dwca-python/csv.py at master · godfoder/dwca-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
#!/bin/python

importzipfile
fromlxmlimportetree
importoptparse
importos
importpprint
importsys
importdwca
importHTMLParser

parser=optparse.OptionParser()
parser.add_option("-f", "--file", help="DWC-a file to read")
parser.add_option("-q", "--quiet",
action="store_false", dest="verbose", default=True,
help="don't print status messages to stdout")

(options, args) =parser.parse_args()

defstripBlanks(rec):
nrec= {}
forkeyinrec.keys():
iflen(rec[key]) !=0:
nrec[key.split('/')[-1]] =rec[key]
returnnrec

ifoptions.file==None:
parser.print_help()
sys.exit(1)
else:
dwcaobj=dwca.Dwca(options.file)
specimens= {}
forrecordindwcaobj.core:
rec=stripBlanks(record)
if'verbatimLongitude'inrecand'verbatimLatitude'inrecand'nomenclaturalStatus'inrecandrec['nomenclaturalStatus'] !="not accepted":
specimens[record["id"]] =rec
fordwcrfindwcaobj.extensions:
forrecordindwcrf:
ifrecord["coreid"] inspecimens:
ifdwcrf.rowtype=="http://rs.tdwg.org/ac/terms/multimedia":
specimens[record["coreid"]]["iDigBioImageUrl"] =HTMLParser.HTMLParser().unescape(record["http://rs.tdwg.org/ac/terms/bestQualityAccessURI"])

keys_c= {}
forspecinspecimens:
forkinspecimens[spec].keys():
ifknotinkeys_c:
keys_c[k] =1
else:
keys_c[k] +=1
keys= []
forkinkeys_c:
ifkeys_c[k] >50000:
keys.append(k)

withopen("dump.csv","w") asof:
of.write("\""+"\",\"".join(keys) +"\"\n")
forspecinspecimens:
rec= []
forkinkeys:
ifkinspecimens[spec]:
rec.append(specimens[spec][k])
else:
rec.append("")
try:
of.write("\""+"\",\"".join(rec) +"\"\n")
exceptUnicodeDecodeError:
pass