def bootstrap_feedpages():
print "Mongo DB feed_pages: %s" % MFeedPage.objects().count()
# db.feed_pages.drop()
print "Dropped! Mongo DB feed_pages: %s" % MFeedPage.objects().count()
print "FeedPages: %s" % FeedPage.objects.count()
pprint(db.feed_pages.index_information())
feeds = Feed.objects.all().order_by('-average_stories_per_month')
feed_count = feeds.count()
i = 0
for feed in feeds:
i += 1
print "%s/%s: %s" % (i, feed_count, feed,)
sys.stdout.flush()
if not MFeedPage.objects(feed_id=feed.pk):
feed_page = FeedPage.objects.filter(feed=feed).values()
if feed_page:
del feed_page[0]['id']
feed_page[0]['feed_id'] = feed.pk
try:
MFeedPage(**feed_page[0]).save()
except:
print '\n\n!\n\n'
continue
print "\nMongo DB feed_pages: %s" % MFeedPage.objects().count()
def bootstrap_feedpages():
print "Mongo DB feed_pages: %s" % MFeedPage.objects().count()
# db.feed_pages.drop()
print "Dropped! Mongo DB feed_pages: %s" % MFeedPage.objects().count()
print "FeedPages: %s" % FeedPage.objects.count()
pprint(db.feed_pages.index_information())
feeds = Feed.objects.all().order_by('-average_stories_per_month')
feed_count = feeds.count()
i = 0
for feed in feeds:
i += 1
print "%s/%s: %s" % (
i,
feed_count,
feed,
)
sys.stdout.flush()
if not MFeedPage.objects(feed_id=feed.pk):
feed_page = FeedPage.objects.filter(feed=feed).values()
if feed_page:
del feed_page[0]['id']
feed_page[0]['feed_id'] = feed.pk
try:
MFeedPage(**feed_page[0]).save()
except:
print '\n\n!\n\n'
continue
print "\nMongo DB feed_pages: %s" % MFeedPage.objects().count()
def fetch_image_from_page_data(self):
image = None
image_file = None
if self.page_data:
content = self.page_data
elif settings.BACKED_BY_AWS.get('pages_on_s3') and self.feed.s3_page:
key = settings.S3_PAGES_BUCKET.get_key(self.feed.s3_pages_key)
compressed_content = key.get_contents_as_string()
stream = StringIO(compressed_content)
gz = gzip.GzipFile(fileobj=stream)
try:
content = gz.read()
except IOError:
content = None
else:
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if not url:
try:
content = requests.get(self.feed.feed_link).content
url = self._url_from_html(content)
except (AttributeError, SocketError, requests.ConnectionError,
requests.models.MissingSchema, requests.sessions.InvalidSchema,
requests.sessions.TooManyRedirects,
requests.models.InvalidURL,
requests.models.ChunkedEncodingError,
requests.models.ContentDecodingError,
LocationParseError, OpenSSLError, PyAsn1Error), e:
logging.debug(" ---> ~SN~FRFailed~FY to fetch ~FGfeed icon~FY: %s" % e)
def fetch_image_from_page_data(self):
image = None
image_file = None
if self.page_data:
content = self.page_data
elif settings.BACKED_BY_AWS.get('pages_on_s3') and self.feed.s3_page:
key = settings.S3_PAGES_BUCKET.get_key(self.feed.s3_pages_key)
compressed_content = key.get_contents_as_string()
stream = StringIO(compressed_content)
gz = gzip.GzipFile(fileobj=stream)
try:
content = gz.read()
except IOError:
content = None
else:
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if not url:
try:
content = requests.get(self.cleaned_feed_link).content
url = self._url_from_html(content)
except (AttributeError, SocketError, requests.ConnectionError,
requests.models.MissingSchema, requests.sessions.InvalidSchema,
requests.sessions.TooManyRedirects,
requests.models.InvalidURL,
requests.models.ChunkedEncodingError,
requests.models.ContentDecodingError,
httplib.IncompleteRead,
LocationParseError, OpenSSLError, PyAsn1Error), e:
logging.debug(" ---> ~SN~FRFailed~FY to fetch ~FGfeed icon~FY: %s" % e)
def fetch_image_from_page_data(self):
image = None
image_file = None
if self.page_data:
content = self.page_data
# Deleted By Xinyan Lu : No S3 storage
# elif settings.BACKED_BY_AWS.get('pages_on_s3') and self.feed.s3_page:
# key = settings.S3_PAGES_BUCKET.get_key(self.feed.s3_pages_key)
# compressed_content = key.get_contents_as_string()
# stream = StringIO(compressed_content)
# gz = gzip.GzipFile(fileobj=stream)
# try:
# content = gz.read()
# except IOError:
# content = None
else:
content = MFeedPage.get_data(feed_id=self.feed.pk)
# Modified By Xinyan Lu : content may be None
if content:
url = self._url_from_html(content)
else:
url = None
if url:
image, image_file = self.get_image_from_url(url)
return image, image_file, url
def fetch_image_from_page_data(self):
image = None
image_file = None
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if url:
image, image_file = self.get_image_from_url(url)
return image, image_file, url
def fetch_image_from_page_data(self):
image = None
image_file = None
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if url:
image, image_file = self.get_image_from_url(url)
return image, image_file, url
def load_feed_page(request, feed_id):
if not feed_id:
raise Http404
data = MFeedPage.get_data(feed_id=feed_id)
if not data:
data = "Fetching feed..."
