David Blume commited on 2018-01-20 20:10:33
Showing 4 changed files, with 4291 additions and 0 deletions.
... | ... |
@@ -0,0 +1,19 @@ |
1 |
+Copyright (c) 2018, David Blume |
|
2 |
+ |
|
3 |
+Permission is hereby granted, free of charge, to any person obtaining |
|
4 |
+a copy of this software and associated documentation files (the "Software"), |
|
5 |
+to deal in the Software without restriction, including without limitation |
|
6 |
+the rights to use, copy, modify, merge, publish, distribute, sublicense, |
|
7 |
+and/or sell copies of the Software, and to permit persons to whom the |
|
8 |
+Software is furnished to do so, subject to the following conditions: |
|
9 |
+ |
|
10 |
+The above copyright notice and this permission notice shall be included |
|
11 |
+in all copies or substantial portions of the Software. |
|
12 |
+ |
|
13 |
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS |
|
14 |
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
|
15 |
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
|
16 |
+THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
|
17 |
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING |
|
18 |
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER |
|
19 |
+DEALINGS IN THE SOFTWARE. |
... | ... |
@@ -0,0 +1,30 @@ |
1 |
+[](http://git.dlma.com/techcrunch.git/blob/master/LICENSE.txt) |
|
2 |
+ |
|
3 |
+# TechCrunch Feed Filter |
|
4 |
+ |
|
5 |
+This is a Python script run as a cronjob to read the TechCrunch article feed, |
|
6 |
+and decide which articles to include in its own feed. |
|
7 |
+ |
|
8 |
+Here's a [blog post about it](http://david.dlma.com/blog/my-techcrunch-feed-filter). |
|
9 |
+ |
|
10 |
+# History |
|
11 |
+ |
|
12 |
+This was originally archived in a Subversion repo. I'd forgotten about the |
|
13 |
+version control and had gotten into the habit of just modifying the production |
|
14 |
+site. |
|
15 |
+ |
|
16 |
+* 2010-09-03: Original |
|
17 |
+* 2010-09-03: Save off the disqus identifier for use later. |
|
18 |
+* 2011-02-04: Algorithm changes (tags and author checked), new chart drawing, spaces used instead of tabs. |
|
19 |
+* 2011-02-04: Update to the chart drawing algorithm. |
|
20 |
+* 2013-08-04: Miscellaneous changes to techcrunch.py |
|
21 |
+* 2015-11-23: Resync svn with production site. |
|
22 |
+* 2015-11-27: Remove obsolete disqus and retweet code, and refactor style to be more PEP-8ish. |
|
23 |
+ |
|
24 |
+# Is it any good? |
|
25 |
+ |
|
26 |
+[Yes](https://news.ycombinator.com/item?id=3067434). |
|
27 |
+ |
|
28 |
+# Licence |
|
29 |
+ |
|
30 |
+This software uses the [MIT license](http://git.dlma.com/techcrunch.git/blob/master/LICENSE.txt) |
... | ... |
@@ -0,0 +1,3612 @@ |
1 |
+#!/usr/bin/env python |
|
2 |
+"""Universal feed parser |
|
3 |
+ |
|
4 |
+Handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds |
|
5 |
+ |
|
6 |
+Visit http://feedparser.org/ for the latest version |
|
7 |
+Visit http://feedparser.org/docs/ for the latest documentation |
|
8 |
+ |
|
9 |
+Required: Python 2.1 or later |
|
10 |
+Recommended: Python 2.3 or later |
|
11 |
+Recommended: CJKCodecs and iconv_codec <http://cjkpython.i18n.org/> |
|
12 |
+""" |
|
13 |
+ |
|
14 |
+__version__ = "4.2-pre-" + "$Revision: 291 $"[11:14] + "-svn" |
|
15 |
+__license__ = """Copyright (c) 2002-2008, Mark Pilgrim, All rights reserved. |
|
16 |
+ |
|
17 |
+Redistribution and use in source and binary forms, with or without modification, |
|
18 |
+are permitted provided that the following conditions are met: |
|
19 |
+ |
|
20 |
+* Redistributions of source code must retain the above copyright notice, |
|
21 |
+ this list of conditions and the following disclaimer. |
|
22 |
+* Redistributions in binary form must reproduce the above copyright notice, |
|
23 |
+ this list of conditions and the following disclaimer in the documentation |
|
24 |
+ and/or other materials provided with the distribution. |
|
25 |
+ |
|
26 |
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS' |
|
27 |
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
|
28 |
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
|
29 |
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE |
|
30 |
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR |
|
31 |
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF |
|
32 |
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS |
|
33 |
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN |
|
34 |
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) |
|
35 |
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
|
36 |
+POSSIBILITY OF SUCH DAMAGE.""" |
|
37 |
+__author__ = "Mark Pilgrim <http://diveintomark.org/>" |
|
38 |
+__contributors__ = ["Jason Diamond <http://injektilo.org/>", |
|
39 |
+ "John Beimler <http://john.beimler.org/>", |
|
40 |
+ "Fazal Majid <http://www.majid.info/mylos/weblog/>", |
|
41 |
+ "Aaron Swartz <http://aaronsw.com/>", |
|
42 |
+ "Kevin Marks <http://epeus.blogspot.com/>", |
|
43 |
+ "Sam Ruby <http://intertwingly.net/>"] |
|
44 |
+_debug = 0 |
|
45 |
+ |
|
46 |
+# HTTP "User-Agent" header to send to servers when downloading feeds. |
|
47 |
+# If you are embedding feedparser in a larger application, you should |
|
48 |
+# change this to your application name and URL. |
|
49 |
+USER_AGENT = "UniversalFeedParser/%s +http://feedparser.org/" % __version__ |
|
50 |
+ |
|
51 |
+# HTTP "Accept" header to send to servers when downloading feeds. If you don't |
|
52 |
+# want to send an Accept header, set this to None. |
|
53 |
+ACCEPT_HEADER = "application/atom+xml,application/rdf+xml,application/rss+xml,application/x-netcdf,application/xml;q=0.9,text/xml;q=0.2,*/*;q=0.1" |
|
54 |
+ |
|
55 |
+# List of preferred XML parsers, by SAX driver name. These will be tried first, |
|
56 |
+# but if they're not installed, Python will keep searching through its own list |
|
57 |
+# of pre-installed parsers until it finds one that supports everything we need. |
|
58 |
+PREFERRED_XML_PARSERS = ["drv_libxml2"] |
|
59 |
+ |
|
60 |
+# If you want feedparser to automatically run HTML markup through HTML Tidy, set |
|
61 |
+# this to 1. Requires mxTidy <http://www.egenix.com/files/python/mxTidy.html> |
|
62 |
+# or utidylib <http://utidylib.berlios.de/>. |
|
63 |
+TIDY_MARKUP = 0 |
|
64 |
+ |
|
65 |
+# List of Python interfaces for HTML Tidy, in order of preference. Only useful |
|
66 |
+# if TIDY_MARKUP = 1 |
|
67 |
+PREFERRED_TIDY_INTERFACES = ["uTidy", "mxTidy"] |
|
68 |
+ |
|
69 |
+# If you want feedparser to automatically resolve all relative URIs, set this |
|
70 |
+# to 1. |
|
71 |
+RESOLVE_RELATIVE_URIS = 1 |
|
72 |
+ |
|
73 |
+# If you want feedparser to automatically sanitize all potentially unsafe |
|
74 |
+# HTML content, set this to 1. |
|
75 |
+SANITIZE_HTML = 1 |
|
76 |
+ |
|
77 |
+# ---------- required modules (should come with any Python distribution) ---------- |
|
78 |
+import sgmllib, re, sys, copy, urlparse, time, rfc822, types, cgi, urllib, urllib2 |
|
79 |
+try: |
|
80 |
+ from cStringIO import StringIO as _StringIO |
|
81 |
+except: |
|
82 |
+ from StringIO import StringIO as _StringIO |
|
83 |
+ |
|
84 |
+# ---------- optional modules (feedparser will work without these, but with reduced functionality) ---------- |
|
85 |
+ |
|
86 |
+# gzip is included with most Python distributions, but may not be available if you compiled your own |
|
87 |
+try: |
|
88 |
+ import gzip |
|
89 |
+except: |
|
90 |
+ gzip = None |
|
91 |
+try: |
|
92 |
+ import zlib |
|
93 |
+except: |
|
94 |
+ zlib = None |
|
95 |
+ |
|
96 |
+# If a real XML parser is available, feedparser will attempt to use it. feedparser has |
|
97 |
+# been tested with the built-in SAX parser, PyXML, and libxml2. On platforms where the |
|
98 |
+# Python distribution does not come with an XML parser (such as Mac OS X 10.2 and some |
|
99 |
+# versions of FreeBSD), feedparser will quietly fall back on regex-based parsing. |
|
100 |
+try: |
|
101 |
+ import xml.sax |
|
102 |
+ xml.sax.make_parser(PREFERRED_XML_PARSERS) # test for valid parsers |
|
103 |
+ from xml.sax.saxutils import escape as _xmlescape |
|
104 |
+ _XML_AVAILABLE = 1 |
|
105 |
+except: |
|
106 |
+ _XML_AVAILABLE = 0 |
|
107 |
+ def _xmlescape(data,entities={}): |
|
108 |
+ data = data.replace('&', '&') |
|
109 |
+ data = data.replace('>', '>') |
|
110 |
+ data = data.replace('<', '<') |
|
111 |
+ for char, entity in entities: |
|
112 |
+ data = data.replace(char, entity) |
|
113 |
+ return data |
|
114 |
+ |
|
115 |
+# base64 support for Atom feeds that contain embedded binary data |
|
116 |
+try: |
|
117 |
+ import base64, binascii |
|
118 |
+except: |
|
119 |
+ base64 = binascii = None |
|
120 |
+ |
|
121 |
+# cjkcodecs and iconv_codec provide support for more character encodings. |
|
122 |
+# Both are available from http://cjkpython.i18n.org/ |
|
123 |
+try: |
|
124 |
+ import cjkcodecs.aliases |
|
125 |
+except: |
|
126 |
+ pass |
|
127 |
+try: |
|
128 |
+ import iconv_codec |
|
129 |
+except: |
|
130 |
+ pass |
|
131 |
+ |
|
132 |
+# chardet library auto-detects character encodings |
|
133 |
+# Download from http://chardet.feedparser.org/ |
|
134 |
+try: |
|
135 |
+ import chardet |
|
136 |
+ if _debug: |
|
137 |
+ import chardet.constants |
|
138 |
+ chardet.constants._debug = 1 |
|
139 |
+except: |
|
140 |
+ chardet = None |
|
141 |
+ |
|
142 |
+# reversable htmlentitydefs mappings for Python 2.2 |
|
143 |
+try: |
|
144 |
+ from htmlentitydefs import name2codepoint, codepoint2name |
|
145 |
+except: |
|
146 |
+ import htmlentitydefs |
|
147 |
+ name2codepoint={} |
|
148 |
+ codepoint2name={} |
|
149 |
+ for (name,codepoint) in htmlentitydefs.entitydefs.iteritems(): |
|
150 |
+ if codepoint.startswith('&#'): codepoint=unichr(int(codepoint[2:-1])) |
|
151 |
+ name2codepoint[name]=ord(codepoint) |
|
152 |
+ codepoint2name[ord(codepoint)]=name |
|
153 |
+ |
|
154 |
+# BeautifulSoup parser used for parsing microformats from embedded HTML content |
|
155 |
+# http://www.crummy.com/software/BeautifulSoup/ |
|
156 |
