def getArticle(self, request, queryset, *arg1, **arg2):
for feed in queryset:
logger.info('start to fetch article,The title is %s', feed.title)
try:
if feed.feed.start_target != 'nohtml':
logger.info('fetch new article %s,at %s' % (feed.link, datetime.now()))
contenthtml = ''
try:
result = getpage(feed.link, 30)
if result.code == 200:
if len(feed.feed.start_target) != 0 and feed.feed.start_target != 'nohtml':
contenthtml = htmllib.parsehtml(result.read(), feed.feed, feed.link, feed.feed.feedurl)
else:
contenthtml = feed.excerpt
self.__store_article(contenthtml, feed)
else:
feed.fetch_stat = 2
feed.save()
except Exception, data:
logger.info('DownloadError in get %s.the error is %s', feed.link, data)
return False
else:
self.__store_article(feed.excerpt, feed)
def handle_result(rpc, entry, feed_url, url, feed_target):
try:
result = rpc.get_result()
if result.status_code == 200:
contenthtml = htmllib.parsehtml(result.content, feed_url, feed_target)
if contenthtml != None:
theresult.append([contenthtml])
else:
print ('something is wrong at %s,the feed is %s,the target is %s ,please check,the call back result is none', url, feed_url, feed_target)
except Exception, Error:
logging.debug ('DownloadError in get %s.' % url)