)CHO', 'C3H4NO2', 'N/A'],
['H3C(cyc-CSiCH)', 'C3H4Si', 'N/A'],
['cyc-CH2CHCHSi', 'C3H4Si', 'N/A'],
['H3CCHCSi', 'C3H4Si', 'N/A'],
['H2CCHCHSi', 'C3H4Si', 'N/A'],
['H3CCCSiH', 'C3H4Si', 'N/A'],
['H3CSiCCH', 'C3H4Si', 'N/A'],
['H2CCCHSiH', 'C3H4Si', 'N/A'],
['H2CSiHCCH', 'C3H4Si', 'N/A'],
['CH2CHCH2-', 'C3H5-', 'N/A'],
['t-1-C3H5Br+', 'C3H5Br+', 'N/A'],
['c-1-C3H5Br+', 'C3H5Br+', 'N/A'],
['2-C3H5Br+', 'C3H5Br+', 'N/A'],
['CH2COCH3', 'C3H5O', 'N/A'],
['CH3CHCHO', 'C3H5O', 'N/A'],
['C3H6+', 'C3H6+', 'N/A'],
['t-1-C3H7O', 'C3H7O', 'N/A'],
['(CH3)2CHO-', 'C3H7O-', 'N/A'],
['(CH3)2Ge=CH2', 'C3H8Ge', 'N/A'],
['cyc-MnC3', 'C3Mn', 'N/A'],
['cyc-MnC3-', 'C3Mn-', 'N/A'],
['Mo(CO)3-', 'C3MoO3-', 'N/A'],
['NCCCS', 'C3NS', 'N/A'],
['NCCCN+', 'C3N2+', 'N/A'],
['C(CN)(NC)', 'C3N2', 'N/A'],
['NC(cyc-C=NC:)', 'C3N2', 'N/A'],
[':C=N(cyc-C=NC:)', 'C3N2', 'N/A'],
['C(NC)2', 'C3N2', 'N/A'],
['C(NCN)2', 'C3N4', 'N/A'],
['(N)3(cyc-C3N3)', 'C3N6', 'N/A'],
['(N)2(cyc-C3N3)N3', 'C3N8', 'N/A'],
['(N3)2(cyc-C3N3)N', 'C3N10', 'N/A'],
['cyc-NbC3', 'C3Nb', 'N/A'],
['cyc-NbC3-', 'C3Nb-', 'N/A'],
['cyc-NiC3', 'C3Ni', 'N/A'],
['cyc-NiC3-', 'C3Ni-', 'N/A'],
['W(CO)3', 'C3O3W', 'N/A'],
['W(CO)3-', 'C3O3W-', 'N/A'],
['cyc-ScC3', 'C3Sc', 'N/A'],
['cyc-ScC3-', 'C3Sc-', 'N/A'],
['SiC3', 'C3Si', 'N/A'],
['SiC3-', 'C3Si-', 'N/A'],
['SiCCCSi-', 'C3Si2-', 'N/A'],
['cyc-TiC3', 'C3Ti', 'N/A'],
['cyc-TiC3-', 'C3Ti-', 'N/A'],
['cyc-VC3', 'C3V', 'N/A'],
['cyc-VC3-', 'C3V-', 'N/A'],
['C3Xe', 'C3Xe', 'N/A'],
['F2C=C=CFCF:', 'C4F4', 'N/A'],
['F2C=(cyc-C3F2)', 'C4F4', 'N/A'],
['FeC4-', 'C4Fe-', 'N/A'],
['C4H-', 'C4H-', 'N/A'],
['FeCCCCH-', 'C4HFe-', 'N/A'],
['HCCCCS', 'C4HS', 'N/A'],
['F2C=(cyc-C3H2)', 'C4H2F2', 'N/A'],
['F2C=CHCCH', 'C4H2F2', 'N/A'],
['F2C=C=C=CH2', 'C4H2F2', 'N/A'],
['HKrC4H', 'C4H2Kr', 'N/A'],
['cyc-(N=CHN=CHC)=CO', 'C4H2N2O', 'N/A'],
['HSiCCCCH', 'C4H2Si', 'N/A'],
['Si(CCH)2', 'C4H2Si', 'N/A'],
['HXeC4H', 'C4H2Xe', 'N/A'],
['H2C=C=CHCH:', 'C4H4', 'N/A'],
['C2H3CH=C:-', 'C4H4-', 'N/A'],
['Cd(C4H4N)', 'C4H4CdN', 'N/A'],
['Mg(C4H4N)', 'C4H4MgN', 'N/A'],
['Zn(C4H4N)', 'C4H4NZn', 'N/A'],
['H2CCHC(CH3):', 'C4H6', 'N/A'],
['C(CH2)3', 'C4H6', 'N/A'],
['C(CH2)3-', 'C4H6-', 'N/A'],
['cyc-C4H4GeH2', 'C4H6Ge', 'N/A'],
['cyc-C4H6Ge:', 'C4H6Ge', 'N/A'],
['cyc-C4H5GeH (1,3)', 'C4H6Ge', 'N/A'],
['cyc-C4H5GeH (1,4)', 'C4H6Ge', 'N/A'],
['CH3CHCOCH3', 'C4H7O', 'N/A'],
['(CH3)2CCHO', 'C4H7O', 'N/A'],
['t-CH3CH=CHCH3+', 'C4H8+', 'N/A'],
['c-CH3CH=CHCH3+', 'C4H8+', 'N/A'],
['g1t2-1-C4H9O', 'C4H9O', 'N/A'],