+# feedparser is tested with BeautifulSoup 3.0.x, but it might work with the |
|
157 |
+# older 2.x series. If it doesn't, and you can figure out why, I'll accept a |
|
158 |
+# patch and modify the compatibility statement accordingly. |
|
159 |
+try: |
|
160 |
+ import BeautifulSoup |
|
161 |
+except: |
|
162 |
+ BeautifulSoup = None |
|
163 |
+ |
|
164 |
+# ---------- don't touch these ---------- |
|
165 |
+class ThingsNobodyCaresAboutButMe(Exception): pass |
|
166 |
+class CharacterEncodingOverride(ThingsNobodyCaresAboutButMe): pass |
|
167 |
+class CharacterEncodingUnknown(ThingsNobodyCaresAboutButMe): pass |
|
168 |
+class NonXMLContentType(ThingsNobodyCaresAboutButMe): pass |
|
169 |
+class UndeclaredNamespace(Exception): pass |
|
170 |
+ |
|
171 |
+sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*') |
|
172 |
+sgmllib.special = re.compile('<!') |
|
173 |
+sgmllib.charref = re.compile('&#(\d+|x[0-9a-fA-F]+);') |
|
174 |
+ |
|
175 |
+if sgmllib.endbracket.search(' <').start(0): |
|
176 |
+ class EndBracketMatch: |
|
177 |
+ endbracket = re.compile('''([^'"<>]|"[^"]*"(?=>|/|\s|\w+=)|'[^']*'(?=>|/|\s|\w+=))*(?=[<>])|.*?(?=[<>])''') |
|
178 |
+ def search(self,string,index=0): |
|
179 |
+ self.match = self.endbracket.match(string,index) |
|
180 |
+ if self.match: return self |
|
181 |
+ def start(self,n): |
|
182 |
+ return self.match.end(n) |
|
183 |
+ sgmllib.endbracket = EndBracketMatch() |
|
184 |
+ |
|
185 |
+SUPPORTED_VERSIONS = {'': 'unknown', |
|
186 |
+ 'rss090': 'RSS 0.90', |
|
187 |
+ 'rss091n': 'RSS 0.91 (Netscape)', |
|
188 |
+ 'rss091u': 'RSS 0.91 (Userland)', |
|
189 |
+ 'rss092': 'RSS 0.92', |
|
190 |
+ 'rss093': 'RSS 0.93', |
|
191 |
+ 'rss094': 'RSS 0.94', |
|
192 |
+ 'rss20': 'RSS 2.0', |
|
193 |
+ 'rss10': 'RSS 1.0', |
|
194 |
+ 'rss': 'RSS (unknown version)', |
|
195 |
+ 'atom01': 'Atom 0.1', |
|
196 |
+ 'atom02': 'Atom 0.2', |
|
197 |
+ 'atom03': 'Atom 0.3', |
|
198 |
+ 'atom10': 'Atom 1.0', |
|
199 |
+ 'atom': 'Atom (unknown version)', |
|
200 |
+ 'cdf': 'CDF', |
|
201 |
+ 'hotrss': 'Hot RSS' |
|
202 |
+ } |
|
203 |
+ |
|
204 |
+try: |
|
205 |
+ UserDict = dict |
|
206 |
+except NameError: |
|
207 |
+ # Python 2.1 does not have dict |
|
208 |
+ from UserDict import UserDict |
|
209 |
+ def dict(aList): |
|
210 |
+ rc = {} |
|
211 |
+ for k, v in aList: |
|
212 |
+ rc[k] = v |
|
213 |
+ return rc |
|
214 |
+ |
|
215 |
+class FeedParserDict(UserDict): |
|
216 |
+ keymap = {'channel': 'feed', |
|
217 |
+ 'items': 'entries', |
|
218 |
+ 'guid': 'id', |
|
219 |
+ 'date': 'updated', |
|
220 |
+ 'date_parsed': 'updated_parsed', |
|
221 |
+ 'description': ['subtitle', 'summary'], |
|
222 |
+ 'url': ['href'], |
|
223 |
+ 'modified': 'updated', |
|
224 |
+ 'modified_parsed': 'updated_parsed', |
|
225 |
+ 'issued': 'published', |
|
226 |
+ 'issued_parsed': 'published_parsed', |
|
227 |
+ 'copyright': 'rights', |
|
228 |
+ 'copyright_detail': 'rights_detail', |
|
229 |
+ 'tagline': 'subtitle', |
|
230 |
+ 'tagline_detail': 'subtitle_detail'} |
|
231 |
+ def __getitem__(self, key): |
|
232 |
+ if key == 'category': |
|
233 |
+ return UserDict.__getitem__(self, 'tags')[0]['term'] |
|
234 |
+ if key == 'enclosures': |
|
235 |
+ norel = lambda link: FeedParserDict([(name,value) for (name,value) in link.items() if name!='rel']) |
|
236 |
+ return [norel(link) for link in UserDict.__getitem__(self, 'links') if link['rel']=='enclosure'] |
|
237 |
+ if key == 'license': |
|
238 |
+ for link in UserDict.__getitem__(self, 'links'): |
|
239 |
+ if link['rel']=='license' and link.has_key('href'): |
|
240 |
+ return link['href'] |
|
241 |
+ if key == 'categories': |
|
242 |
+ return [(tag['scheme'], tag['term']) for tag in UserDict.__getitem__(self, 'tags')] |
|
243 |
+ realkey = self.keymap.get(key, key) |
|
244 |
+ if type(realkey) == types.ListType: |
|
245 |
+ for k in realkey: |
|
246 |
+ if UserDict.has_key(self, k): |
|
247 |
+ return UserDict.__getitem__(self, k) |
|
248 |
+ if UserDict.has_key(self, key): |
|
249 |
+ return UserDict.__getitem__(self, key) |
|
250 |
+ return UserDict.__getitem__(self, realkey) |
|
251 |
+ |
|
252 |
+ def __setitem__(self, key, value): |
|
253 |
+ for k in self.keymap.keys(): |
|
254 |
+ if key == k: |
|
255 |
+ key = self.keymap[k] |
|
256 |
+ if type(key) == types.ListType: |
|
257 |
+ key = key[0] |
|
258 |
+ return UserDict.__setitem__(self, key, value) |
|
259 |
+ |
|
260 |
+ def get(self, key, default=None): |
|
261 |
+ if self.has_key(key): |
|
262 |
+ return self[key] |
|
263 |
+ else: |
|
264 |
+ return default |
|
265 |
+ |
|
266 |
+ def setdefault(self, key, value): |
|
267 |
+ if not self.has_key(key): |
|
268 |
+ self[key] = value |
|
269 |
+ return self[key] |
|
270 |
+ |
|
271 |
+ def has_key(self, key): |
|
272 |
+ try: |
|
273 |
+ return hasattr(self, key) or UserDict.has_key(self, key) |
|
274 |
+ except AttributeError: |
|
275 |
+ return False |
|
276 |
+ |
|
277 |
+ def __getattr__(self, key): |
|
278 |
+ try: |
|
279 |
+ return self.__dict__[key] |
|
280 |
+ except KeyError: |
|
281 |
+ pass |
|
282 |
+ try: |
|
283 |
+ assert not key.startswith('_') |
|
284 |
+ return self.__getitem__(key) |
|
285 |
+ except: |
|
286 |
+ raise AttributeError, "object has no attribute '%s'" % key |
|
287 |
+ |
|
288 |
+ def __setattr__(self, key, value): |
|
289 |
+ if key.startswith('_') or key == 'data': |
|
290 |
+ self.__dict__[key] = value |
|
291 |
+ else: |
|
292 |
+ return self.__setitem__(key, value) |
|
293 |
+ |
|
294 |
+ def __contains__(self, key): |
|
295 |
+ return self.has_key(key) |
|
296 |
+ |
|
297 |
+def zopeCompatibilityHack(): |
|
298 |
+ global FeedParserDict |
|
299 |
+ del FeedParserDict |
|
300 |
+ def FeedParserDict(aDict=None): |
|
301 |
+ rc = {} |
|
302 |
+ if aDict: |
|
303 |
+ rc.update(aDict) |
|
304 |
+ return rc |
|
305 |
+ |
|
306 |
+_ebcdic_to_ascii_map = None |
|
307 |
+def _ebcdic_to_ascii(s): |
|
308 |
+ global _ebcdic_to_ascii_map |
|
309 |
+ if not _ebcdic_to_ascii_map: |
|
310 |
+ emap = ( |
|
311 |
+ 0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15, |
|
312 |
+ 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31, |
|
313 |
+ 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7, |
|
314 |
+ 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26, |
|
315 |
+ 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33, |
|
316 |
+ 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94, |
|
317 |
+ 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63, |
|
318 |
+ 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34, |
|
319 |
+ 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200,201, |
|
320 |
+ 202,106,107,108,109,110,111,112,113,114,203,204,205,206,207,208, |
|
321 |
+ 209,126,115,116,117,118,119,120,121,122,210,211,212,213,214,215, |
|
322 |
+ 216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231, |
|
323 |
+ 123,65,66,67,68,69,70,71,72,73,232,233,234,235,236,237, |
|
324 |
+ 125,74,75,76,77,78,79,80,81,82,238,239,240,241,242,243, |
|
325 |
+ 92,159,83,84,85,86,87,88,89,90,244,245,246,247,248,249, |
|
326 |
+ 48,49,50,51,52,53,54,55,56,57,250,251,252,253,254,255 |
|
327 |
+ ) |
|
328 |
+ import string |
|
329 |
+ _ebcdic_to_ascii_map = string.maketrans( \ |
|
330 |
+ ''.join(map(chr, range(256))), ''.join(map(chr, emap))) |
|
331 |
+ return s.translate(_ebcdic_to_ascii_map) |
|
332 |
+ |
|
333 |
+_cp1252 = { |
|
334 |
+ unichr(128): unichr(8364), # euro sign |
|
335 |
+ unichr(130): unichr(8218), # single low-9 quotation mark |
|
336 |
+ unichr(131): unichr( 402), # latin small letter f with hook |
|
337 |
+ unichr(132): unichr(8222), # double low-9 quotation mark |
|
338 |
+ unichr(133): unichr(8230), # horizontal ellipsis |
|
339 |
+ unichr(134): unichr(8224), # dagger |
|
340 |
+ unichr(135): unichr(8225), # double dagger |
|
341 |
+ unichr(136): unichr( 710), # modifier letter circumflex accent |
|
342 |
+ unichr(137): unichr(8240), # per mille sign |
|
343 |
+ unichr(138): unichr( 352), # latin capital letter s with caron |
|
344 |
+ unichr(139): unichr(8249), # single left-pointing angle quotation mark |
|
345 |
+ unichr(140): unichr( 338), # latin capital ligature oe |
|
346 |
+ unichr(142): unichr( 381), # latin capital letter z with caron |
|
347 |
+ unichr(145): unichr(8216), # left single quotation mark |
|
348 |
+ unichr(146): unichr(8217), # right single quotation mark |
|
349 |
+ unichr(147): unichr(8220), # left double quotation mark |
|
350 |
+ unichr(148): unichr(8221), # right double quotation mark |
|
351 |
+ unichr(149): unichr(8226), # bullet |
|
352 |
+ unichr(150): unichr(8211), # en dash |
|
353 |
+ unichr(151): unichr(8212), # em dash |
|
354 |
+ unichr(152): unichr( 732), # small tilde |
|
355 |
+ unichr(153): unichr(8482), # trade mark sign |
|
356 |
+ unichr(154): unichr( 353), # latin small letter s with caron |
|
357 |
+ unichr(155): unichr(8250), # single right-pointing angle quotation mark |
|
358 |
+ unichr(156): unichr( 339), # latin small ligature oe |
|
359 |
+ unichr(158): unichr( 382), # latin small letter z with caron |
|
360 |
+ unichr(159): unichr( 376)} # latin capital letter y with diaeresis |
|
361 |
+ |
|
362 |
+_urifixer = re.compile('^([A-Za-z][A-Za-z0-9+-.]*://)(/*)(.*?)') |
|
363 |
+def _urljoin(base, uri): |
|
364 |
+ uri = _urifixer.sub(r'\1\3', uri) |
|
365 |
+ try: |
|
366 |
+ return urlparse.urljoin(base, uri) |
|
367 |
+ except: |
|
368 |
+ uri = urlparse.urlunparse([urllib.quote(part) for part in urlparse.urlparse(uri)]) |
|
369 |
+ return urlparse.urljoin(base, uri) |
|
370 |
+ |
|
371 |
+class _FeedParserMixin: |
|
372 |
+ namespaces = {'': '', |
|
373 |
+ 'http://backend.userland.com/rss': '', |
|
374 |
+ 'http://blogs.law.harvard.edu/tech/rss': '', |
|
375 |
+ 'http://purl.org/rss/1.0/': '', |
|
376 |
+ 'http://my.netscape.com/rdf/simple/0.9/': '', |
|
377 |
+ 'http://example.com/newformat#': '', |
|
378 |
+ 'http://example.com/necho': '', |
|
379 |
+ 'http://purl.org/echo/': '', |
|
380 |
+ 'uri/of/echo/namespace#': '', |
|
381 |
+ 'http://purl.org/pie/': '', |
|
382 |
+ 'http://purl.org/atom/ns#': '', |
