1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
|
From 812793c07d3202d3f5bc39091aec2e7071d000c8 Mon Sep 17 00:00:00 2001
From: Sebastian Pipping <sebastian@pipping.org>
Date: Sun, 1 Jan 2012 19:30:57 +0100
Subject: [PATCH] Use shipped sgmllib for Python 3.x
---
feedparser/feedparser.py | 19 +++----------------
setup.py | 2 +-
2 files changed, 4 insertions(+), 17 deletions(-)
diff --git a/feedparser/feedparser.py b/feedparser/feedparser.py
index 8275c29..9a8a053 100644
--- a/feedparser/feedparser.py
+++ b/feedparser/feedparser.py
@@ -204,17 +204,9 @@ else:
try:
import sgmllib
except ImportError:
- # This is probably Python 3, which doesn't include sgmllib anymore
- _SGML_AVAILABLE = 0
+ import _feedparser_sgmllib as sgmllib
- # Mock sgmllib enough to allow subclassing later on
- class sgmllib(object):
- class SGMLParser(object):
- def goahead(self, i):
- pass
- def parse_starttag(self, i):
- pass
-else:
+if True:
_SGML_AVAILABLE = 1
# sgmllib defines a number of module-level regular expressions that are
@@ -2520,9 +2512,6 @@ class _RelativeURIResolver(_BaseHTMLProcessor):
_BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
def _resolveRelativeURIs(htmlSource, baseURI, encoding, _type):
- if not _SGML_AVAILABLE:
- return htmlSource
-
p = _RelativeURIResolver(baseURI, encoding, _type)
p.feed(htmlSource)
return p.output()
@@ -2803,8 +2792,6 @@ class _HTMLSanitizer(_BaseHTMLProcessor):
def _sanitizeHTML(htmlSource, encoding, _type):
- if not _SGML_AVAILABLE:
- return htmlSource
p = _HTMLSanitizer(encoding, _type)
htmlSource = htmlSource.replace('<![CDATA[', '<![CDATA[')
p.feed(htmlSource)
@@ -3890,7 +3877,7 @@ def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, refer
result['bozo'] = 1
result['bozo_exception'] = feedparser.exc or e
use_strict_parser = 0
- if not use_strict_parser and _SGML_AVAILABLE:
+ if not use_strict_parser:
feedparser = _LooseFeedParser(baseuri, baselang, 'utf-8', entities)
feedparser.feed(data.decode('utf-8', 'replace'))
result['feed'] = feedparser.feeddata
diff --git a/setup.py b/setup.py
index a4a60fe..8c15451 100644
--- a/setup.py
+++ b/setup.py
@@ -16,7 +16,7 @@ setup(
download_url = 'http://code.google.com/p/feedparser/',
platforms = ['POSIX', 'Windows'],
package_dir = {'': 'feedparser'},
- py_modules = ['feedparser'],
+ py_modules = ['feedparser', '_feedparser_sgmllib'],
keywords = ['atom', 'cdf', 'feed', 'parser', 'rdf', 'rss'],
classifiers = [
'Development Status :: 5 - Production/Stable',
--
1.7.8.1
|
GitWeb