Das deutsche Python-Forum

Code: Alles auswählen

import urllib.request

url = "http://www.ó.de"  # Fake-Adresse
html = urllib.request.urlopen(url).read()
print(str(html)[:30])

Code: Alles auswählen

Traceback (most recent call last):
  File "C:/Users/[...]/Desktop/skript.py", line 8, in <module>
    html = urllib.request.urlopen(url).read()
  File "C:\Python34\lib\urllib\request.py", line 153, in urlopen
    return opener.open(url, data, timeout)
  File "C:\Python34\lib\urllib\request.py", line 455, in open
    response = self._open(req, data)
  File "C:\Python34\lib\urllib\request.py", line 473, in _open
    '_open', req)
  File "C:\Python34\lib\urllib\request.py", line 433, in _call_chain
    result = func(*args)
  File "C:\Python34\lib\urllib\request.py", line 1261, in http_open
    return self.do_open(http.client.HTTPConnection, req)
  File "C:\Python34\lib\urllib\request.py", line 1235, in do_open
    h.request(req.get_method(), req.selector, req.data, headers)
  File "C:\Python34\lib\http\client.py", line 1066, in request
    self._send_request(method, url, body, headers)
  File "C:\Python34\lib\http\client.py", line 1094, in _send_request
    self.putrequest(method, url, **skips)
  File "C:\Python34\lib\http\client.py", line 958, in putrequest
    self._output(request.encode('ascii'))
UnicodeEncodeError: 'ascii' codec can't encode character '\xf3' in position 20: ordinal not in range(128)

Code: Alles auswählen

url.replace("ó","%C3%B3")

Code: Alles auswählen

import urllib.request
from urllib import parse

url = "http://www.ó.de"  # Fake-Adresse

scheme, netloc, path, query, fragment = parse.urlsplit(link)
path = parse.quote(path)
link = parse.urlunsplit((scheme, netloc, path, query, fragment))

html = urllib.request.urlopen(link).read()

print(str(html)[:30])

Code: Alles auswählen

>>> import codecs
>>> url = 'http://www.ó.de'
>>> code = codecs.encode(url, 'punycode')
>>> print(code)
b'http://www..de-vob'
>>> print(codecs.decode(code, 'punycode'))
http://www.ó.de