def test_image_url(self):
"""Verify we don't store, but just tag an image url"""
img_url = 'http://www.ndftz.com/nickelanddime.png'
read = ReadUrl.parse(img_url)
ok_(read.status == 200, "The status is 200: " + str(read.status))
ok_(read.content is None, "Content should be none: ")
def test_image_url(self):
"""Verify we don't store, but just tag an image url"""
img_url = 'http://www.ndftz.com/nickelanddime.png'
read = ReadUrl.parse(img_url)
ok_(read.status == 200, "The status is 200: " + str(read.status))
ok_(read.content is None, "Content should be none: ")
def test_404_url(self):
"""Test that we get the proper errors in a missing url"""
url = 'http://lococast.net/archives/001'
read = ReadUrl.parse(url)
ok_(read.status == 404, "The status is 404: " + str(read.status))
ok_(not read.is_image(), "The content is not an image")
ok_(read.content is None, "Content should be none")
def test_non_net_url(self):
"""I might be bookmarking something internal bookie can't access"""
test_url = "http://r2"
read = ReadUrl.parse(test_url)
ok_(read.status == 901, "The status is 901: " + str(read.status))
ok_(not read.is_image(), "The content is not an image")
ok_(read.content is None, "Content should be none: " + str(read.content))
def test_404_url(self):
"""Test that we get the proper errors in a missing url"""
url = 'http://lococast.net/archives/001'
read = ReadUrl.parse(url)
ok_(read.status == 404, "The status is 404: " + str(read.status))
ok_(not read.is_image(), "The content is not an image")
ok_(read.content is None, "Content should be none")
def fetch_content(i, q):
"""Our threaded worker to fetch the url contents"""
while True:
hash_id, url = q.get()
print 'Q' + str(i) + ' getting content for ' + hash_id + ' ' + url
read = ReadUrl.parse(url)
parsed[hash_id] = read
q.task_done()
def fetch_content(i, q):
"""Our threaded worker to fetch the url contents"""
while True:
hash_id, url = q.get()
print 'Q' + str(i) + ' getting content for ' + hash_id + ' ' + url
read = ReadUrl.parse(url)
parsed[hash_id] = read
q.task_done()
def test_non_net_url(self):
"""I might be bookmarking something internal bookie can't access"""
test_url = "http://r2"
read = ReadUrl.parse(test_url)
ok_(read.status == 901, "The status is 901: " + str(read.status))
ok_(not read.is_image(), "The content is not an image")
ok_(read.content is None,
"Content should be none: " + str(read.content))
def test_url_content(self):
"""Test that we set the correct status"""
url = 'http://lococast.net/archives/475'
read = ReadUrl.parse(url)
ok_(read.status == 200, "The status is 200" + str(read.status))
ok_(not read.is_image(), "The content is not an image")
ok_(read.content is not None, "Content should not be none")
ok_('Lococast' in read.content,
"The word Lococast is in the content: " + str(read.content))
def test_url_content(self):
"""Test that we set the correct status"""
url = 'http://lococast.net/archives/475'
read = ReadUrl.parse(url)
ok_(read.status == 200, "The status is 200" + str(read.status))
ok_(not read.is_image(), "The content is not an image")
ok_(read.content is not None, "Content should not be none")
ok_('Lococast' in read.content,
"The word Lococast is in the content: " + str(read.content))
def test_nonworking_url(self):
"""Testing some urls we know we had issues with initially"""
urls = { 'CouchSurfing': 'http://allthatiswrong.wordpress.com/2010/01/24/a-criticism-of-couchsurfing-and-review-of-alternatives/#problems',
'Electronic': 'https://www.fbo.gov/index?s=opportunity&mode=form&tab=core&id=dd11f27254c796f80f2aadcbe4158407',
'Will Fuqua': 'http://twitter.com/#!/wafuqua',
}
for key, url in urls.iteritems():
LOG.debug(url)
read = ReadUrl.parse(url)
LOG.debug(read)
ok_(read.status == 200, "The status is 200: " + str(read.status))
ok_(read.content is not None, "Content should not be none: ")
def test_nonworking_url(self):
"""Testing some urls we know we had issues with initially"""
urls = {
'CouchSurfing': ('http://allthatiswrong.wordpress.com/2010/01'
'/24/a-criticism-of-couchsurfing-and-review-o'
'f-alternatives/#problems'),
# 'Electronic': ('https://www.fbo.gov/index?s=opportunity&mode='
# 'form&tab=core&id=dd11f27254c796f80f2aadcbe415'
# '8407'),
}
for key, url in urls.iteritems():
read = ReadUrl.parse(url)
self.assertTrue(
read.status == 200, "The status is 200: " + str(read.status))
self.assertTrue(
read.content is not None, "Content should not be none: ")
def fetch_bmark_content(bid):
"""Given a bookmark, fetch its content and index it."""
