import re
import feedparser
import urllib
import sys
from datetime import *
from django.core.management.base import BaseCommand, CommandError
from feeds.models import *
# see Command definition at the end
# this mechanism isn't robust yet b/c any small sets get parsed repeatedly
MIN_SET_SIZE = 3 # Need to find at least this many images for each set
###############################################################################
def scrape_pics_from_html(pset, html):
if(type(pset) != PicSet):
raise("Type error, expected PicSet")
# assumptions: one per line, ordering, etc
mset = re.finditer('...\n")
return
for shortname in args:
try:
scrape_feed(shortname)
except Exception:
sys.stderr.write("Error scraping " + shortname + "\n")
sys.stdout.flush()
sys.stdout.write('Done scraping feeds.\n')