def set_charset(self, charset):
"""Changes the current charset and codec."""
if self.debug:
print >>sys.stderr, 'set_charset: %s' % charset
self.codec = getcodec(charset)
self.handler.set_charset(charset)
return
self.codec = codec
return
def close(self): pass
def feed(self, s):
sys.stdout.write(s.encode(self.codec, 'replace'))
sys.stdout.flush()
return
def usage():
print 'usage: html2txt.py [-c charset_in] [-C charset_out] files ...'
sys.exit(2)
try:
(opts, args) = getopt.getopt(sys.argv[1:], 'vc:C:')
except getopt.GetoptError:
usage()
(verbose, charset_in, charset_out) = (False, None, 'utf-8')
for (k,v) in opts:
if k == '-v': verbose = True
elif k == '-c': charset_in = v
elif k == '-C': charset_out = v
if not args: args = ['-']
for url in args:
if url == '-':
fp = sys.stdin
elif url.startswith('http:') or url.startswith('ftp:'):
fp = urllib.urlopen(url)
else:
fp = file(url)
p = HTMLParser3(HTMLTextHandler(out(getcodec(charset_out))), charset=charset_in)
p.feedfile(fp).close()
fp.close()
p = HTMLParser3(HTMLDocumentBuilder(base_href=base_href), charset=charset, debug=debug)
p.feed(s)
return p.close()
# main
if __name__ == "__main__":
import getopt
from htmlutils import getcodec
from urllib import urlopen
def usage():
print "usage: htmldom.py [-d] [-c charset_in] [-C charset_out] [url ...]"
sys.exit(2)
try:
(opts, args) = getopt.getopt(sys.argv[1:], "dc:C:")
except getopt.GetoptError:
usage()
(debug, charset_in, charset_out) = (False, 'iso-8859-1', 'iso-8859-1')
for (k, v) in opts:
if k == "-d": debug += 1
elif k == "-c": charset_in = v
elif k == "-C": charset_out = v
codec = getcodec(charset_out)
for url in args:
fp = urlopen(url)
root = parsefile(fp, base_href=url, charset=charset_in)
fp.close()
if debug:
root.debug()
else:
root.dump(codec=codec)