trans = transaction.begin()
logger = get_task_logger('fetch_bmark_content')
if not bid:
raise Exception('missing bookmark id')
bmark = Bmark.query.get(bid)
if not bmark:
raise Exception('Bookmark not found: ' + str(bid))
hashed = bmark.hashed
try:
read = ReadUrl.parse(hashed.url)
except ValueError, exc:
# We hit this where urllib2 choked trying to get the protocol type of
# this url to fetch it.
logger.error('Could not parse url: ' + hashed.url)
logger.error('exc')
read = None
def fetch_bmark_content(bid):
"""Given a bookmark, fetch its content and index it."""
trans = transaction.begin()
logger = get_task_logger('fetch_bmark_content')
if not bid:
raise Exception('missing bookmark id')
bmark = Bmark.query.get(bid)
if not bmark:
raise Exception('Bookmark not found: ' + str(bid))
hashed = bmark.hashed
try:
read = ReadUrl.parse(hashed.url)
except ValueError, exc:
# We hit this where urllib2 choked trying to get the protocol type of
# this url to fetch it.
logger.error('Could not parse url: ' + hashed.url)
logger.error('exc')
read = None
def fetch_content(i, q):
"""Our threaded worker to fetch the url contents"""
while True:
hash_id, url = q.get()
print 'Q' + str(i) + ' getting content for ' + hash_id + ' ' + url
read = ReadUrl.parse(url)
parsed[hash_id] = read
q.task_done()
if __name__ == "__main__":
args = parse_args()
if args.test_url:
# then we only want to test this one url and not process full lists
read = ReadUrl.parse(args.test_url)
print "META"
print "*" * 30
print read.content_type
print read.status
print read.status_message
print "\n\n"
if not read.is_image():
print read.content
else:
print "Url is an image"
# but if we don't we'll just keep getting errors and never end
url_list = Hashed.query.outerjoin(Readable).\
filter(Readable.status_code != 200).all()
else:
url_list = Hashed.query.limit(PER_TRANS).offset(ct).all()
if len(url_list) < PER_TRANS:
all = True
ct = ct + len(url_list)
for hashed in url_list:
print hashed.url
read = ReadUrl.parse(hashed.url)
if not read.is_image():
if not hashed.readable:
hashed.readable = Readable()
hashed.readable.content = read.content
else:
if not hashed.readable:
hashed.readable = Readable()
hashed.readable.content = None
# set some of the extra metadata
hashed.readable.content_type = read.content_type
hashed.readable.status_code = read.status
hashed.readable.status_message = read.status_message
def fetch_content(i, q):
"""Our threaded worker to fetch the url contents"""
while True:
hash_id, url = q.get()
print 'Q' + str(i) + ' getting content for ' + hash_id + ' ' + url
read = ReadUrl.parse(url)
parsed[hash_id] = read
q.task_done()
if __name__ == "__main__":
args = parse_args()
if args.test_url:
# then we only want to test this one url and not process full lists
read = ReadUrl.parse(args.test_url)
print "META"
print "*" * 30
print read.content_type
print read.status
print read.status_message
print "\n\n"
if not read.is_image():
print read.content
else:
print "Url is an image"
def fetch_bmark_content(bid):
"""Given a bookmark, fetch its content and index it."""
trans = transaction.begin()
if not bid:
raise Exception('missing bookmark id')
bmark = Bmark.query.get(bid)
if not bmark:
raise Exception('Bookmark not found: ' + str(bid))
hashed = bmark.hashed
try:
read = ReadUrl.parse(hashed.url)
except ValueError:
# We hit this where urllib2 choked trying to get the protocol type of
# this url to fetch it.
logger.error('Could not parse url: ' + hashed.url)
logger.error('exc')
read = None
if read:
logger.debug(read)
logger.debug(read.content)
logger.debug("%s: %s %d %s %s" % (
hashed.hash_id,
read.url,
len(read.content) if read.content else -1,
read.is_error(),
read.status_message))
if not read.is_image():
if not bmark.readable:
bmark.readable = Readable()
bmark.readable.content = read.content
else:
if not bmark.readable:
bmark.readable = Readable()
bmark.readable.content = None
# set some of the extra metadata
bmark.readable.content_type = read.content_type
bmark.readable.status_code = read.status
bmark.readable.status_message = read.status_message
trans.commit()
fulltext_index_bookmark.delay(
bid,
read.content if read else None)
else:
logger.error(
'No readable record for bookmark: ',
str(bid, bmark.hashed.url))
# There was a failure reading the thing.
bmark.readable = Readable()
bmark.readable.status = '900'
bmark.readable.status_message = (
'No readable record '
'during existing processing')
trans.commit()
parser.add_argument('--test-url', dest="test_url",
action="store",
default=False,
help="Run the parser on the url provided and test things out")
args = parser.parse_args()
return args
if __name__ == "__main__":
args = parse_args()
if args.test_url:
# then we only want to test this one url and not process full lists
read = ReadUrl.parse(args.test_url)
print "META"
print "*" * 30
print read.content_type
print read.status
print read.status_message
print "\n\n"
if not read.is_image():
print read.content
else:
print "Url is an image"
