if "debug" in sys.argv:
debug_arg=True
else: debug_arg=False
title=False
creator=False
metadata={}
# f = GzipFile(fileobj=urlopen(sys.argv[1]))
# f = open(sys.argv[1])
pars=[]
for par in abbyystreams.abbyytext(f, header=htmlhead, footer=htmlfoot,
format=xmlformat,blockfn=htmlblock,
pagefn=htmlpage,picture=htmlimg,
table=htmltable,escapefn=cgi.escape,
linefn=linehandler,floatfn=floatblock,
debug=debug_arg):
pars.append(par)
topclass=False
topscore=-1
for x in classhist:
if not (topclass and (classhist[x]<topscore)):
topclass=x
topscore=classhist[x]
paraprefix="<span class='%s'>"%topclass
paracount=1
print "<?xml version='1.0' encoding='utf-8' ?>"
print "<!DOCTYPE html>"
content_label=False
format_arg=False
layout_arg=False
page_arg=False
block_arg=False
if (os.path.exists(sys.argv[1])):
if sys.argv[1].endswith('.gz'):
f=gzip.open(sys.argv[1])
else: f=open(sys.argv[1])
elif (sys.argv[1].startswith('http')):
if sys.argv[1].endswith('.gz'):
f=GzipFile(fileobj=urlopen(sys.argv[1]))
else: f=urlopen(sys.argv[1])
else:
urlstream=urlopen("http://www.archive.org/download/%s/%s_abbyy.gz"%
(sys.argv[1],sys.argv[1]))
zipdata=urlstream.read()
f=GzipFile(fileobj=StringIO.StringIO(zipdata))
# f = GzipFile(fileobj=urlopen(sys.argv[1]))
# f = open(sys.argv[1])
for par in abbyystreams.abbyytext(f, header=header_arg, footer=footer_arg,
format=format_arg,layout=layout_arg,
blockfn=block_arg,pagefn=page_arg,
debug=debug_arg):
if content_label:
print "Content:",par.encode('utf-8')
else: print par.encode('utf-8')
