def getRelatedTags( tags ):
""" fetches the related tags for the given tags
@param list of tags
@return dictionary of related tags with count
"""
if type(tags).__name__ == 'str':
url = Twitter.TWITTER_SEARCH_URL % tags
else:
url = Twitter.TWITTER_SEARCH_URL % "+".join(tags)
f = Retrieve(Twitter.__name__).open(url)
# convert json into dict and remove null values with ""
search_results = eval(re.sub('null', '""', f.read()))
found_tags = []
related_tags = {}
for result in search_results['results']:
found_tags.extend(Twitter.RE_FIND_TAGS.findall( result['text']))
for tag in found_tags:
related_tags[tag.lower()] = related_tags.get(tag.lower(), 0) + 1
# todo: sort
return related_tags
def getRelatedTags(tags):
""" fetches the related tags for the given tags
@param list of tags
@return dictionary of related tags with count
"""
if type(tags).__name__ == 'str':
url = Twitter.TWITTER_SEARCH_URL % tags
else:
url = Twitter.TWITTER_SEARCH_URL % "+".join(tags)
f = Retrieve(Twitter.__name__).open(url)
# convert json into dict and remove null values with ""
search_results = eval(re.sub('null', '""', f.read()))
found_tags = []
related_tags = {}
for result in search_results['results']:
found_tags.extend(Twitter.RE_FIND_TAGS.findall(result['text']))
for tag in found_tags:
related_tags[tag.lower()] = related_tags.get(tag.lower(), 0) + 1
# todo: sort
return related_tags
def get_content(url):
""" returns the content from Flickr """
assert(url.startswith("http"))
f = Retrieve(Flickr.__name__).open(url)
content = f.read()
f.close()
return content
def get_content(url):
""" returns the content from Flickr """
assert (url.startswith("http"))
f = Retrieve(Flickr.__name__).open(url)
content = f.read()
f.close()
return content
def testRetrievalTimeout(self):
''' tests whether the socket timeout is honored by our class '''
SLOW_URL = "http://www.csse.uwa.edu.au/"
with raises(urllib2.URLError):
r = Retrieve(self.__class__.__name__,
default_timeout=0.1).open(SLOW_URL)
content = r.read()
r.close()
def _get_content( url ):
""" returns the content from delicious """
assert( url.startswith("http") )
f = Retrieve(Delicious.__name__).open(url)
content = f.read()
f.close()
sleep(1)
return content
def _get_content(url):
""" returns the content from delicious """
assert(url.startswith("http"))
f = Retrieve(Delicious.__name__).open(url)
content = f.read()
f.close()
sleep(1)
return content
def t_retrieve(url):
''' retrieves the given url from the web
@remarks
helper module for the testMultiProcessing unit test.
'''
r = Retrieve(__name__).open(url)
try:
content = r.read()
finally:
# this is required as GzipFile does not support the context protocol
# in python 2.6
r.close()
return content
def get_content(url):
""" returns the content from Technorati """
assert(url.startswith("http"))
logger.debug('Fetching content for URL %s' % url)
if (time.time() - Technorati.last_access) < SLEEP_TIME:
logger.debug('Sleeping %s seconds!' % SLEEP_TIME)
time.sleep(SLEEP_TIME)
Technorati.last_access = time.time()
f = Retrieve("%s_new" % Technorati.__name__).open(url)
content = f.read()
f.close()
return content
