tsr/planet
1
0
Fork 0
Code Issues 3 Pull Requests Releases Wiki Activity

author tags can be ignored too!

Browse Source
This commit is contained in:
Sam Ruby 2007-06-18 12:03:30 -04:00
parent 28f5de903a
commit 65e41f7b22
3 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/normalization.html
View File

@ -80,8 +80,8 @@ that can be used to help.</p>
<ul>
<li><code>ignore_in_feed</code> allows you to list any number of elements
or attributes which are to be ignored in feeds. This is often handy in the
case of feeds where the <code>id</code>, <code>updated</code> or
<code>xml:lang</code> values can't be trusted.</li>
case of feeds where the <code>author</code>, <code>id</code>,
<code>updated</code> or <code>xml:lang</code> values can't be trusted.</li>
<li><code>title_type</code>, <code>summary_type</code>,
<code>content_type</code> allow you to override the
<a href="http://www.feedparser.org/docs/reference-entry-title_detail.html#reference.entry.title_detail.type"><code>type</code></a>

4
tests/reconstitute.py
View File

@ -4,13 +4,13 @@ venus_base = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0,venus_base)
if __name__ == "__main__":
import planet
planet.getLogger('WARN',None)
hide_planet_ns = True
while len(sys.argv) > 1:
if sys.argv[1] == '-v' or sys.argv[1] == '--verbose':
import planet
planet.getLogger('DEBUG',None)
del sys.argv[1]
elif sys.argv[1] == '-p' or sys.argv[1] == '--planet':
hide_planet_ns = False

10
tests/test_scrub.py
View File

@ -26,6 +26,9 @@ feed = '''
configData = '''
[testfeed]
ignore_in_feed =
future_dates =
name_type = html
title_type = html
summary_type = html
@ -37,16 +40,21 @@ class ScrubTest(unittest.TestCase):
def test_scrub_ignore(self):
base = feedparser.parse(feed)
self.assertTrue(base.entries[0].has_key('author'))
self.assertTrue(base.entries[0].has_key('author_detail'))
self.assertTrue(base.entries[0].has_key('id'))
self.assertTrue(base.entries[0].has_key('updated'))
self.assertTrue(base.entries[0].has_key('updated_parsed'))
self.assertTrue(base.entries[0].summary_detail.has_key('language'))
config.parser.readfp(StringIO.StringIO(configData))
config.parser.set('testfeed', 'ignore_in_feed', 'id updated xml:lang')
config.parser.set('testfeed', 'ignore_in_feed',
'author id updated xml:lang')
data = deepcopy(base)
scrub('testfeed', data)
self.assertFalse(data.entries[0].has_key('author'))
self.assertFalse(data.entries[0].has_key('author_detail'))
self.assertFalse(data.entries[0].has_key('id'))
self.assertFalse(data.entries[0].has_key('updated'))
self.assertFalse(data.entries[0].has_key('updated_parsed'))