def api_worker(worker_number):
"""stupidly simulates long running process"""
print('Start API {0} worker.'.format(worker_number))
global file_q
global api_q
diffbot = DiffbotClient()
while True:
url = api_q.get()
if url == 'kill':
print('Kill {0} api_worker'.format(worker_number))
break
# print('api_q {0} size {1}'.format(worker_number, api_q.qsize()))
try:
response = diffbot.request(url, API_TOKEN, 'article')
except requests.exceptions.HTTPError:
continue
if 'objects' in response:
obj = response['objects'][0]
if obj['text'] and obj.get('pageURL') == obj.get(
'resolvedPageURL'):
file_q.put(obj)
class DiffbotClientUnitTest(unittest.TestCase):
def setUp(self):
self.patcher = patch('client.requests.get', fake_get)
self.patcher.start()
self.client = DiffbotClient()
def tearDown(self):
self.patcher.stop()
def test_article_api(self):
url = "http://www.xconomy.com/san-francisco/2012/07/25/diffbot-is-using-computer-vision-to-reinvent-the-semantic-web/"
token = "SOME_TOKEN"
api = "article"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertIn('title', response)
self.assertEqual(
response['title'],
"Diffbot Is Using Computer Vision to Reinvent the Semantic Web")
def test_frontpage_api(self):
url = "http://www.huffingtonpost.com/"
token = "SOME_TOKEN"
api = "frontpage"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['tagName'], "dml")
self.assertIn('childNodes', response)
def test_product_api(self):
url = "http://www.overstock.com/Home-Garden/iRobot-650-Roomba-Vacuuming-Robot/7886009/product.html"
token = "SOME_TOKEN"
api = "product"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['type'], "product")
self.assertEqual(response['products'][0]['title'],
"iRobot 650 Roomba Vacuuming Robot")
def test_image_api(self):
url = "http://www.google.com/"
token = "SOME_TOKEN"
api = "image"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['title'], "Google")
self.assertEqual(response['images'][0]['url'],
"https://www.google.com/images/srpr/logo9w.png")
def test_analyze_api(self):
url = "http://www.twitter.com/"
token = "SOME_TOKEN"
api = "analyze"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['type'], "image")
self.assertEqual(response['title'], "Welcome to Twitter.")
def main():
diffbot = DiffbotClient()
token = API_TOKEN
url = "https://newtonfreelibrary.libcal.com/event/4924168"
api = "product"
response = diffbot.request(url, token, api)
print response
print type(response)
print response["objects"][0]["title"]
class DiffbotClientUnitTest(unittest.TestCase):
def setUp(self):
self.patcher = patch('client.requests.get', fake_get)
self.patcher.start()
self.client = DiffbotClient()
def tearDown(self):
self.patcher.stop()
def test_article_api(self):
url = "http://www.xconomy.com/san-francisco/2012/07/25/diffbot-is-using-computer-vision-to-reinvent-the-semantic-web/"
token = "SOME_TOKEN"
api = "article"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertIn('title', response)
self.assertEqual(response['title'], "Diffbot Is Using Computer Vision to Reinvent the Semantic Web")
def test_frontpage_api(self):
url = "http://www.huffingtonpost.com/"
token = "SOME_TOKEN"
api = "frontpage"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['tagName'], "dml")
self.assertIn('childNodes', response)
def test_product_api(self):
url = "http://www.overstock.com/Home-Garden/iRobot-650-Roomba-Vacuuming-Robot/7886009/product.html"
token = "SOME_TOKEN"
api = "product"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['type'], "product")
self.assertEqual(response['products'][0]['title'], "iRobot 650 Roomba Vacuuming Robot")
def test_image_api(self):
url = "http://www.google.com/"
token = "SOME_TOKEN"
api = "image"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['title'], "Google")
self.assertEqual(response['images'][0]['url'], "https://www.google.com/images/srpr/logo9w.png")
def test_analyze_api(self):
url = "http://www.twitter.com/"
token = "SOME_TOKEN"
api = "analyze"
version = 2
response = self.client.request(url, token, api, version=version)
self.assertEqual(response['type'], "image")
self.assertEqual(response['title'], "Welcome to Twitter.")
