def __init__(
self,
title=None, # string
link=None, # url as string
description=None, # string
author=None, # email address as string
categories=None, # list of string or Category
comments=None, # url as string
enclosure=None, # an Enclosure
guid=None, # a unique string
pubDate=None, # a datetime
source=None, # a Source
icon_url=None, # an icon to display
):
if guid is not None:
guid = Guid(guid)
# Initialise base class ..
RSSItem.__init__(self, title, link, description, author, categories,
comments, enclosure, guid, pubDate, source)
# Add media name space (for item icons)
self.icon = None
if icon_url is not None:
self.icon = MediaContentImage(icon_url)
def posts_feed():
base_url = url_for('general.index', _external=True)
items = []
posts = Post.get_published(num=10).all()
for post in posts:
post_url = urljoin(base_url, post.url)
# TODO: Add a real description
item = RSSItem(title=post.title,
link=post_url,
description=post.body.split('\r\n', 1)[0],
author='{} ({})'.format(post.author.email,
post.author.full_name),
categories=[tag.name for tag in post.tags],
guid=Guid(post_url),
pubDate=post.pub_date)
items.append(item)
feed_config = current_app.config['BLOG_POSTS_FEED']
rss2_feed = RSS2(title=feed_config['title'],
link=base_url,
description=feed_config['description'],
language='en-us',
webMaster=feed_config['webmaster'],
lastBuildDate=posts[0].pub_date if posts else None,
ttl=1440,
items=items)
return current_app.response_class(rss2_feed.to_xml(encoding='utf-8'),
mimetype='application/rss+xml')
def toRSSItem(self):
title = self.repo.tagname
if self.message and len(self.message) > 50:
title += " - " + str(Markup.escape(self.message[:50])) + "..."
elif self.message:
title += " - " + str(Markup.escape(self.message))
if self.dbkeywords: title += " - " + ",".join(self.dbkeywords)
description = "<pre>"
description += str(self.getpprint(True))
description += "</pre>"
if type(title) != unicode:
title = unicode(title, 'utf-8')
if type(description) != unicode:
description = unicode(description, 'utf-8')
title = unicodedata.normalize('NFKD', title).encode('ascii', 'ignore')
description = unicodedata.normalize('NFKD', description).encode(
'ascii', 'ignore')
guid = Config.rooturl + "/commit/" + self.repo.tagname + "/" + self.uniqueid
link = ''
if self.repo.viewlink:
link = self.repo.viewlink.replace('%ID', self.uniqueid)
else:
link = guid
item = RSSItem(title=title,
link=link,
description=description,
guid=Guid(guid, isPermaLink=0),
pubDate=unixToDatetime(self.date))
return item
def event_to_rssitem(self, event):
"""Function converting an event (Python dict) to an RSSItem object."""
title = (CrabStatus.get_name(event['status']) + ': ' +
event['user'] + ' @ ' + event['host'])
if event['command'] is not None:
title += ': ' + event['command']
link = self.base + '/job/' + str(event['id'])
if event['finishid'] is not None:
link += '/output/' + str(event['finishid'])
output = ''
if event['stdout']:
output += event['stdout']
if event['stderr']:
if event['stdout']:
output += '\n\nStandard Error:\n\n'
output += event['stderr']
date = self.store.parse_datetime(event['datetime'])
guid = ':'.join(['crab', self.fqdn, str(event['id']),
str(calendar.timegm(date.timetuple())), str(event['status'])])
info = {}
if output != '':
info['description'] = '<pre>' + output + '</pre>'
return RSSItem(title=title,
link=link,
pubDate=date,
guid=Guid(guid, isPermaLink = False),
**info)
def rss(self,language=None,*args,**kwargs):
if language:
l = models.get_language(language)
conf = cherrypy.request.app.config['ligiloj']
query = models.Link().select(models.Link,models.Language).join(models.Language)
if language:
query = query.where(models.Link.language == l)
cherrypy.response.headers['Content-Type'] = 'application/xml'
return RSS2(title=u'{0} - {1}'.format(conf['site_title'],language and l.name or conf['global_title_text']),
link=conf['rss_site_url'],
description=conf['rss_description'],
language=language or conf['rss_default_language'],
items=[RSSItem(title=language and link.title or u"{0}: {1}".format(link.language.name,link.title),
link=link.url,
pubDate=link.published.isoformat(),
guid=Guid(link.url,str(link.id))) for link in query]).to_xml('utf-8')
def generate_rss(self):
if 'rss_title' not in self.config or 'rss_description' not in self.config:
return
RSS2(title=self.config['rss_title'],
link=self.root_url,
description=self.config['rss_description'],
lastBuildDate=datetime.datetime.now(),
items=[
RSSItem(title=entry['title'],
link=self.root_url + entry['link'],
description=entry['html'],
guid=Guid(self.root_url + entry['link']),
pubDate=datetime.datetime.strptime(
entry['date'][:10], '%Y-%m-%d'))
for entry in self.entries
]).write_xml(file(self.out + 'feed.xml', 'wb'), encoding='utf-8')
def read_rss():
rss = []
count = 0
while exists(RSS_FILE + str(count)):
with open(RSS_FILE + str(count)) as source:
title = source.readline()
url = source.readline()
date = eval(source.readline())
description = ''.join(source.readlines())
rss.append(
RSSItem(title=title,
link=BASE_URL + url,
description=description,
guid=Guid(url),
pubDate=datetime(*date[0:5])))
count = count + 1
return rss
def pushRSSItem(self, item):
"""Adds an RSS Item to the top of an RSS feed. If the
resulting feed is longer than the maximum number of items, and
some of those items were put on the feed in previous runs, the
earliest such item will be shifted off the feed."""
