# -*- coding: utf-8 -*-
import gzip
-import HTMLParser
+import io
import locale
import os
import re
import email.utils
import json
-try:
- import cStringIO as StringIO
-except ImportError:
- import StringIO
-
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
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 ImportError: # Python 2
+ import HTMLParser as compat_html_parser
+
+try:
+ 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
+ # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
+ # Python 2's version is apparently totally broken
+ def _unquote(string, encoding='utf-8', errors='replace'):
+ if string == '':
+ return string
+ res = string.split('%')
+ if len(res) == 1:
+ return string
+ if encoding is None:
+ encoding = 'utf-8'
+ if errors is None:
+ errors = 'replace'
+ # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
+ pct_sequence = b''
+ string = res[0]
+ for item in res[1:]:
+ try:
+ if not item:
+ raise ValueError
+ pct_sequence += item[:2].decode('hex')
+ rest = item[2:]
+ if not rest:
+ # This segment was just a single percent-encoded character.
+ # May be part of a sequence of code units, so delay decoding.
+ # (Stored in pct_sequence).
+ continue
+ except ValueError:
+ rest = '%' + item
+ # Encountered non-percent-encoded characters. Flush the current
+ # pct_sequence.
+ string += pct_sequence.decode(encoding, errors) + rest
+ pct_sequence = b''
+ if pct_sequence:
+ # Flush the final pct_sequence
+ string += pct_sequence.decode(encoding, errors)
+ return string
+
+ def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
+ encoding='utf-8', errors='replace'):
+ qs, _coerce_result = qs, unicode
+ pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
+ r = []
+ for name_value in pairs:
+ if not name_value and not strict_parsing:
+ continue
+ nv = name_value.split('=', 1)
+ if len(nv) != 2:
+ if strict_parsing:
+ raise ValueError("bad query field: %r" % (name_value,))
+ # Handle case of a control-name with no equal sign
+ if keep_blank_values:
+ nv.append('')
+ else:
+ continue
+ if len(nv[1]) or keep_blank_values:
+ name = nv[0].replace('+', ' ')
+ name = _unquote(name, encoding=encoding, errors=errors)
+ name = _coerce_result(name)
+ value = nv[1].replace('+', ' ')
+ value = _unquote(value, encoding=encoding, errors=errors)
+ value = _coerce_result(value)
+ r.append((name, value))
+ return r
+
+ def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
+ encoding='utf-8', errors='replace'):
+ parsed_result = {}
+ pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
+ encoding=encoding, errors=errors)
+ for name, value in pairs:
+ if name in parsed_result:
+ parsed_result[name].append(value)
+ else:
+ parsed_result[name] = [value]
+ return parsed_result
+
try:
compat_str = unicode # Python 2
except NameError:
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.
# Unknown entity in name, return its literal representation
return (u'&%s;' % entity)
-HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class IDParser(HTMLParser.HTMLParser):
+compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
+class IDParser(compat_html_parser.HTMLParser):
"""Modified HTMLParser that isolates a tag with the specified id"""
def __init__(self, id):
self.id = id
self.html = None
self.watch_startpos = False
self.error_count = 0
- HTMLParser.HTMLParser.__init__(self)
+ compat_html_parser.HTMLParser.__init__(self)
def error(self, message):
if self.error_count > 10 or self.started:
- raise HTMLParser.HTMLParseError(message, self.getpos())
+ raise compat_html_parser.HTMLParseError(message, self.getpos())
self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
self.error_count += 1
self.goahead(1)
parser = IDParser(id)
try:
parser.loads(html)
- except HTMLParser.HTMLParseError:
+ except compat_html_parser.HTMLParseError:
pass
return parser.get_result()
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
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
- gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
+ gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
- gz = StringIO.StringIO(self.deflate(resp.read()))
+ gz = io.BytesIO(self.deflate(resp.read()))
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
return resp