|
383 |
+ 'http://www.w3.org/2005/Atom': '', |
|
384 |
+ 'http://purl.org/rss/1.0/modules/rss091#': '', |
|
385 |
+ |
|
386 |
+ 'http://webns.net/mvcb/': 'admin', |
|
387 |
+ 'http://purl.org/rss/1.0/modules/aggregation/': 'ag', |
|
388 |
+ 'http://purl.org/rss/1.0/modules/annotate/': 'annotate', |
|
389 |
+ 'http://media.tangent.org/rss/1.0/': 'audio', |
|
390 |
+ 'http://backend.userland.com/blogChannelModule': 'blogChannel', |
|
391 |
+ 'http://web.resource.org/cc/': 'cc', |
|
392 |
+ 'http://backend.userland.com/creativeCommonsRssModule': 'creativeCommons', |
|
393 |
+ 'http://purl.org/rss/1.0/modules/company': 'co', |
|
394 |
+ 'http://purl.org/rss/1.0/modules/content/': 'content', |
|
395 |
+ 'http://my.theinfo.org/changed/1.0/rss/': 'cp', |
|
396 |
+ 'http://purl.org/dc/elements/1.1/': 'dc', |
|
397 |
+ 'http://purl.org/dc/terms/': 'dcterms', |
|
398 |
+ 'http://purl.org/rss/1.0/modules/email/': 'email', |
|
399 |
+ 'http://purl.org/rss/1.0/modules/event/': 'ev', |
|
400 |
+ 'http://rssnamespace.org/feedburner/ext/1.0': 'feedburner', |
|
401 |
+ 'http://freshmeat.net/rss/fm/': 'fm', |
|
402 |
+ 'http://xmlns.com/foaf/0.1/': 'foaf', |
|
403 |
+ 'http://www.w3.org/2003/01/geo/wgs84_pos#': 'geo', |
|
404 |
+ 'http://postneo.com/icbm/': 'icbm', |
|
405 |
+ 'http://purl.org/rss/1.0/modules/image/': 'image', |
|
406 |
+ 'http://www.itunes.com/DTDs/PodCast-1.0.dtd': 'itunes', |
|
407 |
+ 'http://example.com/DTDs/PodCast-1.0.dtd': 'itunes', |
|
408 |
+ 'http://purl.org/rss/1.0/modules/link/': 'l', |
|
409 |
+ 'http://search.yahoo.com/mrss': 'media', |
|
410 |
+ 'http://madskills.com/public/xml/rss/module/pingback/': 'pingback', |
|
411 |
+ 'http://prismstandard.org/namespaces/1.2/basic/': 'prism', |
|
412 |
+ 'http://www.w3.org/1999/02/22-rdf-syntax-ns#': 'rdf', |
|
413 |
+ 'http://www.w3.org/2000/01/rdf-schema#': 'rdfs', |
|
414 |
+ 'http://purl.org/rss/1.0/modules/reference/': 'ref', |
|
415 |
+ 'http://purl.org/rss/1.0/modules/richequiv/': 'reqv', |
|
416 |
+ 'http://purl.org/rss/1.0/modules/search/': 'search', |
|
417 |
+ 'http://purl.org/rss/1.0/modules/slash/': 'slash', |
|
418 |
+ 'http://schemas.xmlsoap.org/soap/envelope/': 'soap', |
|
419 |
+ 'http://purl.org/rss/1.0/modules/servicestatus/': 'ss', |
|
420 |
+ 'http://hacks.benhammersley.com/rss/streaming/': 'str', |
|
421 |
+ 'http://purl.org/rss/1.0/modules/subscription/': 'sub', |
|
422 |
+ 'http://purl.org/rss/1.0/modules/syndication/': 'sy', |
|
423 |
+ 'http://schemas.pocketsoap.com/rss/myDescModule/': 'szf', |
|
424 |
+ 'http://purl.org/rss/1.0/modules/taxonomy/': 'taxo', |
|
425 |
+ 'http://purl.org/rss/1.0/modules/threading/': 'thr', |
|
426 |
+ 'http://purl.org/rss/1.0/modules/textinput/': 'ti', |
|
427 |
+ 'http://madskills.com/public/xml/rss/module/trackback/':'trackback', |
|
428 |
+ 'http://wellformedweb.org/commentAPI/': 'wfw', |
|
429 |
+ 'http://purl.org/rss/1.0/modules/wiki/': 'wiki', |
|
430 |
+ 'http://www.w3.org/1999/xhtml': 'xhtml', |
|
431 |
+ 'http://www.w3.org/1999/xlink': 'xlink', |
|
432 |
+ 'http://www.w3.org/XML/1998/namespace': 'xml' |
|
433 |
+} |
|
434 |
+ _matchnamespaces = {} |
|
435 |
+ |
|
436 |
+ can_be_relative_uri = ['link', 'id', 'wfw_comment', 'wfw_commentrss', 'docs', 'url', 'href', 'comments', 'icon', 'logo'] |
|
437 |
+ can_contain_relative_uris = ['content', 'title', 'summary', 'info', 'tagline', 'subtitle', 'copyright', 'rights', 'description'] |
|
438 |
+ can_contain_dangerous_markup = ['content', 'title', 'summary', 'info', 'tagline', 'subtitle', 'copyright', 'rights', 'description'] |
|
439 |
+ html_types = ['text/html', 'application/xhtml+xml'] |
|
440 |
+ |
|
441 |
+ def __init__(self, baseuri=None, baselang=None, encoding='utf-8'): |
|
442 |
+ if _debug: sys.stderr.write('initializing FeedParser\n') |
|
443 |
+ if not self._matchnamespaces: |
|
444 |
+ for k, v in self.namespaces.items(): |
|
445 |
+ self._matchnamespaces[k.lower()] = v |
|
446 |
+ self.feeddata = FeedParserDict() # feed-level data |
|
447 |
+ self.encoding = encoding # character encoding |
|
448 |
+ self.entries = [] # list of entry-level data |
|
449 |
+ self.version = '' # feed type/version, see SUPPORTED_VERSIONS |
|
450 |
+ self.namespacesInUse = {} # dictionary of namespaces defined by the feed |
|
451 |
+ |
|
452 |
+ # the following are used internally to track state; |
|
453 |
+ # this is really out of control and should be refactored |
|
454 |
+ self.infeed = 0 |
|
455 |
+ self.inentry = 0 |
|
456 |
+ self.incontent = 0 |
|
457 |
+ self.intextinput = 0 |
|
458 |
+ self.inimage = 0 |
|
459 |
+ self.inauthor = 0 |
|
460 |
+ self.incontributor = 0 |
|
461 |
+ self.inpublisher = 0 |
|
462 |
+ self.insource = 0 |
|
463 |
+ self.sourcedata = FeedParserDict() |
|
464 |
+ self.contentparams = FeedParserDict() |
|
465 |
+ self._summaryKey = None |
|
466 |
+ self.namespacemap = {} |
|
467 |
+ self.elementstack = [] |
|
468 |
+ self.basestack = [] |
|
469 |
+ self.langstack = [] |
|
470 |
+ self.baseuri = baseuri or '' |
|
471 |
+ self.lang = baselang or None |
|
472 |
+ self.svgOK = 0 |
|
473 |
+ self.hasTitle = 0 |
|
474 |
+ if baselang: |
|
475 |
+ self.feeddata['language'] = baselang.replace('_','-') |
|
476 |
+ |
|
477 |
+ def unknown_starttag(self, tag, attrs): |
|
478 |
+ if _debug: sys.stderr.write('start %s with %s\n' % (tag, attrs)) |
|
479 |
+ # normalize attrs |
|
480 |
+ attrs = [(k.lower(), v) for k, v in attrs] |
|
481 |
+ attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] |
|
482 |
+ |
|
483 |
+ # track xml:base and xml:lang |
|
484 |
+ attrsD = dict(attrs) |
|
485 |
+ baseuri = attrsD.get('xml:base', attrsD.get('base')) or self.baseuri |
|
486 |
+ if type(baseuri) != type(u''): |
|
487 |
+ try: |
|
488 |
+ baseuri = unicode(baseuri, self.encoding) |
|
489 |
+ except: |
|
490 |
+ baseuri = unicode(baseuri, 'iso-8859-1') |
|
491 |
+ self.baseuri = _urljoin(self.baseuri, baseuri) |
|
492 |
+ lang = attrsD.get('xml:lang', attrsD.get('lang')) |
|
493 |
+ if lang == '': |
|
494 |
+ # xml:lang could be explicitly set to '', we need to capture that |
|
495 |
+ lang = None |
|
496 |
+ elif lang is None: |
|
497 |
+ # if no xml:lang is specified, use parent lang |
|
498 |
+ lang = self.lang |
|
499 |
+ if lang: |
|
500 |
+ if tag in ('feed', 'rss', 'rdf:RDF'): |
|
501 |
+ self.feeddata['language'] = lang.replace('_','-') |
|
502 |
+ self.lang = lang |
|
503 |
+ self.basestack.append(self.baseuri) |
|
504 |
+ self.langstack.append(lang) |
|
505 |
+ |
|
506 |
+ # track namespaces |
|
507 |
+ for prefix, uri in attrs: |
|
508 |
+ if prefix.startswith('xmlns:'): |
|
509 |
+ self.trackNamespace(prefix[6:], uri) |
|
510 |
+ elif prefix == 'xmlns': |
|
511 |
+ self.trackNamespace(None, uri) |
|
512 |
+ |
|
513 |
+ # track inline content |
|
514 |
+ if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): |
|
515 |
+ if tag in ['xhtml:div', 'div']: return # typepad does this 10/2007 |
|
516 |
+ # element declared itself as escaped markup, but it isn't really |
|
517 |
+ self.contentparams['type'] = 'application/xhtml+xml' |
|
518 |
+ if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': |
|
519 |
+ if tag.find(':') <> -1: |
|
520 |
+ prefix, tag = tag.split(':', 1) |
|
521 |
+ namespace = self.namespacesInUse.get(prefix, '') |
|
522 |
+ if tag=='math' and namespace=='http://www.w3.org/1998/Math/MathML': |
|
523 |
+ attrs.append(('xmlns',namespace)) |
|
524 |
+ if tag=='svg' and namespace=='http://www.w3.org/2000/svg': |
|
525 |
+ attrs.append(('xmlns',namespace)) |
|
526 |
+ if tag == 'svg': self.svgOK += 1 |
|
527 |
+ return self.handle_data('<%s%s>' % (tag, self.strattrs(attrs)), escape=0) |
|
528 |
+ |
|
529 |
+ # match namespaces |
|
530 |
+ if tag.find(':') <> -1: |
|
531 |
+ prefix, suffix = tag.split(':', 1) |
|
532 |
+ else: |
|
533 |
+ prefix, suffix = '', tag |
|
534 |
+ prefix = self.namespacemap.get(prefix, prefix) |
|
535 |
+ if prefix: |
|
536 |
+ prefix = prefix + '_' |
|
537 |
+ |
|
538 |
+ # special hack for better tracking of empty textinput/image elements in illformed feeds |
|
539 |
+ if (not prefix) and tag not in ('title', 'link', 'description', 'name'): |
|
540 |
+ self.intextinput = 0 |
|
541 |
+ if (not prefix) and tag not in ('title', 'link', 'description', 'url', 'href', 'width', 'height'): |
|
542 |
+ self.inimage = 0 |
|
543 |
+ |
|
544 |
+ # call special handler (if defined) or default handler |
|
545 |
+ methodname = '_start_' + prefix + suffix |
|
546 |
+ try: |
|
547 |
+ method = getattr(self, methodname) |
|
548 |
+ return method(attrsD) |
|
549 |
+ except AttributeError: |
|
550 |
+ return self.push(prefix + suffix, 1) |
|
551 |
+ |
|
552 |
+ def unknown_endtag(self, tag): |
|
553 |
+ if _debug: sys.stderr.write('end %s\n' % tag) |
|
554 |
+ # match namespaces |
|
555 |
+ if tag.find(':') <> -1: |
|
556 |
+ prefix, suffix = tag.split(':', 1) |
|
557 |
+ else: |
|
558 |
+ prefix, suffix = '', tag |
|
559 |
+ prefix = self.namespacemap.get(prefix, prefix) |
|
560 |
+ if prefix: |
|
561 |
+ prefix = prefix + '_' |
|
562 |
+ if suffix == 'svg' and self.svgOK: self.svgOK -= 1 |
|
563 |
+ |
|
564 |
+ # call special handler (if defined) or default handler |
|
565 |
+ methodname = '_end_' + prefix + suffix |
|
566 |
+ try: |
|
567 |
+ if self.svgOK: raise AttributeError() |
|
568 |
+ method = getattr(self, methodname) |
|
569 |
+ method() |
|
570 |
+ except AttributeError: |
|
571 |
+ self.pop(prefix + suffix) |
|
572 |
+ |
|
573 |
+ # track inline content |
|
574 |
+ if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): |
|
575 |
+ # element declared itself as escaped markup, but it isn't really |
|
576 |
+ if tag in ['xhtml:div', 'div']: return # typepad does this 10/2007 |
|
577 |
+ self.contentparams['type'] = 'application/xhtml+xml' |
|
578 |
+ if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': |
|
579 |
+ tag = tag.split(':')[-1] |
|
580 |
+ self.handle_data('</%s>' % tag, escape=0) |
|
581 |
+ |
|
582 |
+ # track xml:base and xml:lang going out of scope |
|
583 |
+ if self.basestack: |
|
584 |
+ self.basestack.pop() |
|
585 |