if not getattr(item, 'guid') and item.link:
item.guid = Guid(item.link)
if not getattr(item, 'pubDate'):
item.pubDate = self.lastBuildDate
#Stringify data from external sources (eg. Beautiful Soup) to
#avoid complications with pickling.
for field in ('title', 'link', 'description', 'author', 'category',
'comments', ' source'):
s = getattr(item, field, None)
if s:
setattr(item, field, str(s))
if self.hasSeen(item.guid):
#print "Checking for newer version of %s", item.guid.guid
#This item is already in this feed. Replace it with the possibly
#new version.
for i in range(0, len(self.items)):
check = self.items[i]
if check.guid.guid == item.guid.guid:
#print "Updating possibly old version of %s" % item.guid.guid
self.items[i] = item
break
else:
#We haven't seen this item before, so the new one can go in.
#print "Inserting ", item.guid.guid
self.items.insert(0, item)
self.currentGuids[item.guid.guid] = self.lastBuildDate
while len(self.items) > self.maxItems \
and self.currentGuids.get(self.items[-1].guid.guid) != self.lastBuildDate:
#There are too many items in the feed, and the oldest one
#was inserted in a previous update, so we can get rid of
#it.
#print "%s pushed off the edge!" % self.items[-1].guid.guid
old = self.items.pop(-1)
del (self.currentGuids[old.guid.guid])
def menu():
resource = urllib2.urlopen("http://www.ufrgs.br/ufrgs/ru")
page = BeautifulSoup(resource)
items = []
for ru in page.find_all("div", "ru"):
ru_name = ru.h3.contents[0]
desc = ', '.join([(item or '').strip() for item in ru.div.contents if not hasattr(item, 'contents')])
items.append(RSSItem(
title = '%s - %s' % (ru_name, date.today().strftime('%d/%m/%Y')),
link='http://www.ufrgs.br/ufrgs/ru',
description=desc,
guid=Guid(ru_name+date.today().isoformat()),
))
feed = RSS2(
title=u"Cardápio do RU-UFRGS - diário",
link='http://www.ufrgs.br/ufrgs/ru',
description=u"Cardápio do dia no Restaurante Universitário da UFRGS",
pubDate=datetime.today(),
items=items,
)
return feed.to_xml()
def HTML2RSS(self, headers, body):
soup = BeautifulSoup(body, 'html.parser')
items = []
for item in soup.find_all("tr", "titlebg2"):
a = item.find_all("a")[-1]
#topic_details = item.find("div", "topic_details")
#author = topic_details.find("strong").a.text
#a = topic_details.find("h5").find_all("a")[1]
link = a['href']
subject = a.text
if 'ICO' not in subject:
continue
logging.info(subject)
rss = RSSItem(author='x',
title=subject,
link=link,
pubDate='',
guid=Guid(link),
description='')
items.append(rss)
self.addRSSItems(items)
def get_guid(site, workshop):
'''
Create non-permalink Guid consisting of Software Carpentry
site URL and workshop identifier ('slug').
'''
return Guid('{0}/{1}'.format(site, workshop['slug']), isPermaLink=False)
guid = link
if "rel" in a.attrib:
author = a.text # NOT COMPLIANT
description = work.xpath(".//blockquote[@class='userstuff summary']")[0].text_content().strip()
category = work.xpath(".//a[@class='tag']")[0].text
try:
comments = urljoin(BASE_URL, work.xpath(".//dd[@class='comments']/a/@href")[0])
except Exception:
comments = None
pubDate = dateparser.parse(work.xpath(".//p[@class='datetime']")[0].text)
item = RSSItem(
title = title,
link = link,
description = description,
guid = Guid(guid),
pubDate = pubDate,
comments = comments)
items.append(item)
print (title, link, author, description, category,comments, pubDate)
item = None
link = None
description = None
guid = None
pubDate = None
comments = None
rss = RSS2(
title = "AO3 works of {}".format(USER),