из браузера механизатора импорта
br = Браузер ()
page = br.open ('http://wow.interzet.ru/news.php?readmore=23')
br.form = br.forms (). next ()
печать br.form
выдает мне следующую ошибку:
Traceback (most recent call last):
File "C:\Users\roddik\Desktop\mech.py", line 6, in <module>
br.form = br.forms().next()
File "build\bdist.win32\egg\mechanize\_mechanize.py", line 426, in forms
File "D:\py26\lib\site-package\mechanize-0.1.11-py2.6.egg\mechanize\_html.py", line 559, in forms
File "D:\py26\lib\site-packages\mechanize-0.1.11-py2.6.egg\mechanize\_html.py", line 225, in forms
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 967, in ParseResponseEx
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 1100, in _ParseFileEx
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 870, in feed
File "D:\py26\lib\sgmllib.py", line 104, in feed
self.goahead(0)
File "D:\py26\lib\sgmllib.py", line 138, in goahead
k = self.parse_starttag(i)
File "D:\py26\lib\sgmllib.py", line 290, in parse_starttag
self._convert_ref, attrvalue)
File "D:\py26\lib\sgmllib.py", line 302, in _convert_ref
return self.convert_charref(match.group(2)) or \
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 850, in convert_charref
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 244, in unescape_charref
ValueError: invalid literal for int() with base 10: 'e'
Как я могу это исправить?
Edit:
Я исправил это так. Это нормально? Если нет, то как вместо?
import ClientForm
from mechanize import Browser
def myunescape_charref(data, encoding):
if not str(data).isdigit(): return 0
name, base = data, 10
if name.startswith("x"):
name, base= name[1:], 16
uc = unichr(int(name, base))
if encoding is None:
return uc
else:
try:
repl = uc.encode(encoding)
except UnicodeError:
repl = "&#%s;" % data
return repl
ClientForm.unescape_charref = myunescape_charref