def buildContent(self, item):
content = Content()
pub_date = item.findtext('pubDate')
if pub_date:
content.publication_date = datetime.strptime(pub_date, self.date_format)
content.web_url = db.Link(item.findtext('link'))
self.parse_item_media(item, content)
return content
def get(self, id):
json_content = {}
content = Content.all().filter('id =', id).fetch(1)[0]
json_content['id'] = id
json_content['headline'] = content.headline
json_content['thumbnail'] = self.buildPicture(content.thumbnail)
json_content['summary'] = content.trail_text
json_content['detail_url'] = self.detail_url + id
json_content['section_name'] = content.section_name
self.returnJSON(json_content)
def get(self):
logging.info("Deleting old content")
print("Deleting old content" + "\n")
old_content = Content.all().filter('publication_date >', datetime.now() - timedelta(-1))
count = 0
for content in old_content:
count = count + 1
self.response.out.write(content.key() + "\n")
taskqueue.add(url='/task/deleteold', params={'key': content.key()})
logging.info("Marked %d content for deletion" % count)
def buildContent(self, content_id):
json = {}
content = Content.all().filter('id =', content_id).fetch(1)[0]
json['id'] = content_id
json['byline'] = content.byline
json['publication'] = content.publication
json['section_name'] = content.section_name
json['headline'] = content.headline
json['web_url'] = content.web_url
json['trail_text'] = content.trail_text
json['link_text'] = content.link_text
json['type'] = content.type
json['body'] = content.body
json['publication_date'] = content.publication_date
json['tags'] = self.buildTags(content.tags)
json['pictures'] = self.buildPictures(content.pictures)
return json
try:
rss_feed = urllib2.urlopen(req)
except urllib2.HTTPError, e:
logging.info("RSS still valid for: " + path)
return #rss not updated: win!
else:
rss_feed = urllib2.urlopen(url)
feed_item.last_modified = rss_feed.headers['date']
feed_item.content = []
#process the feed
for event, elem in ET.iterparse(rss_feed):
if elem.tag == "item":
link = elem.findtext("link")
if re.search(r'guardian.co.uk', link):
content = Content.all().filter('web_url =', link).fetch(1)
if not content:
content = self.buildContent(elem)
key = content.put()
feed_item.content.append(key)
taskqueue.add(url='/task/web', params={'key': key})
else:
content = content[0]
feed_item.content.append(content.put())
elem.clear() # won't need the children any more
else:
logging.info("None guardian url, bailing (%s)" % link)
content.delete()
feed_item.put()
