def create_if_doesnt_exist(url):
try:
Domain.objects.get(url=url)
except Domain.DoesNotExist:
site_data = sites[url]
site_data['url'] = url
site = Domain(**site_data)
site.save()
def create_if_doesnt_exist(url):
try:
Domain.objects.get(url=url)
except Domain.DoesNotExist:
site_data = sites[url]
site_data['url'] = url
site = Domain(**site_data)
site.save()
from livetime.models import Domain
try:
Domain.objects.get(url='bbc.co.uk')
except Domain.DoesNotExist:
bbc = Domain(url='bbc.co.uk',
title_selector="h1.story-header",
date_selector="span.date",
date_fmt="%d %B %Y")
bbc.save()
try:
Domain.objects.get(url='guardian.co.uk')
except Domain.DoesNotExist:
guardian = Domain(url='guardian.co.uk',
title_selector='#main-article-info h1',
date_selector='.publication time',
date_fmt="%A %d %B %Y %H.%M %Z")
guardian.save()
sites = {'bbc.co.uk':{'title_selector':'h1 .story-header',
'date_selector':'meta[property=OriginalPublicationDate]&content',
'date_fmt':"%Y/%m/%d %H:%M:%S"},
'guardian.co.uk': {'title_selector':'title',
'date_selector':'meta[property=article:published_time]&content',
'date_fmt':"%Y-%m-%dT%H:%M:%S%z"},
'huffingtonpost.com': {'title_selector':'meta[property=og:title]&content',
'date_selector':'meta[name=publish_date]&content',
from livetime.models import Domain
try:
Domain.objects.get(url='bbc.co.uk')
except Domain.DoesNotExist:
bbc = Domain(url='bbc.co.uk',
title_selector="h1.story-header",
date_selector="span.date",
date_fmt="%d %B %Y")
bbc.save()
try:
Domain.objects.get(url='guardian.co.uk')
except Domain.DoesNotExist:
guardian = Domain(url='guardian.co.uk',
title_selector='#main-article-info h1',
date_selector='.publication time',
date_fmt="%A %d %B %Y %H.%M %Z")
guardian.save()
sites = {
'bbc.co.uk': {
'title_selector': 'h1 .story-header',
'date_selector': 'meta[property=OriginalPublicationDate]&content',
'date_fmt': "%Y/%m/%d %H:%M:%S"
},
'guardian.co.uk': {
'title_selector': 'title',
'date_selector': 'meta[property=article:published_time]&content',
'date_fmt': "%Y-%m-%dT%H:%M:%S%z"