['t1t2-1-C4H9O', 'C4H9O', 'N/A'],
['t1g2-1-C4H9O', 'C4H9O', 'N/A'],
['2-C4H9O (I)', 'C4H9O', 'N/A'],
['2-C4H9O (II)', 'C4H9O', 'N/A'],
['(CH3)3CO', 'C4H9O', 'N/A'],
['(CH3)3CO-', 'C4H9O-', 'N/A'],
['t-C4H9O2-', 'C4H9O2-', 'N/A'],
['CCCNCN', 'C4N2', 'N/A'],
['C4O-', 'C4O-', 'N/A'],
['C4S-', 'C4S-', 'N/A'],
['C4Si', 'C4Si', 'N/A'],
['SiC4Si', 'C4Si2', 'N/A'],
['SiC4Si-', 'C4Si2-', 'N/A'],
['TiC4', 'C4Ti', 'N/A'],
['TiC4-', 'C4Ti-', 'N/A'],
['cyc-C5Br4O-1-O', 'C5Br4O2', 'N/A'],
['C5Cl+', 'C5Cl+', 'N/A'],
['C5Cl', 'C5Cl', 'N/A'],
['C5H', 'C5H', 'N/A'],
['3,5-cyc-C5H3N', 'C5H3N', 'N/A'],
['MgC5H5', 'C5H5Mg', 'N/A'],
['ZnC5H5', 'C5H5Zn', 'N/A'],
['(cyc-C5H4N)NH2+', 'C5H6N2+', 'N/A'],
['(CH3)2CCOCH3', 'C5H9O', 'N/A'],
['C5N', 'C5N', 'N/A'],
['C5N-', 'C5N-', 'N/A'],
['C5N2', 'C5N2', 'N/A'],
['C5N3+', 'C5N3+', 'N/A'],
['C5O', 'C5O', 'N/A'],
['C5S', 'C5S', 'N/A'],
['TiC5', 'C5Ti', 'N/A'],
['TiC5-', 'C5Ti-', 'N/A'],
['C5Xe', 'C5Xe', 'N/A'],
['C6+', 'C6+', 'N/A'],
['cyc-C6+', 'C6+', 'N/A'],
['cyc-C6', 'C6', 'N/A'],
['C6Cl+', 'C6Cl+', 'N/A'],
['C6Cl', 'C6Cl', 'N/A'],
['o-C6F4', 'C6F4', 'N/A'],
['m-C6F4', 'C6F4', 'N/A'],
['p-C6F4', 'C6F4', 'N/A'],
['FCCCF=CFCCF', 'C6F4', 'N/A'],
['m-C6F4I', 'C6F4I', 'N/A'],
['p-C6F4I', 'C6F4I', 'N/A'],
['bicyc-C6F5N', 'C6F5N', 'N/A'],
['C6H-', 'C6H-', 'N/A'],
['HC6N', 'C6HN', 'N/A'],
['HC6S', 'C6HS', 'N/A'],
['O=C6H2=O', 'C6H2O2', 'N/A'],
['O=C6H2=O-', 'C6H2O2-', 'N/A'],
['3,5-C6H3F', 'C6H3F', 'N/A'],
['bicyc-C6H3F2N', 'C6H3F2N', 'N/A'],
['HC4CH=CH2+', 'C6H4+', 'N/A'],
['p-C6H4', 'C6H4', 'N/A'],
['m-C6H4-', 'C6H4-', 'N/A'],
['p-C6H4-', 'C6H4-', 'N/A'],
['C6H5Br+', 'C6H5Br+', 'N/A'],
['C6H5I+', 'C6H5I+', 'N/A'],
['3-CH(cyc-C5H4N)', 'C6H5N', 'N/A'],
['C6H5NN+', 'C6H5N2+', 'N/A'],
['p-C6H4ClNH2+', 'C6H6ClN+', 'N/A'],
['o-C6H4FNH2+', 'C6H6FN+', 'N/A'],
['p-C6H4FNH2+', 'C6H6FN+', 'N/A'],
['o-C6H4(OH)2+', 'C6H6O2+', 'N/A'],
['m-C6H4(OH)2+ (Cs)', 'C6H6O2+', 'N/A'],
['m-C6H4(OH)2+ (C2v)', 'C6H6O2+', 'N/A'],
['p-C6H4(OH)2+ (C2v)', 'C6H6O2+', 'N/A'],
['CaC5H4CH3', 'C6H7Ca', 'N/A'],
['CdC5H4CH3', 'C6H7Cd', 'N/A'],
['MgC5H4CH3', 'C6H7Mg', 'N/A'],
['ZnC5H4CH3', 'C6H7Zn', 'N/A'],
['(CH3)3CCH=C:', 'C6H10', 'N/A'],
['(CH3)3CCH=C-', 'C6H10-', 'N/A'],
['CN(CC)2CN', 'C6N2', 'N/A'],
['C6N3+', 'C6N3+', 'N/A'],
['C6N4+', 'C6N4+', 'N/A'],
['C6N4-', 'C6N4-', 'N/A'],
['C6S', 'C6S', 'N/A'],
['C6S-', 'C6S-', 'N/A'],
['1,2-C6F4>CO', 'C7F4O', 'N/A'],
['GeC7', 'C7Ge', 'N/A'],
['C7H', 'C7H', 'N/A'],
['C6F5CH2', 'C7H2F5', 'N/A'],
['(cyc-H2CC=C)C4H', 'C7H3', 'N/A'],
['(cyc-C5H4)CCO', 'C7H4O', 'N/A'],