def swallowURL(url):
import time
diffbot = DiffbotClient()
token = API_TOKEN
api = "article"
response = diffbot.request(url, token, api, version=2)
#time.sleep(1)
if 'html' not in response:
return
subtexts = response['html'].split("<p>")
res = []
for t in subtexts:
outgt = clean(
t,
fix_unicode=True, # fix various unicode errors
to_ascii=True, # transliterate to closest ASCII representation
lower=False, # lowercase text
no_line_breaks=
True, # fully strip line breaks as opposed to only normalizing them
no_urls=False, # replace all URLs with a special token
no_emails=False, # replace all email addresses with a special token
no_phone_numbers=
False, # replace all phone numbers with a special token
no_numbers=False, # replace all numbers with a special token
no_digits=False, # replace all digits with a special token
no_currency_symbols=
False, # replace all currency symbols with a special token
no_punct=False, # fully remove punctuation
replace_with_email="<EMAIL>",
replace_with_phone_number="<PHONE>",
replace_with_currency_symbol="<CUR>",
lang="en" # set to 'de' for German special handling
)
outgt = re.sub("<.*?>", " ", outgt)
ogt = outgt.strip()
ogt = re.sub("\s\s+", " ", ogt)
ogt = re.sub('</?[a-z]+>', '', ogt)
ogt = ogt.replace("’", "")
ogt = ogt.replace("“", "")
ogt = ogt.replace("\n", "")
ogt = ogt.replace("\r", "")
ogt = ogt.replace("\\n", "")
if len(ogt) > 10:
res.append(outgt)
if len(res) > 2:
fields = [''.join(e for e in url if e.isalnum()), str(res)]
if 'http' in fields[0]:
with open('pdfs/data.csv', 'a') as f:
writer = csv.writer(f)
writer.writerow(fields)
def diffbotScrape(my_url):
global count
global json_count
global my_dict
count = count + 1
diffbot = DiffbotClient()
token = "2587daf076cad7bba4e58fd272780b2d"
url = my_url
api = "article"
response = diffbot.request(url, token, api, fields=['title', 'type'])
print("\nPrinting response:\n")
print(count)
#forgot to add to my dict before adding it to tthe json
my_dict[my_url] = response
print("Writing to my_dict...\n")
if (count == 15):
file = "diffbot" + str(json_count) + ".json"
with open(file, 'a+') as f:
json.dump(my_dict, f, sort_keys=True, indent=4)
count = 0
json_count += 1
my_dict = {}
from client import DiffbotClient
from config import API_TOKEN
import pprint
print "Calling article API endpoint on the url: http://shichuan.github.io/javascript-patterns/...\n"
diffbot = DiffbotClient()
token = API_TOKEN
version = 2
url = "http://shichuan.github.io/javascript-patterns/"
api = "article"
response = diffbot.request(url, token, api, version=2)
print "\nPrinting response:\n"
pp = pprint.PrettyPrinter(indent=4)
print pp.pprint(response)
print
print "Calling article API endpoint with fields specified on the url: http://shichuan.github.io/javascript-patterns/...\n"
diffbot = DiffbotClient()
token = API_TOKEN
version = 2
url = "http://shichuan.github.io/javascript-patterns/"
api = "article"
response = diffbot.request(url,
token,
api,
fields=['title', 'type'],
version=2)
print "\nPrinting response:\n"
pp = pprint.PrettyPrinter(indent=4)
print pp.pprint(response)
def setUp(self):
self.patcher = patch('client.requests.get', fake_get)
self.patcher.start()
self.client = DiffbotClient()
from client import DiffbotClient, DiffbotCrawl
from config import API_TOKEN
import pprint
import time
print(
"Calling article API endpoint on the url: http://shichuan.github.io/javascript-patterns/...\n"
)
diffbot = DiffbotClient()
token = API_TOKEN
url = "http://shichuan.github.io/javascript-patterns/"
api = "article"
response = diffbot.request(url, token, api)
print("\nPrinting response:\n")
pp = pprint.PrettyPrinter(indent=4)
print(pp.pprint(response))
print()
print(
"Calling article API endpoint with fields specified on the url: http://shichuan.github.io/javascript-patterns/...\n"
)
diffbot = DiffbotClient()
token = API_TOKEN
url = "http://shichuan.github.io/javascript-patterns/"
api = "article"
response = diffbot.request(url, token, api, fields=['title', 'type'])
print("\nPrinting response:\n")
pp = pprint.PrettyPrinter(indent=4)
print(pp.pprint(response))
print()
def setUp(self):
self.patcher = patch('client.requests.get', fake_get)
self.patcher.start()
self.client = DiffbotClient()
from client import DiffbotClient,DiffbotCrawl from config import API_TOKEN import pprint import time print "Calling article API endpoint on the url: http://shichuan.github.io/javascript-patterns/...\n" diffbot = DiffbotClient() token = API_TOKEN url = "http://shichuan.github.io/javascript-patterns/" api = "article" response = diffbot.request(url, token, api) print "\nPrinting response:\n" pp = pprint.PrettyPrinter(indent=4) print pp.pprint(response) print print "Calling article API endpoint with fields specified on the url: http://shichuan.github.io/javascript-patterns/...\n" diffbot = DiffbotClient() token = API_TOKEN url = "http://shichuan.github.io/javascript-patterns/" api = "article" response = diffbot.request(url, token, api, fields=['title', 'type']) print "\nPrinting response:\n" pp = pprint.PrettyPrinter(indent=4) print pp.pprint(response) print print "Calling frontpage API endpoint on the url: http://www.huffingtonpost.com/...\n" diffbot = DiffbotClient() token = API_TOKEN url = "http://www.huffingtonpost.com/"
