def moincms(wikibase, outputdir, pattern):
if pattern: pattern = re.compile(pattern)
#print (wikibase, outputdir, rewrite)
req = urllib2.Request(wikibase, headers={'Accept': RDF_IMT})
resp = urllib2.urlopen(req)
original_wiki_base = dict(resp.info())[ORIG_BASE_HEADER]
feed = bindery.parse(resp)
process_list = []
for item in feed.RDF.channel.items.Seq.li:
uri = split_fragment(item.resource)[0]
#print >> sys.stderr, (uri, str(item.resource), split_fragment(item.resource))
#Deal with the wrapped URI
if original_wiki_base:
#print >> sys.stderr, (uri, original_wiki_base.rstrip('/')+'/')
relative = relativize(uri, original_wiki_base.rstrip('/')+'/').lstrip('/')
uri = absolutize(relative, wikibase)
#print >> sys.stderr, (uri, relative)
if pattern and not pattern.match(relative):
continue
n = node.factory(uri, relative, outputdir)
if n.up_to_date():
pass
#print >> sys.stderr, 'Up to date. Skipped...'
else:
process_list.append(n)
#Process nodes needing update according to priority
for n in sorted(process_list, key=attrgetter('PRIORITY'), reverse=True):
#print >> sys.stderr, "processing ", n.rest_uri
n.render()
return
def moin2atomentries(wikibase, outputdir, rewrite, pattern):
wikibase_len = len(rewrite)
if pattern: pattern = re.compile(pattern)
#print (wikibase, outputdir, rewrite)
req = urllib2.Request(wikibase, headers={'Accept': RDF_IMT})
with closing(urllib2.urlopen(req)) as resp:
feed = bindery.parse(resp)
for item in feed.RDF.channel.items.Seq.li:
uri = split_fragment(item.resource)[0]
relative = uri[wikibase_len:]
print >> sys.stderr, uri, relative
if pattern and not pattern.match(relative):
continue
if rewrite:
uri = uri.replace(rewrite, wikibase)
req = urllib2.Request(uri, headers={'Accept': DOCBOOK_IMT})
with closing(urllib2.urlopen(req)) as resp:
page = bindery.parse(resp)
entrydate = dateparse(unicode(page.article.articleinfo.revhistory.revision.date))
if entrydate.tzinfo == None: entrydate = entrydate.replace(tzinfo=DEFAULT_TZ)
output = os.path.join(outputdir, OUTPUTPATTERN%pathsegment(relative))
if os.access(output, os.R_OK):
lastrev = dateparse(unicode(bindery.parse(output).entry.updated))
if lastrev.tzinfo == None: lastrev = lastrev.replace(tzinfo=DEFAULT_TZ)
if (entrydate == lastrev):
print >> sys.stderr, 'Not updated. Skipped...'
continue
print >> sys.stderr, 'Writing to ', output
with open(output, 'w') as output:
handle_page(uri, page, outputdir, relative, output)
return
def moincms(wikibase, outputdir, pattern):
if pattern: pattern = re.compile(pattern)
#print (wikibase, outputdir, rewrite)
req = urllib2.Request(wikibase, headers={'Accept': RDF_IMT})
resp = urllib2.urlopen(req)
original_wiki_base = dict(resp.info())[ORIG_BASE_HEADER]
feed = bindery.parse(resp)
process_list = []
for item in feed.RDF.channel.items.Seq.li:
uri = split_fragment(item.resource)[0]
#print >> sys.stderr, (uri, str(item.resource), split_fragment(item.resource))
#Deal with the wrapped URI
if original_wiki_base:
#print >> sys.stderr, (uri, original_wiki_base.rstrip('/')+'/')
relative = relativize(uri,
original_wiki_base.rstrip('/') +
'/').lstrip('/')
uri = absolutize(relative, wikibase)
#print >> sys.stderr, (uri, relative)
if pattern and not pattern.match(relative):
continue
n = node.factory(uri, relative, outputdir)
if n.up_to_date():
pass
#print >> sys.stderr, 'Up to date. Skipped...'
else:
process_list.append(n)
#Process nodes needing update according to priority
for n in sorted(process_list, key=attrgetter('PRIORITY'), reverse=True):
#print >> sys.stderr, "processing ", n.rest_uri
n.render()
return
def execute(top=None):
'''
Sample request:
curl -F "pattern=wiki/path" -F "wiki=http://localhost:8880/moin/foo/" "http://*****:*****@class="navigation"]//@href'):
link = navchild.xml_value
#print >> sys.stderr, 'LINK:', link
#uri = split_fragment(item.resource)[0]
#relative = uri[wikibase_len:]
#print >> sys.stderr, uri, relative
#if rewrite:
# uri = uri.replace(rewrite, wikibase)
rest_uri = wrapped_uri(original_wiki_base, link)
#print >> sys.stderr, 'rest uri:', rest_uri
items.append(freemix(rest_uri, opener).render())
return json.dumps({'items': items}, indent=4)
def execute(top=None):
'''
Sample request:
curl -F "pattern=wiki/path" -F "wiki=http://localhost:8880/moin/foo/" "http://*****:*****@class="navigation"]//@href'):
link = navchild.xml_value
#print >> sys.stderr, 'LINK:', link
#uri = split_fragment(item.resource)[0]
#relative = uri[wikibase_len:]
#print >> sys.stderr, uri, relative
#if rewrite:
# uri = uri.replace(rewrite, wikibase)
rest_uri = wrapped_uri(original_wiki_base, link)
#print >> sys.stderr, 'rest uri:', rest_uri
items.append(freemix(rest_uri, opener).render())
return json.dumps({'items': items}, indent=4)