return HttpResponse(data, mimetype='text/html')
def load_feed_page(request, feed_id):
if not feed_id:
raise Http404
data = MFeedPage.get_data(feed_id=feed_id)
if not data:
data = "Fetching feed..."
return HttpResponse(data, mimetype='text/html')
def load_feed_page(request):
feed_id = int(request.GET.get('feed_id', 0))
if feed_id == 0:
raise Http404
data = MFeedPage.get_data(feed_id=feed_id)
if not data:
data = "Fetching feed..."
return HttpResponse(data, mimetype='text/html')
def fetch_image_from_page_data(self):
image = None
image_file = None
content = None
if self.page_data:
content = self.page_data
elif settings.BACKED_BY_AWS.get('pages_on_node'):
domain = Site.objects.get_current().domain
url = "https://%s/original_page/%s" % (
domain,
self.feed.pk,
)
try:
page_response = requests.get(url)
if page_response.status_code == 200:
content = page_response.content
except requests.ConnectionError:
pass
elif settings.BACKED_BY_AWS.get('pages_on_s3') and self.feed.s3_page:
key = settings.S3_CONN.Bucket(
settings.S3_PAGES_BUCKET_NAME).Object(
key=self.feed.s3_pages_key)
compressed_content = key.get()["Body"].read()
stream = BytesIO(compressed_content)
gz = gzip.GzipFile(fileobj=stream)
try:
content = gz.read()
except IOError:
pass
else:
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if not url:
try:
content = requests.get(self.cleaned_feed_link,
timeout=10).content
url = self._url_from_html(content)
except (AttributeError, SocketError, requests.ConnectionError,
requests.models.MissingSchema,
requests.sessions.InvalidSchema,
requests.sessions.TooManyRedirects,
requests.models.InvalidURL,
requests.models.ChunkedEncodingError,
requests.models.ContentDecodingError,
http.client.IncompleteRead, requests.adapters.ReadTimeout,
LocationParseError, OpenSSLError, PyAsn1Error,
ValueError) as e:
logging.debug(
" ---> ~SN~FRFailed~FY to fetch ~FGfeed icon~FY: %s" % e)
if url:
image, image_file = self.get_image_from_url(url)
return image, image_file, url
def load_feed_page(request):
feed_id = None
try:
feed_id = int(request.REQUEST.get('feed_id', 0))
except ValueError:
feed_id_matches = re.search(r'(\d+)', request.REQUEST['feed_id'])
if feed_id_matches: feed_id = int(feed_id_matches.group(1))
if not feed_id:
raise Http404
data = MFeedPage.get_data(feed_id=feed_id)
if not data:
data = "Fetching feed..."
return HttpResponse(data, mimetype='text/html')
def fetch_image_from_page_data(self):
image = None
image_file = None
if self.page_data:
content = self.page_data
elif settings.BACKED_BY_AWS.get('pages_on_s3') and self.feed.s3_page:
key = settings.S3_PAGES_BUCKET.get_key(self.feed.s3_pages_key)
compressed_content = key.get_contents_as_string()
stream = StringIO(compressed_content)
gz = gzip.GzipFile(fileobj=stream)
content = gz.read()
else:
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if url:
image, image_file = self.get_image_from_url(url)
return image, image_file, url
def fetch_image_from_page_data(self):
image = None
image_file = None
if self.page_data:
content = self.page_data
elif settings.BACKED_BY_AWS.get('pages_on_s3') and self.feed.s3_page:
key = settings.S3_PAGES_BUCKET.get_key(self.feed.s3_pages_key)
compressed_content = key.get_contents_as_string()
stream = StringIO(compressed_content)
gz = gzip.GzipFile(fileobj=stream)
content = gz.read()
else:
content = MFeedPage.get_data(feed_id=self.feed.pk)
url = self._url_from_html(content)
if url:
image, image_file = self.get_image_from_url(url)
return image, image_file, url