+ if self.basestack and self.basestack[-1]: |
|
586 |
+ self.baseuri = self.basestack[-1] |
|
587 |
+ if self.langstack: |
|
588 |
+ self.langstack.pop() |
|
589 |
+ if self.langstack: # and (self.langstack[-1] is not None): |
|
590 |
+ self.lang = self.langstack[-1] |
|
591 |
+ |
|
592 |
+ def handle_charref(self, ref): |
|
593 |
+ # called for each character reference, e.g. for ' ', ref will be '160' |
|
594 |
+ if not self.elementstack: return |
|
595 |
+ ref = ref.lower() |
|
596 |
+ if ref in ('34', '38', '39', '60', '62', 'x22', 'x26', 'x27', 'x3c', 'x3e'): |
|
597 |
+ text = '&#%s;' % ref |
|
598 |
+ else: |
|
599 |
+ if ref[0] == 'x': |
|
600 |
+ c = int(ref[1:], 16) |
|
601 |
+ else: |
|
602 |
+ c = int(ref) |
|
603 |
+ text = unichr(c).encode('utf-8') |
|
604 |
+ self.elementstack[-1][2].append(text) |
|
605 |
+ |
|
606 |
+ def handle_entityref(self, ref): |
|
607 |
+ # called for each entity reference, e.g. for '©', ref will be 'copy' |
|
608 |
+ if not self.elementstack: return |
|
609 |
+ if _debug: sys.stderr.write('entering handle_entityref with %s\n' % ref) |
|
610 |
+ if ref in ('lt', 'gt', 'quot', 'amp', 'apos'): |
|
611 |
+ text = '&%s;' % ref |
|
612 |
+ elif ref in self.entities.keys(): |
|
613 |
+ text = self.entities[ref] |
|
614 |
+ if text.startswith('&#') and text.endswith(';'): |
|
615 |
+ return self.handle_entityref(text) |
|
616 |
+ else: |
|
617 |
+ try: name2codepoint[ref] |
|
618 |
+ except KeyError: text = '&%s;' % ref |
|
619 |
+ else: text = unichr(name2codepoint[ref]).encode('utf-8') |
|
620 |
+ self.elementstack[-1][2].append(text) |
|
621 |
+ |
|
622 |
+ def handle_data(self, text, escape=1): |
|
623 |
+ # called for each block of plain text, i.e. outside of any tag and |
|
624 |
+ # not containing any character or entity references |
|
625 |
+ if not self.elementstack: return |
|
626 |
+ if escape and self.contentparams.get('type') == 'application/xhtml+xml': |
|
627 |
+ text = _xmlescape(text) |
|
628 |
+ self.elementstack[-1][2].append(text) |
|
629 |
+ |
|
630 |
+ def handle_comment(self, text): |
|
631 |
+ # called for each comment, e.g. <!-- insert message here --> |
|
632 |
+ pass |
|
633 |
+ |
|
634 |
+ def handle_pi(self, text): |
|
635 |
+ # called for each processing instruction, e.g. <?instruction> |
|
636 |
+ pass |
|
637 |
+ |
|
638 |
+ def handle_decl(self, text): |
|
639 |
+ pass |
|
640 |
+ |
|
641 |
+ def parse_declaration(self, i): |
|
642 |
+ # override internal declaration handler to handle CDATA blocks |
|
643 |
+ if _debug: sys.stderr.write('entering parse_declaration\n') |
|
644 |
+ if self.rawdata[i:i+9] == '<![CDATA[': |
|
645 |
+ k = self.rawdata.find(']]>', i) |
|
646 |
+ if k == -1: k = len(self.rawdata) |
|
647 |
+ self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0) |
|
648 |
+ return k+3 |
|
649 |
+ else: |
|
650 |
+ k = self.rawdata.find('>', i) |
|
651 |
+ return k+1 |
|
652 |
+ |
|
653 |
+ def mapContentType(self, contentType): |
|
654 |
+ contentType = contentType.lower() |
|
655 |
+ if contentType == 'text': |
|
656 |
+ contentType = 'text/plain' |
|
657 |
+ elif contentType == 'html': |
|
658 |
+ contentType = 'text/html' |
|
659 |
+ elif contentType == 'xhtml': |
|
660 |
+ contentType = 'application/xhtml+xml' |
|
661 |
+ return contentType |
|
662 |
+ |
|
663 |
+ def trackNamespace(self, prefix, uri): |
|
664 |
+ loweruri = uri.lower() |
|
665 |
+ if (prefix, loweruri) == (None, 'http://my.netscape.com/rdf/simple/0.9/') and not self.version: |
|
666 |
+ self.version = 'rss090' |
|
667 |
+ if loweruri == 'http://purl.org/rss/1.0/' and not self.version: |
|
668 |
+ self.version = 'rss10' |
|
669 |
+ if loweruri == 'http://www.w3.org/2005/atom' and not self.version: |
|
670 |
+ self.version = 'atom10' |
|
671 |
+ if loweruri.find('backend.userland.com/rss') <> -1: |
|
672 |
+ # match any backend.userland.com namespace |
|
673 |
+ uri = 'http://backend.userland.com/rss' |
|
674 |
+ loweruri = uri |
|
675 |
+ if self._matchnamespaces.has_key(loweruri): |
|
676 |
+ self.namespacemap[prefix] = self._matchnamespaces[loweruri] |
|
677 |
+ self.namespacesInUse[self._matchnamespaces[loweruri]] = uri |
|
678 |
+ else: |
|
679 |
+ self.namespacesInUse[prefix or ''] = uri |
|
680 |
+ |
|
681 |
+ def resolveURI(self, uri): |
|
682 |
+ return _urljoin(self.baseuri or '', uri) |
|
683 |
+ |
|
684 |
+ def decodeEntities(self, element, data): |
|
685 |
+ return data |
|
686 |
+ |
|
687 |
+ def strattrs(self, attrs): |
|
688 |
+ return ''.join([' %s="%s"' % (t[0],_xmlescape(t[1],{'"':'"'})) for t in attrs]) |
|
689 |
+ |
|
690 |
+ def push(self, element, expectingText): |
|
691 |
+ self.elementstack.append([element, expectingText, []]) |
|
692 |
+ |
|
693 |
+ def pop(self, element, stripWhitespace=1): |
|
694 |
+ if not self.elementstack: return |
|
695 |
+ if self.elementstack[-1][0] != element: return |
|
696 |
+ |
|
697 |
+ element, expectingText, pieces = self.elementstack.pop() |
|
698 |
+ |
|
699 |
+ if self.version == 'atom10' and self.contentparams.get('type','text') == 'application/xhtml+xml': |
|
700 |
+ # remove enclosing child element, but only if it is a <div> and |
|
701 |
+ # only if all the remaining content is nested underneath it. |
|
702 |
+ # This means that the divs would be retained in the following: |
|
703 |
+ # <div>foo</div><div>bar</div> |
|
704 |
+ while pieces and len(pieces)>1 and not pieces[-1].strip(): |
|
705 |
+ del pieces[-1] |
|
706 |
+ while pieces and len(pieces)>1 and not pieces[0].strip(): |
|
707 |
+ del pieces[0] |
|
708 |
+ if pieces and (pieces[0] == '<div>' or pieces[0].startswith('<div ')) and pieces[-1]=='</div>': |
|
709 |
+ depth = 0 |
|
710 |
+ for piece in pieces[:-1]: |
|
711 |
+ if piece.startswith('</'): |
|
712 |
+ depth -= 1 |
|
713 |
+ if depth == 0: break |
|
714 |
+ elif piece.startswith('<') and not piece.endswith('/>'): |
|
715 |
+ depth += 1 |
|
716 |
+ else: |
|
717 |
+ pieces = pieces[1:-1] |
|
718 |
+ |
|
719 |
+ output = ''.join(pieces) |
|
720 |
+ if stripWhitespace: |
|
721 |
+ output = output.strip() |
|
722 |
+ if not expectingText: return output |
|
723 |
+ |
|
724 |
+ # decode base64 content |
|
725 |
+ if base64 and self.contentparams.get('base64', 0): |
|
726 |
+ try: |
|
727 |
+ output = base64.decodestring(output) |
|
728 |
+ except binascii.Error: |
|
729 |
+ pass |
|
730 |
+ except binascii.Incomplete: |
|
731 |
+ pass |
|
732 |
+ |
|
733 |
+ # resolve relative URIs |
|
734 |
+ if (element in self.can_be_relative_uri) and output: |
|
735 |
+ output = self.resolveURI(output) |
|
736 |
+ |
|
737 |
+ # decode entities within embedded markup |
|
738 |
+ if not self.contentparams.get('base64', 0): |
|
739 |
+ output = self.decodeEntities(element, output) |
|
740 |
+ |
|
741 |
+ if self.lookslikehtml(output): |
|
742 |
+ self.contentparams['type']='text/html' |
|
743 |
+ |
|
744 |
+ # remove temporary cruft from contentparams |
|
745 |
+ try: |
|
746 |
+ del self.contentparams['mode'] |
|
747 |
+ except KeyError: |
|
748 |
+ pass |
|
749 |
+ try: |
|
750 |
+ del self.contentparams['base64'] |
|
751 |
+ except KeyError: |
|
752 |
+ pass |
|
753 |
+ |
|
754 |
+ is_htmlish = self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types |
|
755 |
+ # resolve relative URIs within embedded markup |
|
756 |
+ if is_htmlish and RESOLVE_RELATIVE_URIS: |
|
757 |
+ if element in self.can_contain_relative_uris: |
|
758 |
+ output = _resolveRelativeURIs(output, self.baseuri, self.encoding, self.contentparams.get('type', 'text/html')) |
|
759 |
+ |
|
760 |
+ # parse microformats |
|
761 |
+ # (must do this before sanitizing because some microformats |
|
762 |
+ # rely on elements that we sanitize) |
|
763 |
+ if is_htmlish and element in ['content', 'description', 'summary']: |
|
764 |
+ mfresults = _parseMicroformats(output, self.baseuri, self.encoding) |
|
765 |
+ if mfresults: |
|
766 |
+ for tag in mfresults.get('tags', []): |
|
767 |
+ self._addTag(tag['term'], tag['scheme'], tag['label']) |
|
768 |
+ for enclosure in mfresults.get('enclosures', []): |
|
769 |
+ self._start_enclosure(enclosure) |
|
770 |
+ for xfn in mfresults.get('xfn', []): |
|
771 |
+ self._addXFN(xfn['relationships'], xfn['href'], xfn['name']) |
|
772 |
+ vcard = mfresults.get('vcard') |
|
773 |
+ if vcard: |
|
774 |
+ self._getContext()['vcard'] = vcard |
|
775 |
+ |
|
776 |
+ # sanitize embedded markup |
|
777 |
+ if is_htmlish and SANITIZE_HTML: |
|
778 |
+ if element in self.can_contain_dangerous_markup: |
|
779 |
+ output = _sanitizeHTML(output, self.encoding, self.contentparams.get('type', 'text/html')) |
|
780 |
+ |
|
781 |
+ if self.encoding and type(output) != type(u''): |
|
782 |
+ try: |
|
783 |
+ output = unicode(output, self.encoding) |
|
784 |
+ except: |
|
785 |
+ pass |
|
786 |
+ |
|
787 |
+ # address common error where people take data that is already |
|
788 |
+ # utf-8, presume that it is iso-8859-1, and re-encode it. |
|
789 |
+ if self.encoding=='utf-8' and type(output) == type(u''): |
|
790 |
+ try: |
|
791 |
+ output = unicode(output.encode('iso-8859-1'), 'utf-8') |
|
792 |
+ except: |
|
793 |
+ pass |
|
794 |
+ |
|
795 |
+ # map win-1252 extensions to the proper code points |
|
796 |
+ if type(output) == type(u''): |
|
797 |
+ output = u''.join([c in _cp1252.keys() and _cp1252[c] or c for c in output]) |
|
798 |
+ |
|
799 |
+ # categories/tags/keywords/whatever are handled in _end_category |
|
800 |
+ if element == 'category': |
|
801 |
+ return output |
|
802 |
+ |
|
803 |
+ if element == 'title' and self.hasTitle: |
|
804 |
+ return output |
|
805 |
+ |
|
806 |
+ # store output in appropriate place(s) |
|
807 |
+ if self.inentry and not self.insource: |
|
808 |
+ if element == 'content': |
|
809 |
+ self.entries[-1].setdefault(element, []) |
|
810 |
+ contentparams = copy.deepcopy(self.contentparams) |
|
811 |
+ contentparams['value'] = output |
|
812 |
+ self.entries[-1][element].append(contentparams) |
|
813 |
+ elif element == 'link': |
|
814 |
+ self.entries[-1][element] = output |
|
815 |
+ if output: |
|
816 |
