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

More accurately track and report http status

Browse Source
This commit is contained in:
Sam Ruby 2006-09-04 17:12:22 -04:00
parent 9d85882503
commit 777cd9b603
3 changed files with 28 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
planet/shell/tmpl.py
View File

@ -80,6 +80,7 @@ Base = [
['title', String, 'title_detail', 'value'], ['title', String, 'title_detail', 'value'],
['title_plain', Plain, 'title_detail', 'value'], ['title_plain', Plain, 'title_detail', 'value'],
['url', String, 'links', {'rel':'self'}, 'href'], ['url', String, 'links', {'rel':'self'}, 'href'],
['url', String, 'planet_http_location'],
] ]
Items = [ Items = [

20
planet/spider.py
View File

@ -128,7 +128,9 @@ def spiderFeed(feed):
# process based on the HTTP status code # process based on the HTTP status code
log = planet.logger log = planet.logger
if data.status == 301 and data.has_key("entries") and len(data.entries)>0: if data.status == 200 and data.has_key("url"):
data.feed['planet_http_location'] = data.url
elif data.status == 301 and data.has_key("entries") and len(data.entries)>0:
log.warning("Feed has moved from <%s> to <%s>", feed, data.url) log.warning("Feed has moved from <%s> to <%s>", feed, data.url)
data.feed['planet_http_location'] = data.url data.feed['planet_http_location'] = data.url
elif data.status == 304: elif data.status == 304:
@ -194,14 +196,6 @@ def spiderFeed(feed):
# perform user configured scrub operations on the data # perform user configured scrub operations on the data
scrub(feed, data) scrub(feed, data)
# write the feed info to the cache
if not os.path.exists(sources): os.makedirs(sources)
xdoc=minidom.parseString('''<feed xmlns:planet="%s"
xmlns="http://www.w3.org/2005/Atom"/>\n''' % planet.xmlns)
reconstitute.source(xdoc.documentElement, data.feed, data.bozo)
write(xdoc.toxml('utf-8'), filename(sources, feed))
xdoc.unlink()
# write each entry to the cache # write each entry to the cache
cache = config.cache_directory() cache = config.cache_directory()
for entry in data.entries: for entry in data.entries:
@ -240,6 +234,14 @@ def spiderFeed(feed):
write(output, cache_file) write(output, cache_file)
os.utime(cache_file, (mtime, mtime)) os.utime(cache_file, (mtime, mtime))
# write the feed info to the cache
if not os.path.exists(sources): os.makedirs(sources)
xdoc=minidom.parseString('''<feed xmlns:planet="%s"
xmlns="http://www.w3.org/2005/Atom"/>\n''' % planet.xmlns)
reconstitute.source(xdoc.documentElement, data.feed, data.bozo)
write(xdoc.toxml('utf-8'), filename(sources, feed))
xdoc.unlink()
def spiderPlanet(): def spiderPlanet():
""" Spider (fetch) an entire planet """ """ Spider (fetch) an entire planet """
log = planet.getLogger(config.log_level()) log = planet.getLogger(config.log_level())

17
themes/asf/index.html.xslt
View File

@ -37,9 +37,24 @@
<xsl:sort select="planet:name"/> <xsl:sort select="planet:name"/>
<xsl:text>&#10;</xsl:text> <xsl:text>&#10;</xsl:text>
<li> <li>
<a href="{atom:link[@rel='self']/@href}" title="subscribe"> <!-- icon -->
<a title="subscribe">
<xsl:choose>
<xsl:when test="planet:http_location">
<xsl:attribute name="href">
<xsl:value-of select="planet:http_location"/>
</xsl:attribute>
</xsl:when>
<xsl:when test="atom:link[@rel='self']/@href">
<xsl:attribute name="href">
<xsl:value-of select="atom:link[@rel='self']/@href"/>
</xsl:attribute>
</xsl:when>
</xsl:choose>
<img src="images/feed-icon-10x10.png" alt="(feed)"/> <img src="images/feed-icon-10x10.png" alt="(feed)"/>
</a> </a>
<!-- name -->
<a href="{atom:link[@rel='alternate']/@href}"> <a href="{atom:link[@rel='alternate']/@href}">
<xsl:choose> <xsl:choose>
<xsl:when test="planet:message"> <xsl:when test="planet:message">