try:
import html.entities as compat_html_entities
-except NameError: # Python 2
+except ImportError: # Python 2
import htmlentitydefs as compat_html_entities
try:
import html.parser as compat_html_parser
-except NameError: # Python 2
+except ImportError: # Python 2
import HTMLParser as compat_html_parser
try:
- import http.client as compat_html_client
-except NameError: # Python 2
- import httplib as compat_html_client
+ import http.client as compat_http_client
+except ImportError: # Python 2
+ import httplib as compat_http_client
+try:
+ from urllib.parse import parse_qs as compat_parse_qs
+except ImportError: # Python 2
+ from urlparse import parse_qs as compat_parse_qs
try:
compat_str = unicode # Python 2
except NameError:
compat_chr = chr
-
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
return pref
+if sys.version_info < (3,0):
+ def compat_print(s):
+ print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
+else:
+ def compat_print(s):
+ assert type(s) == type(u'')
+ print(s)
def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a character.
assert type(s) == type(u'')
+ # Python 3 has a Unicode API
+ if sys.version_info >= (3, 0):
+ return s
+
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
# Pass u'' directly to use Unicode APIs on Windows 2000 and up
# (Detecting Windows NT 4 is tricky because 'major >= 4' would