def test_cached_webpage(self):
"""When we readable parse we cache the data in redis."""
url = 'http://www.google.com/intl/en/about/index.html'
hashed = generate_hash(url)
resp = self.app.get(
'/v',
params={
'url': url
},
status=302)
# follow the redirect and we land at the actual page.
resp = resp.follow()
from bookie_parser.models import server
# Make sure the data exists in redis
self.assertTrue(server.get(hashed), 'The key is found.')
# Now hit up our redis server and find what data we've stored.
data = WebPageMgr.get(hash_id=hashed)
self.assertEqual(
url, data.url,
"The url is stored in the root object")
self.assertEqual(
hashed, data.hash_id,
"The hash is stored in the root object")
self.assertTrue(
data.request is not None,
'The request is stored in the cache.')
self.assertEqual(
u'Google - About Google',
data.title)
self.assertTrue(data.readable is not None)
def api_hash(request):
"""Fetch the data based on the given hash id."""
# Look up the data from the hash_id
hash_id = request.matchdict.get('hash_id', None)
if not hash_id:
LOG.debug('no hash id supplied: ' + hash_id)
return HTTPNotFound()
exists = WebPageMgr.exists(hash_id=hash_id)
if not exists:
request.response.status_int = 404
return {
'error': 'Hash id not found: ' + hash_id,
}
page = WebPageMgr.get(exists)
if not page:
LOG.debug('notfound: ' + hash_id)
return HTTPNotFound()
resp = request.response
environ = request.environ
resp.headers['Content-Type'] = 'application/json; charset="utf8"'
# allow cross domain requests: xdr
resp.headers['Access-Control-Allow-Origin'] = environ.get(
'HTTP_ORIGIN', "")
return {
'data': dict(page),
'readable': page.readable,
}
def url(request):
""""""
# Look up the url from the hash_id
hash_id = request.matchdict.get('hash_id', None)
page = WebPageMgr.get(hash_id)
if page:
return {
'webpage': page,
}
else:
return HTTPNotFound()
def readable(request):
"""This is the old api endpoint that returns json data.
"""
url = request.params.get('url', None)
LOG.debug('readable process, ' + url)
if not url:
LOG.debug('notfound,' + url)
return HTTPNotFound()
url = url.strip('/')
LOG.debug('Checking url: ' + url)
request.response.headers['Content-Type'] = \
'application/json; charset="utf8"'
# allow cross domain requests: xdr
request.response.headers['Access-Control-Allow-Origin'] = '*'
exists = WebPageMgr.exists(url=url)
if exists:
page = WebPageMgr.get(exists)
return {
'data': dict(page),
'readable': page.readable,
}
else:
LOG.debug('Does not Exist: ...fetching')
read = ReadableRequest(url)
read.process()
if not read.is_error:
page = WebPageMgr.store_request(read)
return {
'data': dict(page),
'readable': page.readable
}
else:
LOG.error('url_is_error,' + url)
request.response.status_int = 500
error_message = 'There was an error reading the page.'
return {
'error': error_message
}