+ self.entries[-1]['links'][-1]['href'] = output |
|
817 |
+ else: |
|
818 |
+ if element == 'description': |
|
819 |
+ element = 'summary' |
|
820 |
+ self.entries[-1][element] = output |
|
821 |
+ if self.incontent: |
|
822 |
+ contentparams = copy.deepcopy(self.contentparams) |
|
823 |
+ contentparams['value'] = output |
|
824 |
+ self.entries[-1][element + '_detail'] = contentparams |
|
825 |
+ elif (self.infeed or self.insource):# and (not self.intextinput) and (not self.inimage): |
|
826 |
+ context = self._getContext() |
|
827 |
+ if element == 'description': |
|
828 |
+ element = 'subtitle' |
|
829 |
+ context[element] = output |
|
830 |
+ if element == 'link': |
|
831 |
+ context['links'][-1]['href'] = output |
|
832 |
+ elif self.incontent: |
|
833 |
+ contentparams = copy.deepcopy(self.contentparams) |
|
834 |
+ contentparams['value'] = output |
|
835 |
+ context[element + '_detail'] = contentparams |
|
836 |
+ return output |
|
837 |
+ |
|
838 |
+ def pushContent(self, tag, attrsD, defaultContentType, expectingText): |
|
839 |
+ self.incontent += 1 |
|
840 |
+ if self.lang: self.lang=self.lang.replace('_','-') |
|
841 |
+ self.contentparams = FeedParserDict({ |
|
842 |
+ 'type': self.mapContentType(attrsD.get('type', defaultContentType)), |
|
843 |
+ 'language': self.lang, |
|
844 |
+ 'base': self.baseuri}) |
|
845 |
+ self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams) |
|
846 |
+ self.push(tag, expectingText) |
|
847 |
+ |
|
848 |
+ def popContent(self, tag): |
|
849 |
+ value = self.pop(tag) |
|
850 |
+ self.incontent -= 1 |
|
851 |
+ self.contentparams.clear() |
|
852 |
+ return value |
|
853 |
+ |
|
854 |
+ # a number of elements in a number of RSS variants are nominally plain |
|
855 |
+ # text, but this is routinely ignored. This is an attempt to detect |
|
856 |
+ # the most common cases. As false positives often result in silent |
|
857 |
+ # data loss, this function errs on the conservative side. |
|
858 |
+ def lookslikehtml(self, str): |
|
859 |
+ if self.version.startswith('atom'): return |
|
860 |
+ if self.contentparams.get('type','text/html') != 'text/plain': return |
|
861 |
+ |
|
862 |
+ # must have a close tag or a entity reference to qualify |
|
863 |
+ if not (re.search(r'</(\w+)>',str) or re.search("&#?\w+;",str)): return |
|
864 |
+ |
|
865 |
+ # all tags must be in a restricted subset of valid HTML tags |
|
866 |
+ if filter(lambda t: t.lower() not in _HTMLSanitizer.acceptable_elements, |
|
867 |
+ re.findall(r'</?(\w+)',str)): return |
|
868 |
+ |
|
869 |
+ # all entities must have been defined as valid HTML entities |
|
870 |
+ from htmlentitydefs import entitydefs |
|
871 |
+ if filter(lambda e: e not in entitydefs.keys(), |
|
872 |
+ re.findall(r'&(\w+);',str)): return |
|
873 |
+ |
|
874 |
+ return 1 |
|
875 |
+ |
|
876 |
+ def _mapToStandardPrefix(self, name): |
|
877 |
+ colonpos = name.find(':') |
|
878 |
+ if colonpos <> -1: |
|
879 |
+ prefix = name[:colonpos] |
|
880 |
+ suffix = name[colonpos+1:] |
|
881 |
+ prefix = self.namespacemap.get(prefix, prefix) |
|
882 |
+ name = prefix + ':' + suffix |
|
883 |
+ return name |
|
884 |
+ |
|
885 |
+ def _getAttribute(self, attrsD, name): |
|
886 |
+ return attrsD.get(self._mapToStandardPrefix(name)) |
|
887 |
+ |
|
888 |
+ def _isBase64(self, attrsD, contentparams): |
|
889 |
+ if attrsD.get('mode', '') == 'base64': |
|
890 |
+ return 1 |
|
891 |
+ if self.contentparams['type'].startswith('text/'): |
|
892 |
+ return 0 |
|
893 |
+ if self.contentparams['type'].endswith('+xml'): |
|
894 |
+ return 0 |
|
895 |
+ if self.contentparams['type'].endswith('/xml'): |
|
896 |
+ return 0 |
|
897 |
+ return 1 |
|
898 |
+ |
|
899 |
+ def _itsAnHrefDamnIt(self, attrsD): |
|
900 |
+ href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None))) |
|
901 |
+ if href: |
|
902 |
+ try: |
|
903 |
+ del attrsD['url'] |
|
904 |
+ except KeyError: |
|
905 |
+ pass |
|
906 |
+ try: |
|
907 |
+ del attrsD['uri'] |
|
908 |
+ except KeyError: |
|
909 |
+ pass |
|
910 |
+ attrsD['href'] = href |
|
911 |
+ return attrsD |
|
912 |
+ |
|
913 |
+ def _save(self, key, value): |
|
914 |
+ context = self._getContext() |
|
915 |
+ context.setdefault(key, value) |
|
916 |
+ |
|
917 |
+ def _start_rss(self, attrsD): |
|
918 |
+ versionmap = {'0.91': 'rss091u', |
|
919 |
+ '0.92': 'rss092', |
|
920 |
+ '0.93': 'rss093', |
|
921 |
+ '0.94': 'rss094'} |
|
922 |
+ if not self.version: |
|
923 |
+ attr_version = attrsD.get('version', '') |
|
924 |
+ version = versionmap.get(attr_version) |
|
925 |
+ if version: |
|
926 |
+ self.version = version |
|
927 |
+ elif attr_version.startswith('2.'): |
|
928 |
+ self.version = 'rss20' |
|
929 |
+ else: |
|
930 |
+ self.version = 'rss' |
|
931 |
+ |
|
932 |
+ def _start_dlhottitles(self, attrsD): |
|
933 |
+ self.version = 'hotrss' |
|
934 |
+ |
|
935 |
+ def _start_channel(self, attrsD): |
|
936 |
+ self.infeed = 1 |
|
937 |
+ self._cdf_common(attrsD) |
|
938 |
+ _start_feedinfo = _start_channel |
|
939 |
+ |
|
940 |
+ def _cdf_common(self, attrsD): |
|
941 |
+ if attrsD.has_key('lastmod'): |
|
942 |
+ self._start_modified({}) |
|
943 |
+ self.elementstack[-1][-1] = attrsD['lastmod'] |
|
944 |
+ self._end_modified() |
|
945 |
+ if attrsD.has_key('href'): |
|
946 |
+ self._start_link({}) |
|
947 |
+ self.elementstack[-1][-1] = attrsD['href'] |
|
948 |
+ self._end_link() |
|
949 |
+ |
|
950 |
+ def _start_feed(self, attrsD): |
|
951 |
+ self.infeed = 1 |
|
952 |
+ versionmap = {'0.1': 'atom01', |
|
953 |
+ '0.2': 'atom02', |
|
954 |
+ '0.3': 'atom03'} |
|
955 |
+ if not self.version: |
|
956 |
+ attr_version = attrsD.get('version') |
|
957 |
+ version = versionmap.get(attr_version) |
|
958 |
+ if version: |
|
959 |
+ self.version = version |
|
960 |
+ else: |
|
961 |
+ self.version = 'atom' |
|
962 |
+ |
|
963 |
+ def _end_channel(self): |
|
964 |
+ self.infeed = 0 |
|
965 |
+ _end_feed = _end_channel |
|
966 |
+ |
|
967 |
+ def _start_image(self, attrsD): |
|
968 |
+ context = self._getContext() |
|
969 |
+ context.setdefault('image', FeedParserDict()) |
|
970 |
+ self.inimage = 1 |
|
971 |
+ self.hasTitle = 0 |
|
972 |
+ self.push('image', 0) |
|
973 |
+ |
|
974 |
+ def _end_image(self): |
|
975 |
+ self.pop('image') |
|
976 |
+ self.inimage = 0 |
|
977 |
+ |
|
978 |
+ def _start_textinput(self, attrsD): |
|
979 |
+ context = self._getContext() |
|
980 |
+ context.setdefault('textinput', FeedParserDict()) |
|
981 |
+ self.intextinput = 1 |
|
982 |
+ self.hasTitle = 0 |
|
983 |
+ self.push('textinput', 0) |
|
984 |
+ _start_textInput = _start_textinput |
|
985 |
+ |
|
986 |
+ def _end_textinput(self): |
|
987 |
+ self.pop('textinput') |
|
988 |
+ self.intextinput = 0 |
|
989 |
+ _end_textInput = _end_textinput |
|
990 |
+ |
|
991 |
+ def _start_author(self, attrsD): |
|
992 |
+ self.inauthor = 1 |
|
993 |
+ self.push('author', 1) |
|
994 |
+ _start_managingeditor = _start_author |
|
995 |
+ _start_dc_author = _start_author |
|
996 |
+ _start_dc_creator = _start_author |
|
997 |
+ _start_itunes_author = _start_author |
|
998 |
+ |
|
999 |
+ def _end_author(self): |
|
1000 |
+ self.pop('author') |
|
1001 |
+ self.inauthor = 0 |
|
1002 |
+ self._sync_author_detail() |
|
1003 |
+ _end_managingeditor = _end_author |
|
1004 |
+ _end_dc_author = _end_author |
|
1005 |
+ _end_dc_creator = _end_author |
|
1006 |
+ _end_itunes_author = _end_author |
|
1007 |
+ |
|
1008 |
+ def _start_itunes_owner(self, attrsD): |
|
1009 |
+ self.inpublisher = 1 |
|
1010 |
+ self.push('publisher', 0) |
|
1011 |
+ |
|
1012 |
+ def _end_itunes_owner(self): |
|
1013 |
+ self.pop('publisher') |
|
1014 |
+ self.inpublisher = 0 |
|
1015 |
+ self._sync_author_detail('publisher') |
|
1016 |
+ |
|
1017 |
+ def _start_contributor(self, attrsD): |
|
1018 |
+ self.incontributor = 1 |
|
1019 |
+ context = self._getContext() |
|
1020 |
+ context.setdefault('contributors', []) |
|
1021 |
+ context['contributors'].append(FeedParserDict()) |
|
1022 |
+ self.push('contributor', 0) |
|
1023 |
+ |
|
1024 |
+ def _end_contributor(self): |
|
1025 |
+ self.pop('contributor') |
|
1026 |
+ self.incontributor = 0 |
|
1027 |
+ |
|
1028 |
+ def _start_dc_contributor(self, attrsD): |
|
1029 |
+ self.incontributor = 1 |
|
1030 |
+ context = self._getContext() |
|
1031 |
+ context.setdefault('contributors', []) |
|
1032 |
+ context['contributors'].append(FeedParserDict()) |
|
1033 |
+ self.push('name', 0) |
|
1034 |
+ |
|
1035 |
+ def _end_dc_contributor(self): |
|
1036 |
+ self._end_name() |
|
1037 |
+ self.incontributor = 0 |
|
1038 |
+ |
|
1039 |
+ def _start_name(self, attrsD): |
|
1040 |
+ self.push('name', 0) |
|
1041 |
+ _start_itunes_name = _start_name |
|
1042 |
+ |
|
1043 |
+ def _end_name(self): |
|
1044 |
+ value = self.pop('name') |
|
1045 |
+ if self.inpublisher: |
|
1046 |
+ self._save_author('name', value, 'publisher') |
|
1047 |
+ elif self.inauthor: |
|
1048 |
+ self._save_author('name', value) |
|
1049 |
+ elif self.incontributor: |
|
1050 |
+ self._save_contributor('name', value) |
|
1051 |
+ elif self.intextinput: |
|
1052 |
+ context = self._getContext() |
|
1053 |
+ context['name'] = value |
|
1054 |
+ _end_itunes_name = _end_name |
|
1055 |
+ |
|
1056 |
+ def _start_width(self, attrsD): |
|
1057 |
+ self.push('width', 0) |
|
1058 |
+ |
|
1059 |
+ def _end_width(self): |
|
1060 |
+ value = self.pop('width') |
|
1061 |
+ try: |
|
1062 |
+ value = int(value) |
|
1063 |
+ except: |
|
1064 |
+ value = 0 |
|
1065 |
+ if self.inimage: |
|
1066 |
+ context = self._getContext() |
|
1067 |
+ context['width'] = value |
|
1068 |
+ |
|
1069 |
+ def _start_height(self, attrsD): |
|
1070 |
+ self.push('height', 0) |
|
1071 |
+ |
|
1072 |
+ def _end_height(self): |
|
1073 |
+ value = self.pop('height') |
|
1074 |
+ try: |
|
1075 |
+ value = int(value) |
|
1076 |
+ except: |
|
1077 |
+ value = 0 |
|
1078 |
+ if self.inimage: |
|
1079 |
+ context = self._getContext() |
|
1080 |
+ context['height'] = value |
|
1081 |
+ |
|
1082 |
+ def _start_url(self, attrsD): |
|
1083 |
+ self.push('href', 1) |
|
1084 |
+ _start_homepage = _start_url |
|
1085 |
+ _start_uri = _start_url |
|
1086 |
+ |
|
1087 |
+ def _end_url(self): |
|
1088 |
+ value = self.pop('href') |
|
1089 |
+ if self.inauthor: |
|
1090 |
+ self._save_author('href', value) |
|
1091 |
+ elif self.incontributor: |
|
1092 |
+ self._save_contributor('href', value) |
|
1093 |
+ _end_homepage = _end_url |
|
1094 |
+ _end_uri = _end_url |
|
1095 |
+ |
|
1096 |
+ def _start_email(self, attrsD): |
|
1097 |
+ self.push('email', 0) |
|
1098 |
+ _start_itunes_email = _start_email |
|
1099 |
+ |
|
1100 |
+ def _end_email(self): |
|
1101 |
+ value = self.pop('email') |
|
1102 |
+ if self.inpublisher: |
|
1103 |
+ self._save_author('email', value, 'publisher') |
|
1104 |
+ elif self.inauthor: |
|
1105 |
+ self._save_author('email', value) |
|
1106 |
+ elif self.incontributor: |
|
1107 |
+ self._save_contributor('email', value) |
|
1108 |
+ _end_itunes_email = _end_email |
|
1109 |
+ |
|
1110 |
+ def _getContext(self): |
|
1111 |
+ if self.insource: |
|
1112 |
+ context = self.sourcedata |
|
1113 |
+ elif self.inimage: |
|
1114 |
+ context = self.feeddata['image'] |
|
1115 |
+ elif self.intextinput: |
|
1116 |
+ context = self.feeddata['textinput'] |
|
1117 |
+ elif self.inentry: |
|
1118 |
+ context = self.entries[-1] |
|
1119 |
+ else: |
|
1120 |
+ context = self.feeddata |
|
1121 |
+ return context |
|
1122 |
+ |
|
1123 |
+ def _save_author(self, key, value, prefix='author'): |
|
1124 |
+ context = self._getContext() |
|
1125 |
+ context.setdefault(prefix + '_detail', FeedParserDict()) |
|
1126 |
+ context[prefix + '_detail'][key] = value |
|
1127 |
+ self._sync_author_detail() |
|
1128 |
+ |
|
1129 |
+ def _save_contributor(self, key, value): |
|
1130 |
+ context = self._getContext() |
|
1131 |
+ context.setdefault('contributors', [FeedParserDict()]) |
|
1132 |
+ context['contributors'][-1][key] = value |
|
1133 |
+ |
|
1134 |
+ def _sync_author_detail(self, key='author'): |
|
1135 |
+ context = self._getContext() |
|
1136 |
+ detail = context.get('%s_detail' % key) |
|
1137 |
+ if detail: |
|
1138 |
+ name = detail.get('name') |
|
1139 |
+ email = detail.get('email') |
|
1140 |
+ if name and email: |
|
1141 |
+ context[key] = '%s (%s)' % (name, email) |
|
1142 |
+ elif name: |
|
1143 |
+ context[key] = name |
|
1144 |
+ elif email: |
|
1145 |
+ context[key] = email |
|
1146 |
+ else: |
|
1147 |
+ author, email = context.get(key), None |
|
1148 |
+ if not author: return |
|
1149 |
+ emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))(\?subject=\S+)?''', author) |
|
1150 |
+ if emailmatch: |
|
1151 |
+ email = emailmatch.group(0) |
|
1152 |
+ # probably a better way to do the following, but it passes all the tests |
|
1153 |
+ author = author.replace(email, '') |
|
1154 |
+ author = author.replace('()', '') |
|
1155 |
+ author = author.replace('<>', '') |
|
1156 |
+ author = author.replace('<>', '') |
|
1157 |
+ author = author.strip() |
|
1158 |
+ if author and (author[0] == '('): |
|
1159 |
+ author = author[1:] |
|
1160 |
+ if author and (author[-1] == ')'): |
|
1161 |
+ author = author[:-1] |
|
1162 |
+ author = author.strip() |
|
1163 |
+ if author or email: |
|
1164 |
+ context.setdefault('%s_detail' % key, FeedParserDict()) |
|
1165 |
+ if author: |
|
1166 |
+ context['%s_detail' % key]['name'] = author |
|
1167 |
+ if email: |
|
1168 |
+ context['%s_detail' % key]['email'] = email |
|
1169 |
+ |
|
1170 |
+ def _start_subtitle(self, attrsD): |
|
1171 |
+ self.pushContent('subtitle', attrsD, 'text/plain', 1) |
|
1172 |
+ _start_tagline = _start_subtitle |
|
1173 |
+ _start_itunes_subtitle = _start_subtitle |
|
1174 |
+ |
|
1175 |
+ def _end_subtitle(self): |
|
1176 |
+ self.popContent('subtitle') |
|
1177 |
+ _end_tagline = _end_subtitle |
|
1178 |
+ _end_itunes_subtitle = _end_subtitle |
|
1179 |
+ |
|
1180 |
+ def _start_rights(self, attrsD): |
|
1181 |
+ self.pushContent('rights', attrsD, 'text/plain', 1) |
|
1182 |
+ _start_dc_rights = _start_rights |
|
1183 |
+ _start_copyright = _start_rights |
|
1184 |
+ |
|
1185 |
+ def _end_rights(self): |
|
1186 |
+ self.popContent('rights') |
|
1187 |
+ _end_dc_rights = _end_rights |
|
1188 |
+ _end_copyright = _end_rights |
|
1189 |
+ |
|
1190 |
+ def _start_item(self, attrsD): |
|
1191 |
+ self.entries.append(FeedParserDict()) |
|
1192 |
+ self.push('item', 0) |
|
1193 |
+ self.inentry = 1 |
|
1194 |
+ self.guidislink = 0 |
|
1195 |
+ self.hasTitle = 0 |
|
1196 |
+ id = self._getAttribute(attrsD, 'rdf:about') |
|
1197 |
+ if id: |
|
1198 |
+ context = self._getContext() |
|
1199 |
+ context['id'] = id |
|
1200 |
+ self._cdf_common(attrsD) |
|
1201 |
+ _start_entry = _start_item |
|
1202 |
+ _start_product = _start_item |
|
1203 |
+ |
|
1204 |
+ def _end_item(self): |
|
1205 |
+ self.pop('item') |
|
1206 |
+ self.inentry = 0 |
|
1207 |
+ _end_entry = _end_item |
|
1208 |
+ |
|
1209 |
+ def _start_dc_language(self, attrsD): |
|
1210 |
+ self.push('language', 1) |
|
1211 |
+ _start_language = _start_dc_language |
|
1212 |
+ |
|
1213 |
+ def _end_dc_language(self): |
|
1214 |
+ self.lang = self.pop('language') |
|
1215 |
+ _end_language = _end_dc_language |
|
1216 |
+ |
|
1217 |
+ def _start_dc_publisher(self, attrsD): |
|
1218 |
+ self.push('publisher', 1) |
|
1219 |
+ _start_webmaster = _start_dc_publisher |
|
1220 |
+ |
|
1221 |
+ def _end_dc_publisher(self): |
|
1222 |
+ self.pop('publisher') |
|
1223 |
+ self._sync_author_detail('publisher') |
|
1224 |
+ _end_webmaster = _end_dc_publisher |
|
1225 |
+ |
|
1226 |
+ def _start_published(self, attrsD): |
|
1227 |
+ self.push('published', 1) |
|
1228 |
+ _start_dcterms_issued = _start_published |
|
1229 |
+ _start_issued = _start_published |
|
1230 |
+ |
|
1231 |
+ def _end_published(self): |
|
1232 |
+ value = self.pop('published') |
|
1233 |
+ self._save('published_parsed', _parse_date(value)) |
|
1234 |
+ _end_dcterms_issued = _end_published |
|
1235 |
+ _end_issued = _end_published |
|
1236 |
+ |
|
1237 |
+ def _start_updated(self, attrsD): |
|
1238 |
+ self.push('updated', 1) |
|
1239 |
+ _start_modified = _start_updated |
|
1240 |
+ _start_dcterms_modified = _start_updated |
|
1241 |
+ _start_pubdate = _start_updated |
|
1242 |
+ _start_dc_date = _start_updated |
|
1243 |
+ |
|
1244 |
+ def _end_updated(self): |
|
1245 |
+ value = self.pop('updated') |
|
1246 |
+ parsed_value = _parse_date(value) |
|
1247 |
+ self._save('updated_parsed', parsed_value) |
|
1248 |
+ _end_modified = _end_updated |
|
1249 |
+ _end_dcterms_modified = _end_updated |
|
1250 |
+ _end_pubdate = _end_updated |
|
1251 |
+ _end_dc_date = _end_updated |
|
1252 |
+ |
|
1253 |
+ def _start_created(self, attrsD): |
|
1254 |
+ self.push('created', 1) |
|
1255 |
+ _start_dcterms_created = _start_created |
|
1256 |
+ |
|
1257 |
+ def _end_created(self): |
|
1258 |
+ value = self.pop('created') |
|
1259 |
+ self._save('created_parsed', _parse_date(value)) |
|
1260 |
+ _end_dcterms_created = _end_created |
|
1261 |
+ |
|
1262 |
+ def _start_expirationdate(self, attrsD): |
|
1263 |
+ self.push('expired', 1) |
|
1264 |
+ |
|
1265 |
+ def _end_expirationdate(self): |
|
1266 |
+ self._save('expired_parsed', _parse_date(self.pop('expired'))) |
|
1267 |
+ |
|
1268 |
+ def _start_cc_license(self, attrsD): |
|
1269 |
+ context = self._getContext() |
|
1270 |
+ value = self._getAttribute(attrsD, 'rdf:resource') |
|
1271 |
+ attrsD = FeedParserDict() |
|
1272 |
+ attrsD['rel']='license' |
|
1273 |
+ if value: attrsD['href']=value |
|
1274 |
+ context.setdefault('links', []).append(attrsD) |
|
1275 |
+ |
|
1276 |
+ def _start_creativecommons_license(self, attrsD): |
|
1277 |
+ self.push('license', 1) |
|
1278 |
+ _start_creativeCommons_license = _start_creativecommons_license |
|
1279 |
+ |
|
1280 |
+ def _end_creativecommons_license(self): |
|
1281 |
+ value = self.pop('license') |
|
1282 |
+ context = self._getContext() |
|
1283 |
+ attrsD = FeedParserDict() |
|
1284 |
+ attrsD['rel']='license' |
|
1285 |
+ if value: attrsD['href']=value |
|
1286 |
+ context.setdefault('links', []).append(attrsD) |
|
1287 |
+ del context['license'] |
|
1288 |
+ _end_creativeCommons_license = _end_creativecommons_license |
|
1289 |
+ |
|
1290 |
+ def _addXFN(self, relationships, href, name): |
|
1291 |
+ context = self._getContext() |
|
1292 |
+ xfn = context.setdefault('xfn', []) |
|
1293 |
+ value = FeedParserDict({'relationships': relationships, 'href': href, 'name': name}) |
|
1294 |
+ if value not in xfn: |
|
1295 |
+ xfn.append(value) |
|
1296 |
+ |
|
1297 |
+ def _addTag(self, term, scheme, label): |
|
1298 |
+ context = self._getContext() |
|
1299 |
+ tags = context.setdefault('tags', []) |
|
1300 |
+ if (not term) and (not scheme) and (not label): return |
|
1301 |
+ value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label}) |
|
1302 |
+ if value not in tags: |
|
1303 |
+ tags.append(value) |
|
1304 |
+ |
|
1305 |
+ def _start_category(self, attrsD): |
|
1306 |
+ if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD)) |
|
1307 |
+ term = attrsD.get('term') |
|
1308 |
+ scheme = attrsD.get('scheme', attrsD.get('domain')) |
|
1309 |
+ label = attrsD.get('label') |
|
1310 |
+ self._addTag(term, scheme, label) |
|
1311 |
+ self.push('category', 1) |
|
1312 |
+ _start_dc_subject = _start_category |
|
1313 |
+ _start_keywords = _start_category |
|
1314 |
+ |
|
1315 |
+ def _end_itunes_keywords(self): |
|
1316 |
+ for term in self.pop('itunes_keywords').split(): |
|
1317 |
+ self._addTag(term, 'http://www.itunes.com/', None) |
|
1318 |
+ |
|
1319 |
+ def _start_itunes_category(self, attrsD): |
|
1320 |
+ self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None) |
|
1321 |
+ self.push('category', 1) |
|
1322 |
+ |
|
1323 |
+ def _end_category(self): |
|
1324 |
+ value = self.pop('category') |
|
1325 |
+ if not value: return |
|
1326 |
+ context = self._getContext() |
|
1327 |
+ tags = context['tags'] |
|
1328 |
+ if value and len(tags) and not tags[-1]['term']: |
|
1329 |
+ tags[-1]['term'] = value |
|
1330 |
+ else: |
|
1331 |
+ self._addTag(value, None, None) |
|
1332 |
+ _end_dc_subject = _end_category |
|
1333 |
+ _end_keywords = _end_category |
|
1334 |
+ _end_itunes_category = _end_category |
|
1335 |
+ |
|
1336 |
+ def _start_cloud(self, attrsD): |
|
1337 |
+ self._getContext()['cloud'] = FeedParserDict(attrsD) |
|
1338 |
+ |
|
1339 |
+ def _start_link(self, attrsD): |
|
1340 |
+ attrsD.setdefault('rel', 'alternate') |
|
1341 |
+ if attrsD['rel'] == 'self': |
|
1342 |
+ attrsD.setdefault('type', 'application/atom+xml') |
|
1343 |
+ else: |
|
1344 |
+ attrsD.setdefault('type', 'text/html') |
|
1345 |
+ context = self._getContext() |
|
1346 |
+ attrsD = self._itsAnHrefDamnIt(attrsD) |
|
1347 |
+ if attrsD.has_key('href'): |
|
1348 |
+ attrsD['href'] = self.resolveURI(attrsD['href']) |
|
1349 |
+ if attrsD.get('rel')=='enclosure' and not context.get('id'): |
|
1350 |
+ context['id'] = attrsD.get('href') |
|
1351 |
+ expectingText = self.infeed or self.inentry or self.insource |
|
1352 |
+ context.setdefault('links', []) |
|
1353 |
+ context['links'].append(FeedParserDict(attrsD)) |
|
1354 |
+ if attrsD.has_key('href'): |
|
1355 |
+ expectingText = 0 |
|
1356 |
+ if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types): |
|
1357 |
+ context['link'] = attrsD['href'] |
|
1358 |
+ else: |
|
1359 |
+ self.push('link', expectingText) |
|
1360 |
+ _start_producturl = _start_link |
|
1361 |
+ |
|
1362 |
+ def _end_link(self): |
|
1363 |
+ value = self.pop('link') |
|
1364 |
+ context = self._getContext() |
|
1365 |
+ _end_producturl = _end_link |
|
1366 |
+ |
|
1367 |
+ def _start_guid(self, attrsD): |
|
1368 |
+ self.guidislink = (attrsD.get('ispermalink', 'true') == 'true') |
|
1369 |
+ self.push('id', 1) |
|
1370 |
+ |
|
1371 |
+ def _end_guid(self): |
|
1372 |
+ value = self.pop('id') |
|
1373 |
+ self._save('guidislink', self.guidislink and not self._getContext().has_key('link')) |
|
1374 |
+ if self.guidislink: |
|
1375 |
+ # guid acts as link, but only if 'ispermalink' is not present or is 'true', |
|
1376 |
+ # and only if the item doesn't already have a link element |
|
1377 |
+ self._save('link', value) |
|
1378 |
+ |
|
1379 |
+ def _start_title(self, attrsD): |
|
1380 |
+ if self.svgOK: return self.unknown_starttag('title', attrsD.items()) |
|
1381 |
+ self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) |
|
1382 |
+ _start_dc_title = _start_title |
|
1383 |
+ _start_media_title = _start_title |
|
1384 |
+ |
|
1385 |
+ def _end_title(self): |
|
1386 |
+ if self.svgOK: return |
|
1387 |
+ value = self.popContent('title') |
|
1388 |
+ if not value: return |
|
1389 |
+ context = self._getContext() |
|
1390 |
+ self.hasTitle = 1 |
|
1391 |
+ _end_dc_title = _end_title |
|
1392 |
+ |
|
1393 |
+ def _end_media_title(self): |
|
1394 |
+ hasTitle = self.hasTitle |
|
1395 |
+ self._end_title() |
|
1396 |
+ self.hasTitle = hasTitle |
|
1397 |
+ |
|
1398 |
+ def _start_description(self, attrsD): |
|
1399 |
+ context = self._getContext() |
|
1400 |
+ if context.has_key('summary'): |
|
1401 |
+ self._summaryKey = 'content' |
|
1402 |
+ self._start_content(attrsD) |
|
1403 |
+ else: |
|
1404 |
+ self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource) |
|
1405 |
+ _start_dc_description = _start_description |
|
1406 |
+ |
|
1407 |
+ def _start_abstract(self, attrsD): |
|
1408 |
+ self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) |
|
1409 |
+ |
|
1410 |
+ def _end_description(self): |
|
1411 |
+ if self._summaryKey == 'content': |
|
1412 |
+ self._end_content() |
|
1413 |
+ else: |
|
1414 |
+ value = self.popContent('description') |
|
1415 |
+ self._summaryKey = None |
|
1416 |
+ _end_abstract = _end_description |
|
1417 |
+ _end_dc_description = _end_description |
|
1418 |
+ |
|
1419 |
+ def _start_info(self, attrsD): |
|
1420 |
+ self.pushContent('info', attrsD, 'text/plain', 1) |
|
1421 |
+ _start_feedburner_browserfriendly = _start_info |
|
1422 |
+ |
|
1423 |
+ def _end_info(self): |
|
1424 |
+ self.popContent('info') |
|
1425 |
+ _end_feedburner_browserfriendly = _end_info |
|
1426 |
+ |
|
1427 |
+ def _start_generator(self, attrsD): |
|
1428 |
+ if attrsD: |
|
1429 |
+ attrsD = self._itsAnHrefDamnIt(attrsD) |
|
1430 |
+ if attrsD.has_key('href'): |
|
1431 |
+ attrsD['href'] = self.resolveURI(attrsD['href']) |
|
1432 |
+ self._getContext()['generator_detail'] = FeedParserDict(attrsD) |
|
1433 |
+ self.push('generator', 1) |
|
1434 |
+ |
|
1435 |
+ def _end_generator(self): |
|
1436 |
+ value = self.pop('generator') |
|
1437 |
+ context = self._getContext() |
|
1438 |
+ if context.has_key('generator_detail'): |
|
1439 |
+ context['generator_detail']['name'] = value |
|
1440 |
+ |
|
1441 |
+ def _start_admin_generatoragent(self, attrsD): |
|
1442 |
+ self.push('generator', 1) |
|
1443 |
+ value = self._getAttribute(attrsD, 'rdf:resource') |
|
1444 |
+ if value: |
|
1445 |
+ self.elementstack[-1][2].append(value) |
|
1446 |
+ self.pop('generator') |
|
1447 |
+ self._getContext()['generator_detail'] = FeedParserDict({'href': value}) |
|
1448 |
+ |
|
1449 |
+ def _start_admin_errorreportsto(self, attrsD): |
|
1450 |
+ self.push('errorreportsto', 1) |
|
1451 |
+ value = self._getAttribute(attrsD, 'rdf:resource') |
|
1452 |
+ if value: |
|
1453 |
+ self.elementstack[-1][2].append(value) |
|
1454 |
+ self.pop('errorreportsto') |
|
1455 |
+ |
|
1456 |
+ def _start_summary(self, attrsD): |
|
1457 |
+ context = self._getContext() |
|
1458 |
+ if context.has_key('summary'): |
|
1459 |
+ self._summaryKey = 'content' |
|
1460 |
+ self._start_content(attrsD) |
|
1461 |
+ else: |
|
1462 |
+ self._summaryKey = 'summary' |
|
1463 |
+ self.pushContent(self._summaryKey, attrsD, 'text/plain', 1) |
|
1464 |
+ _start_itunes_summary = _start_summary |
|
1465 |
+ |
|
1466 |
+ def _end_summary(self): |
|
1467 |
+ if self._summaryKey == 'content': |
|
1468 |
+ self._end_content() |
|
1469 |
+ else: |
|
1470 |
+ self.popContent(self._summaryKey or 'summary') |
|
1471 |
+ self._summaryKey = None |
|
1472 |
+ _end_itunes_summary = _end_summary |
|
1473 |
+ |
|
1474 |
+ def _start_enclosure(self, attrsD): |
|
1475 |
+ attrsD = self._itsAnHrefDamnIt(attrsD) |
|
1476 |
+ context = self._getContext() |
|
1477 |
+ attrsD['rel']='enclosure' |
|
1478 |
+ context.setdefault('links', []).append(FeedParserDict(attrsD)) |
|
1479 |
+ href = attrsD.get('href') |
|
1480 |
+ if href and not context.get('id'): |
|
1481 |
+ context['id'] = href |
|
1482 |
+ |
|
1483 |
+ def _start_source(self, attrsD): |
|
1484 |
+ self.insource = 1 |
|
1485 |
+ self.hasTitle = 0 |
|
1486 |
+ |
|
1487 |
+ def _end_source(self): |
|
1488 |
+ self.insource = 0 |
|
1489 |
+ self._getContext()['source'] = copy.deepcopy(self.sourcedata) |
|
1490 |
+ self.sourcedata.clear() |
|
1491 |
+ |
|
1492 |
+ def _start_content(self, attrsD): |
|
1493 |
+ self.pushContent('content', attrsD, 'text/plain', 1) |
|
1494 |
+ src = attrsD.get('src') |
|
1495 |
+ if src: |
|
1496 |
+ self.contentparams['src'] = src |
|
1497 |
+ self.push('content', 1) |
|
1498 |
+ |
|
1499 |
+ def _start_prodlink(self, attrsD): |
|
1500 |
+ self.pushContent('content', attrsD, 'text/html', 1) |
|
1501 |
+ |
|
1502 |
+ def _start_body(self, attrsD): |
|
1503 |
+ self.pushContent('content', attrsD, 'application/xhtml+xml', 1) |
|
1504 |
+ _start_xhtml_body = _start_body |
|
1505 |
+ |
|
1506 |
+ def _start_content_encoded(self, attrsD): |
|
1507 |
+ self.pushContent('content', attrsD, 'text/html', 1) |
|
1508 |
+ _start_fullitem = _start_content_encoded |
|
1509 |
+ |
|
1510 |
+ def _end_content(self): |
|
1511 |
+ copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types) |
|
1512 |
+ value = self.popContent('content') |
|
1513 |
+ if copyToDescription: |
|
1514 |
+ self._save('description', value) |
|
1515 |
+ |
|
1516 |
+ _end_body = _end_content |
|
1517 |
+ _end_xhtml_body = _end_content |
|
1518 |
+ _end_content_encoded = _end_content |
|
1519 |
+ _end_fullitem = _end_content |
|
1520 |
+ _end_prodlink = _end_content |
|
1521 |
+ |
|
1522 |
+ def _start_itunes_image(self, attrsD): |
|
1523 |
+ self.push('itunes_image', 0) |
|
1524 |
+ self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')}) |
|
1525 |
+ _start_itunes_link = _start_itunes_image |
|
1526 |
+ |
|
1527 |
+ def _end_itunes_block(self): |
|
1528 |
+ value = self.pop('itunes_block', 0) |
|
1529 |
+ self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0 |
|
1530 |
+ |
|
1531 |
+ def _end_itunes_explicit(self): |
|
1532 |
+ value = self.pop('itunes_explicit', 0) |
|
1533 |
+ self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0 |
|
1534 |
+ |
|
1535 |
+if _XML_AVAILABLE: |
|
1536 |
+ class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler): |
|
1537 |
+ def __init__(self, baseuri, baselang, encoding): |
|
1538 |
+ if _debug: sys.stderr.write('trying StrictFeedParser\n') |
|
1539 |
+ xml.sax.handler.ContentHandler.__init__(self) |
|
1540 |
+ _FeedParserMixin.__init__(self, baseuri, baselang, encoding) |
|
1541 |
+ self.bozo = 0 |
|
1542 |
+ self.exc = None |
|
1543 |
+ |
|
1544 |
+ def startPrefixMapping(self, prefix, uri): |
|
1545 |
+ self.trackNamespace(prefix, uri) |
|
1546 |
+ |
|
1547 |
+ def startElementNS(self, name, qname, attrs): |
|
1548 |
+ namespace, localname = name |
|
1549 |
+ lowernamespace = str(namespace or '').lower() |
|
1550 |
+ if lowernamespace.find('backend.userland.com/rss') <> -1: |
|
1551 |
+ # match any backend.userland.com namespace |
|
1552 |
+ namespace = 'http://backend.userland.com/rss' |
|
1553 |
+ lowernamespace = namespace |
|
1554 |
+ if qname and qname.find(':') > 0: |
|
1555 |
+ givenprefix = qname.split(':')[0] |
|
1556 |
+ else: |
|
1557 |
+ givenprefix = None |
|
1558 |
+ prefix = self._matchnamespaces.get(lowernamespace, givenprefix) |
|
1559 |
+ if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix): |
|
1560 |
+ raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix |
|
1561 |
+ localname = str(localname).lower() |
|
1562 |
+ |
|
1563 |
+ # qname implementation is horribly broken in Python 2.1 (it |
|
1564 |
+ # doesn't report any), and slightly broken in Python 2.2 (it |