['C6H5CCl2', 'C7H5Cl2', 'N/A'],
['(2,6-F2C6H3)CH2', 'C7H5F2', 'N/A'],
['C6H5CO+', 'C7H5O+', 'N/A'],
['3,5-C6H3CH3', 'C7H6', 'N/A'],
['C6H5CHBr', 'C7H6Br', 'N/A'],
['(2-BrC6H4)CH2', 'C7H6Br', 'N/A'],
['(3-BrC6H4)CH2', 'C7H6Br', 'N/A'],
['(4-BrC6H4)CH2', 'C7H6Br', 'N/A'],
['(2-BrC6H4)CH2-', 'C7H6Br-', 'N/A'],
['(3-BrC6H4)CH2-', 'C7H6Br-', 'N/A'],
['(4-BrC6H4)CH2-', 'C7H6Br-', 'N/A'],
['C6H5CHCl', 'C7H6Cl', 'N/A'],
['(2-ClC6H4)CH2', 'C7H6Cl', 'N/A'],
['(3-ClC6H4)CH2', 'C7H6Cl', 'N/A'],
['(2-ClC6H4)CH2-', 'C7H6Cl-', 'N/A'],
...]
In [3]:
DataPaths().raw()
Out[3]:
PosixPath('/home/topolo/PropD/Propulsion/T1000/data/raw')
In [4]:
list(DataPaths().raw().glob('**/*'))
Out[4]:
[PosixPath('/home/topolo/PropD/Propulsion/T1000/data/raw/species.zip'),
PosixPath('/home/topolo/PropD/Propulsion/T1000/data/raw/species.txt')]
In [9]:
species_txt_path = \
next(path for path in list(DataPaths().raw().glob('**/*')) if "species" in str(path) and ".txt" in str(path))
In [16]:
f = open(species_txt_path, 'r', newline='')
csv_reader = csv.reader(f, delimiter="\t")
In [17]:
csv_as_list = list(csv_reader)
f.close()
In [22]:
for row in csv_as_list:
if len(row) != 3:
print(len(row))
In [3]:
species_list_columns = species_list.ScrapeWebpage.species_list_columns()
In [4]:
species_list_columns
Out[4]:
['Species name', 'Species formula', 'CAS registry number (if known)']
In [5]:
ready_data = species_list.ReadAndClean.to_database_ready_data(species_list_columns)
In [7]:
ready_data[:5]
Out[7]:
[OrderedDict([('Species name', 'Electron'),
('Species formula', 'e-'),
('CAS registry number (if known)', None)]),
OrderedDict([('Species name', 'Iron(2) oxide anion'),
('Species formula', 'FeO-'),
('CAS registry number (if known)', None)]),
OrderedDict([('Species name', 'AsF3..Cl anion'),
('Species formula', 'AsClF3-'),
('CAS registry number (if known)', None)]),
OrderedDict([('Species name', 'AgH2-'),
('Species formula', 'H2Ag-'),
('CAS registry number (if known)', None)]),
OrderedDict([('Species name', 'HAg(H2)'),
('Species formula', 'H3Ag'),
('CAS registry number (if known)', None)])]
In [3]:
NISTChemistryWebbookPaths.species_list()
Out[3]:
'https://webbook.nist.gov/chemistry/download/'
In [4]:
page = requests.get(NISTChemistryWebbookPaths.species_list())
In [5]:
# Use Python's built-in html.parser
soup = BeautifulSoup(page.text, 'html.parser')
In [13]:
soup.find(id="main").find('ul').find_all('li')[0].text
Out[13]:
'Species name'
In [ ]:
Content source: ernestyalumni/Propulsion
Similar notebooks: