In [1]:

    

import pandas as pd


    

In [2]:

    

theURL = 'ftp://newftp.epa.gov/EPADataCommons/ORD/NHDPlusLandscapeAttributes/StreamCat/Documentation/VariableList-QuickReference.html'


    

In [12]:

    

dfList = pd.read_html(theURL,skiprows=6)
dfRaw = dfList[0]


    

In [13]:

    

dfRaw.head()


    

    
Out[13]:






  

    

      

      
0
      
1
      
2
      
3
    
  
  

    

      
0
      
1.0
      
CatAreaSqKm
      
Area of local NHDPlus catchment (square km)
      
All tables
    
    

      
1
      
2.0
      
WsAreaSqKm
      
Watershed area (square km) at NHDPlus stream s...
      
All tables
    
    

      
2
      
3.0
      
CatAreaSqKmRp100
      
Area of local NHDPlus catchments (square km)  ...
      
All RipBuf100  tables
    
    

      
3
      
4.0
      
WsAreaSqKmRp100
      
Watershed area (square km)   within a 100-m bu...
      
All RipBuf100  tables
    
    

      
4
      
5.0
      
CatPctFull
      
% of the catchment that is covered by the land...
      
All tables
    
  

In [38]:

    

dfRaw.columns = ['Index','Variable','Description','Table']
dfClean = dfRaw.drop('Index',axis=1)
dfClean.dropna(inplace=True)
dfClean.head()


    

    
Out[38]:






  

    

      

      
Variable
      
Description
      
Table
    
  
  

    

      
0
      
CatAreaSqKm
      
Area of local NHDPlus catchment (square km)
      
All tables
    
    

      
1
      
WsAreaSqKm
      
Watershed area (square km) at NHDPlus stream s...
      
All tables
    
    

      
2
      
CatAreaSqKmRp100
      
Area of local NHDPlus catchments (square km)  ...
      
All RipBuf100  tables
    
    

      
3
      
WsAreaSqKmRp100
      
Watershed area (square km)   within a 100-m bu...
      
All RipBuf100  tables
    
    

      
4
      
CatPctFull
      
% of the catchment that is covered by the land...
      
All tables
    
  

In [39]:

    

#List the variables includeed in the NLCD2011_<StateID>.csv
dfClean[dfClean['Table'].str.contains("NLCD2006")]  #['Variable']


    

    
Out[39]:






  

    

      

      
Variable
      
Description
      
Table
    
  
  

    

      
12
      
PctUrbHi2006Cat
      
% of catchment area classified as developed, h...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
13
      
PctUrbHi2006Ws
      
% of watershed area classified as developed, h...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
14
      
PctUrbHi2006CatRp100
      
% of catchment area classified as developed, h...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
15
      
PctUrbHi2006WsRp100
      
% of watershed area classified as developed, h...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
16
      
PctUrbMd2006Cat
      
% of catchment area classified as developed, m...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
17
      
PctUrbMd2006Ws
      
% of watershed area classified as developed, m...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
18
      
PctUrbMd2006CatRp100
      
% of catchment area classified as developed, m...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
19
      
PctUrbMd2006WsRp100
      
% of watershed area classified as developed, m...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
20
      
PctUrbLo2006Cat
      
% of catchment area classified as developed, l...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
21
      
PctUrbLo2006Ws
      
% of watershed area classified as developed, l...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
22
      
PctUrbLo2006CatRp100
      
% of catchment area classified as developed, l...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
23
      
PctUrbLo2006WsRp100
      
% of watershed area classified as developed, l...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
24
      
PctUrbOp2006Cat
      
% of catchment area classified as developed, o...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
25
      
PctUrbOp2006Ws
      
% of watershed area classified as developed, o...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
26
      
PctUrbOp2006CatRp100
      
% of catchment area classified as developed, o...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
27
      
PctUrbOp2006WsRp100
      
% of watershed area classified as developed, o...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
28
      
PctCrop2006Cat
      
% of catchment area classified as crop land us...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
29
      
PctCrop2006Ws
      
% of watershed area classified as crop land us...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
30
      
PctCrop2006CatRp100
      
% of catchment area classified as crop land us...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
31
      
PctCrop2006WsRp100
      
% of watershed area classified as crop land us...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
32
      
PctHay2006Cat
      
% of catchment area classified as hay land use...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
33
      
PctHay2006Ws
      
% of watershed area classified as hay land use...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
34
      
PctHay2006CatRp100
      
% of catchment area classified as hay land use...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
35
      
PctHay2006WsRp100
      
% of watershed area classified as hay land use...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
36
      
PctDecid2006Cat
      
% of catchment area classified as deciduous fo...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
37
      
PctDecid2006Ws
      
% of watershed area classified as deciduous fo...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
38
      
PctDecid2006CatRp100
      
% of catchment area classified as deciduous fo...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
39
      
PctDecid2006WsRp100
      
% of watershed area classified as deciduous fo...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
40
      
PctConif2006Cat
      
% of catchment area classified as evergreen fo...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
41
      
PctConif2006Ws
      
% of watershed area classified as evergreen fo...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
...
      
...
      
...
      
...
    
    

      
46
      
PctMxFst2006CatRp100
      
% of catchment area classified as mixed decidu...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
47
      
PctMxFst2006WsRp100
      
% of watershed area classified as mixed decidu...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
48
      
PctBl2006Cat
      
% of catchment area classified as barren land ...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
49
      
PctBl2006Ws
      
% of watershed area classified as barren land ...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
50
      
PctBl2006CatRp100
      
% of catchment area classified as barren land ...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
51
      
PctBl2006WsRp100
      
% of watershed area classified as barren land ...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
52
      
PctOw2006Cat
      
% of catchment area classified as open water l...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
53
      
PctOw2006Ws
      
% of watershed area classified as open water l...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
54
      
PctOw2006CatRp100
      
% of catchment area classified as open water l...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
55
      
PctOw2006WsRp100
      
% of watershed area classified as open water l...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
56
      
PctIce2006Cat
      
% of catchment area classified as ice/snow lan...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
57
      
PctIce2006Ws
      
% of watershed area classified as ice/snow lan...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
58
      
PctIce2006CatRp100
      
% of catchment area classified as ice/snow lan...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
59
      
PctIce2006WsRp100
      
% of watershed area classified as ice/snow lan...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
60
      
PctHbWet2006Cat
      
% of catchment area classified as herbaceous w...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
61
      
PctHbWet2006Ws
      
% of watershed area classified as herbaceous w...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
62
      
PctHbWet2006CatRp100
      
% of catchment area classified as herbaceous w...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
63
      
PctHbWet2006WsRp100
      
% of watershed area classified as herbaceous w...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
64
      
PctWdWet2006Cat
      
% of catchment area classified as woody wetlan...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
65
      
PctWdWet2006Ws
      
% of watershed area classified as woody wetlan...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
66
      
PctWdWet2006CatRp100
      
% of catchment area classified as woody wetlan...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
67
      
PctWdWet2006WsRp100
      
% of watershed area classified as woody wetlan...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
68
      
PctShrb2006Cat
      
% of catchment area classified as shrub/scrub ...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
69
      
PctShrb2006Ws
      
% of watershed area classified as shrub/scrub ...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
70
      
PctShrb2006CatRp100
      
% of catchment area classified as shrub/scrub ...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
71
      
PctShrb2006WsRp100
      
% of watershed area classified as shrub/scrub ...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
72
      
PctGrs2006Cat
      
% of catchment area classified as grassland/he...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
73
      
PctGrs2006Ws
      
% of watershed area classified as grassland/he...
      
NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
    
    

      
74
      
PctGrs2006CatRp100
      
% of catchment area classified as grassland/he...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
    

      
75
      
PctGrs2006WsRp100
      
% of watershed area classified as grassland/he...
      
NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
    
  

64 rows × 3 columns

In [36]:

    

dfClean.Table


    

    
Out[36]:





0                                             All tables
1                                             All tables
2                                  All RipBuf100  tables
3                                  All RipBuf100  tables
4                                             All tables
5                                             All tables
6                                  All RipBuf100  tables
7                                  All RipBuf100  tables
8      CanalDensity_<RegionID>.csv,  CanalDensity_<St...
9      CanalDensity_<RegionID>.csv,  CanalDensity_<St...
10     Elevation_<RegionID>.csv, Elevation_<StateID>.csv
11     Elevation_<RegionID>.csv, Elevation_<StateID>.csv
12       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
13       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
14     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
15     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
16       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
17       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
18     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
19     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
20       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
21       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
22     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
23     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
24       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
25       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
26     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
27     NLCD2006RipBuf100_<RegionID>.csv,  NLCD2006Rip...
28       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
29       NLCD2006_<RegionID>.csv, NLCD2006_<StateID>.csv
                             ...                        
470    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
471      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
472      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
473    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
474    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
475      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
476      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
477    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
478    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
479      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
480      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
481    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
482    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
483      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
484      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
485    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
486    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
487      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
488      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
489    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
490    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
491      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
492      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
493    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
494    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
495      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
496      NLCD2001_<RegionID>.csv, NLCD2001_<StateID>.csv
497    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
498    NLCD2001RipBuf100_<RegionID>.csv,  NLCD2001Rip...
499                                                  NaN
Name: Table, dtype: object