|
1565 |
+ # doesn't report the xml: namespace). So we match up namespaces |
|
1566 |
+ # with a known list first, and then possibly override them with |
|
1567 |
+ # the qnames the SAX parser gives us (if indeed it gives us any |
|
1568 |
+ # at all). Thanks to MatejC for helping me test this and |
|
1569 |
+ # tirelessly telling me that it didn't work yet. |
|
1570 |
+ attrsD = {} |
|
1571 |
+ if localname=='math' and namespace=='http://www.w3.org/1998/Math/MathML': |
|
1572 |
+ attrsD['xmlns']=namespace |
|
1573 |
+ if localname=='svg' and namespace=='http://www.w3.org/2000/svg': |
|
1574 |
+ attrsD['xmlns']=namespace |
|
1575 |
+ |
|
1576 |
+ if prefix: |
|
1577 |
+ localname = prefix.lower() + ':' + localname |
|
1578 |
+ elif namespace and not qname: #Expat |
|
1579 |
+ for name,value in self.namespacesInUse.items(): |
|
1580 |
+ if name and value == namespace: |
|
1581 |
+ localname = name + ':' + localname |
|
1582 |
+ break |
|
1583 |
+ if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname)) |
|
1584 |
+ |
|
1585 |
+ for (namespace, attrlocalname), attrvalue in attrs._attrs.items(): |
|
1586 |
+ lowernamespace = (namespace or '').lower() |
|
1587 |
+ prefix = self._matchnamespaces.get(lowernamespace, '') |
|
1588 |
+ if prefix: |
|
1589 |
+ attrlocalname = prefix + ':' + attrlocalname |
|
1590 |
+ attrsD[str(attrlocalname).lower()] = attrvalue |
|
1591 |
+ for qname in attrs.getQNames(): |
|
1592 |
+ attrsD[str(qname).lower()] = attrs.getValueByQName(qname) |
|
1593 |
+ self.unknown_starttag(localname, attrsD.items()) |
|
1594 |
+ |
|
1595 |
+ def characters(self, text): |
|
1596 |
+ self.handle_data(text) |
|
1597 |
+ |
|
1598 |
+ def endElementNS(self, name, qname): |
|
1599 |
+ namespace, localname = name |
|
1600 |
+ lowernamespace = str(namespace or '').lower() |
|
1601 |
+ if qname and qname.find(':') > 0: |
|
1602 |
+ givenprefix = qname.split(':')[0] |
|
1603 |
+ else: |
|
1604 |
+ givenprefix = '' |
|
1605 |
+ prefix = self._matchnamespaces.get(lowernamespace, givenprefix) |
|
1606 |
+ if prefix: |
|
1607 |
+ localname = prefix + ':' + localname |
|
1608 |
+ elif namespace and not qname: #Expat |
|
1609 |
+ for name,value in self.namespacesInUse.items(): |
|
1610 |
+ if name and value == namespace: |
|
1611 |
+ localname = name + ':' + localname |
|
1612 |
+ break |
|
1613 |
+ localname = str(localname).lower() |
|
1614 |
+ self.unknown_endtag(localname) |
|
1615 |
+ |
|
1616 |
+ def error(self, exc): |
|
1617 |
+ self.bozo = 1 |
|
1618 |
+ self.exc = exc |
|
1619 |
+ |
|
1620 |
+ def fatalError(self, exc): |
|
1621 |
+ self.error(exc) |
|
1622 |
+ raise exc |
|
1623 |
+ |
|
1624 |
+class _BaseHTMLProcessor(sgmllib.SGMLParser): |
|
1625 |
+ special = re.compile('''[<>'"]''') |
|
1626 |
+ bare_ampersand = re.compile("&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)") |
|
1627 |
+ elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr', |
|
1628 |
+ 'img', 'input', 'isindex', 'link', 'meta', 'param'] |
|
1629 |
+ |
|
1630 |
+ def __init__(self, encoding, type): |
|
1631 |
+ self.encoding = encoding |
|
1632 |
+ self.type = type |
|
1633 |
+ if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding) |
|
1634 |
+ sgmllib.SGMLParser.__init__(self) |
|
1635 |
+ |
|
1636 |
+ def reset(self): |
|
1637 |
+ self.pieces = [] |
|
1638 |
+ sgmllib.SGMLParser.reset(self) |
|
1639 |
+ |
|
1640 |
+ def _shorttag_replace(self, match): |
|
1641 |
+ tag = match.group(1) |
|
1642 |
+ if tag in self.elements_no_end_tag: |
|
1643 |
+ return '<' + tag + ' />' |
|
1644 |
+ else: |
|
1645 |
+ return '<' + tag + '></' + tag + '>' |
|
1646 |
+ |
|
1647 |
+ def parse_starttag(self,i): |
|
1648 |
+ j=sgmllib.SGMLParser.parse_starttag(self, i) |
|
1649 |
+ if self.type == 'application/xhtml+xml': |
|
1650 |
+ if j>2 and self.rawdata[j-2:j]=='/>': |
|
1651 |
+ self.unknown_endtag(self.lasttag) |
|
1652 |
+ return j |
|
1653 |
+ |
|
1654 |
+ def feed(self, data): |
|
1655 |
+ data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'<!\1', data) |
|
1656 |
+ #data = re.sub(r'<(\S+?)\s*?/>', self._shorttag_replace, data) # bug [ 1399464 ] Bad regexp for _shorttag_replace |
|
1657 |
+ data = re.sub(r'<([^<\s]+?)\s*/>', self._shorttag_replace, data) |
|
1658 |
+ data = data.replace(''', "'") |
|
1659 |
+ data = data.replace('"', '"') |
|
1660 |
+ if self.encoding and type(data) == type(u''): |
|
1661 |
+ data = data.encode(self.encoding) |
|
1662 |
+ sgmllib.SGMLParser.feed(self, data) |
|
1663 |
+ sgmllib.SGMLParser.close(self) |
|
1664 |
+ |
|
1665 |
+ def normalize_attrs(self, attrs): |
|
1666 |
+ if not attrs: return attrs |
|
1667 |
+ # utility method to be called by descendants |
|
1668 |
+ attrs = dict([(k.lower(), v) for k, v in attrs]).items() |
|
1669 |
+ attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] |
|
1670 |
+ attrs.sort() |
|
1671 |
+ return attrs |
|
1672 |
+ |
|
1673 |
+ def unknown_starttag(self, tag, attrs): |
|
1674 |
+ # called for each start tag |
|
1675 |
+ # attrs is a list of (attr, value) tuples |
|
1676 |
+ # e.g. for <pre class='screen'>, tag='pre', attrs=[('class', 'screen')] |
|
1677 |
+ if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag) |
|
1678 |
+ uattrs = [] |
|
1679 |
+ strattrs='' |
|
1680 |
+ if attrs: |
|
1681 |
+ for key, value in attrs: |
|
1682 |
+ value=value.replace('>','>').replace('<','<').replace('"','"') |
|
1683 |
+ value = self.bare_ampersand.sub("&", value) |
|
1684 |
+ # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds |
|
1685 |
+ if type(value) != type(u''): |
|
1686 |
+ try: |
|
1687 |
+ value = unicode(value, self.encoding) |
|
1688 |
+ except: |
|
1689 |
+ value = unicode(value, 'iso-8859-1') |
|
1690 |
+ uattrs.append((unicode(key, self.encoding), value)) |
|
1691 |
+ strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]) |
|
1692 |
+ if self.encoding: |
|
1693 |
+ try: |
|
1694 |
+ strattrs=strattrs.encode(self.encoding) |
|
1695 |
+ except: |
|
1696 |
+ pass |
|
1697 |
+ if tag in self.elements_no_end_tag: |
|
1698 |
+ self.pieces.append('<%(tag)s%(strattrs)s />' % locals()) |
|
1699 |
+ else: |
|
1700 |
+ self.pieces.append('<%(tag)s%(strattrs)s>' % locals()) |
|
1701 |
+ |
|
1702 |
+ def unknown_endtag(self, tag): |
|
1703 |
+ # called for each end tag, e.g. for </pre>, tag will be 'pre' |
|
1704 |
+ # Reconstruct the original end tag. |
|
1705 |
+ if tag not in self.elements_no_end_tag: |
|
1706 |
+ self.pieces.append("</%(tag)s>" % locals()) |
|
1707 |
+ |
|
1708 |
+ def handle_charref(self, ref): |
|
1709 |
+ # called for each character reference, e.g. for ' ', ref will be '160' |
|
1710 |
+ # Reconstruct the original character reference. |
|
1711 |
+ if ref.startswith('x'): |
|
1712 |
+ value = unichr(int(ref[1:],16)) |
|
1713 |
+ else: |
|
1714 |
+ value = unichr(int(ref)) |
|
1715 |
+ |
|
1716 |
+ if value in _cp1252.keys(): |
|
1717 |
+ self.pieces.append('&#%s;' % hex(ord(_cp1252[value]))[1:]) |
|
1718 |
+ else: |
|
1719 |
+ self.pieces.append('&#%(ref)s;' % locals()) |
|
1720 |
+ |
|
1721 |
+ def handle_entityref(self, ref): |
|
1722 |
+ # called for each entity reference, e.g. for '©', ref will be 'copy' |
|
1723 |
+ # Reconstruct the original entity reference. |
|
1724 |
+ if name2codepoint.has_key(ref): |
|
1725 |
+ self.pieces.append('&%(ref)s;' % locals()) |
|
1726 |
+ else: |
|
1727 |
+ self.pieces.append('&%(ref)s' % locals()) |
|
1728 |
+ |
|
1729 |
+ def handle_data(self, text): |
|
1730 |
+ # called for each block of plain text, i.e. outside of any tag and |
|
1731 |
+ # not containing any character or entity references |
|
1732 |
+ # Store the original text verbatim. |
|
1733 |
+ if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text) |
|
1734 |
+ self.pieces.append(text) |
|
1735 |
+ |
|
1736 |
+ def handle_comment(self, text): |
|
1737 |
+ # called for each HTML comment, e.g. <!-- insert Javascript code here --> |
|
1738 |
+ # Reconstruct the original comment. |
|
1739 |
+ self.pieces.append('<!--%(text)s-->' % locals()) |
|
1740 |
+ |
|
1741 |
+ def handle_pi(self, text): |
|
1742 |
+ # called for each processing instruction, e.g. <?instruction> |
|
1743 |
+ # Reconstruct original processing instruction. |
|
1744 |
+ self.pieces.append('<?%(text)s>' % locals()) |
|
1745 |
+ |
|
1746 |
+ def handle_decl(self, text): |
|
1747 |
+ # called for the DOCTYPE, if present, e.g. |
|
1748 |
+ # <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" |
|
1749 |
+ # "http://www.w3.org/TR/html4/loose.dtd"> |
|
1750 |
+ # Reconstruct original DOCTYPE |
|
1751 |
+ self.pieces.append('<!%(text)s>' % locals()) |
|
1752 |
+ |
|
1753 |
+ _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match |
|
1754 |
+ def _scan_name(self, i, declstartpos): |
|
1755 |
+ rawdata = self.rawdata |
|
1756 |
+ n = len(rawdata) |
|
1757 |
+ if i == n: |
|
1758 |
+ return None, -1 |
|
1759 |
+ m = self._new_declname_match(rawdata, i) |
|
1760 |
+ if m: |
|
1761 |
+ s = m.group() |
|
1762 |
+ name = s.strip() |
|
1763 |
+ if (i + len(s)) == n: |
|
1764 |
+ return None, -1 # end of buffer |
|
1765 |
+ return name.lower(), m.end() |
|
1766 |
+ else: |
|
1767 |
+ self.handle_data(rawdata) |
|
1768 |
+# self.updatepos(declstartpos, i) |
|
1769 |
+ return None, -1 |
|
1770 |
+ |
|
1771 |
+ def convert_charref(self, name): |
|
1772 |
+ return '&#%s;' % name |
|
1773 |
+ |
|
1774 |
+ def convert_entityref(self, name): |
|
1775 |
+ return '&%s;' % name |
|
1776 |
+ |
|
1777 |
+ def output(self): |
|
1778 |
+ '''Return processed HTML as a single string''' |
|
1779 |
+ return ''.join([str(p) for p in self.pieces]) |
|
1780 |
+ |
|
1781 |
+class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor): |
|
1782 |
+ def __init__(self, baseuri, baselang, encoding, entities): |
|
1783 |
+ sgmllib.SGMLParser.__init__(self) |
|
1784 |
+ _FeedParserMixin.__init__(self, baseuri, baselang, encoding) |
|
1785 |
+ _BaseHTMLProcessor.__init__(self, encoding, 'application/xhtml+xml') |
|
1786 |
+ self.entities=entities |
|
1787 |
+ |
|
1788 |
+ def decodeEntities(self, element, data): |
|
1789 |