├── hosts ├── libs ├── cclib │ ├── __init__.py │ ├── data │ │ ├── crawl_index_2013_1.gz │ │ ├── crawl_index_2013_2.gz │ │ └── crawl_index_2014_1.gz │ └── commoncrawl.py └── setup.py ├── .gitignore ├── filequeue.py ├── worker.py ├── config.py ├── spotinstance.py ├── readme.md ├── fabfile.py ├── Monitor.ipynb ├── Demo.ipynb └── example.json /hosts: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /libs/cclib/__init__.py: -------------------------------------------------------------------------------- 1 | __author__ = 'aub3' 2 | -------------------------------------------------------------------------------- /libs/cclib/data/crawl_index_2013_1.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gfjreg/CommonCrawl/HEAD/libs/cclib/data/crawl_index_2013_1.gz -------------------------------------------------------------------------------- /libs/cclib/data/crawl_index_2013_2.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gfjreg/CommonCrawl/HEAD/libs/cclib/data/crawl_index_2013_2.gz -------------------------------------------------------------------------------- /libs/cclib/data/crawl_index_2014_1.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gfjreg/CommonCrawl/HEAD/libs/cclib/data/crawl_index_2014_1.gz -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | keys.py 2 | boto.cfg 3 | hosts 4 | temp.json 5 | *.pyc 6 | *.log 7 | .idea/* 8 | libs/build/* 9 | logs/* 10 | .ipynb_checkpoints/* 11 | -------------------------------------------------------------------------------- /libs/setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | __author__ = 'aub3' 3 | from distutils.core import setup 4 | 5 | setup(name='CommonCrawlLibrary', 6 | version='0.1', 7 | description='Python Distribution Utilities', 8 | author='Akshay Bhat', 9 | author_email='aub3 cornell.edu', 10 | url='http://www.datamininghobby.com/', 11 | packages=['cclib'], 12 | package_dir={'cclib': 'cclib'}, 13 | package_data={'cclib': ['data/*.gz']}, 14 | ) -------------------------------------------------------------------------------- /filequeue.py: -------------------------------------------------------------------------------- 1 | __author__ = 'aub3' 2 | from boto.sqs.connection import SQSConnection 3 | from boto.sqs.message import Message 4 | import base64 5 | 6 | class FileQueue(object): 7 | """ 8 | A simple queue of files stored on SQS. 9 | """ 10 | SQS = SQSConnection() 11 | 12 | def __init__(self,name,visibility_timeout=300,files=None): 13 | """ 14 | Requires list of files and queue name 15 | """ 16 | if files == None: 17 | files = [] 18 | self.name = name 19 | self.files = files 20 | self.visibility_timeout = visibility_timeout 21 | self.queue = FileQueue.SQS.get_queue(name) 22 | if not self.queue: 23 | self.queue = FileQueue.SQS.create_queue(self.name,visibility_timeout=self.visibility_timeout) # set as default timeout 24 | 25 | def add_files(self,count=None): 26 | """ 27 | if count is none then add all files to queue, otherwise add count files to queue 28 | """ 29 | message_buffer =[] 30 | if count is None: 31 | count = len(self.files) 32 | while count: 33 | count -= 1 34 | message_buffer.append((count,base64.b64encode(self.files.pop()),0)) # required to maintain compatibility with 35 | if len(message_buffer) > 9: 36 | self.queue.write_batch(message_buffer) 37 | message_buffer = [] 38 | self.queue.write_batch(message_buffer) 39 | 40 | 41 | def clear(self): 42 | """ 43 | Clears the queue. This is a costly operation. 44 | """ 45 | self.queue.clear() 46 | 47 | def __iter__(self): 48 | return self 49 | 50 | def next(self): # wait for 5 minutes after sending message 51 | """ iterate over the queue""" 52 | if self.queue: 53 | messages = self.queue.get_messages(1,visibility_timeout=self.visibility_timeout) 54 | if messages: 55 | for m in messages: 56 | return m 57 | raise StopIteration 58 | 59 | def delete_message(self,m): 60 | self.queue.delete_message(m) 61 | 62 | if __name__ == '__main__': 63 | from cclib import commoncrawl13 64 | crawl = commoncrawl13.CommonCrawl13() 65 | wat_queue = FileQueue('aksay_test_queue',crawl.wat) 66 | wat_queue.add_files(5) 67 | for m in wat_queue: 68 | print m.get_body() 69 | wat_queue.delete_message(m) 70 | -------------------------------------------------------------------------------- /worker.py: -------------------------------------------------------------------------------- 1 | __author__ = 'aub3' 2 | import logging 3 | from collections import defaultdict 4 | from cclib import commoncrawl 5 | from filequeue import FileQueue 6 | from boto.s3.connection import S3Connection 7 | from boto.s3.key import Key 8 | import json 9 | 10 | from config import OUTPUT_S3_BUCKET, JOB_QUEUE, CRAWL_ID 11 | 12 | logging.basicConfig(filename='worker.log',level=logging.DEBUG,format='%(asctime)s - %(name)s - %(levelname)s - %(message)s') 13 | logging.getLogger('boto').setLevel(logging.CRITICAL) 14 | 15 | CONN = S3Connection() 16 | BUCKET = CONN.get_bucket(OUTPUT_S3_BUCKET,validate=False) 17 | 18 | def store_S3(fname,data): 19 | try: 20 | item = Key(BUCKET) 21 | item.key = str(hash(fname))+'.json' 22 | item.set_contents_from_string(json.dumps(data),reduced_redundancy=True) # reduced_redundancy=True to save costs 23 | except: 24 | logging.exception("error while storing data on S3") 25 | 26 | 27 | def process_queue(queue,crawl,test=False): 28 | logging.debug("starting queue "+JOB_QUEUE) 29 | for m in queue: 30 | fname = m.get_body() 31 | logging.debug("starting "+fname) 32 | data = process_file(crawl.get_file(fname),fname,test) 33 | store_S3(fname,data) 34 | if test: 35 | logging.debug("did not delete the message") 36 | break # stop after processing one message 37 | else: 38 | queue.delete_message(m) 39 | logging.debug("finished "+fname) 40 | logging.debug("finished queue "+JOB_QUEUE) 41 | 42 | 43 | def process_file(fileobj,filename,test=False): 44 | count = 0 45 | counts = defaultdict(int) 46 | amazon = [] 47 | error = False 48 | try: 49 | for line in fileobj: 50 | line = line.strip() 51 | if line.startswith('WARC-Target-URI'): 52 | count += 1 53 | if "http://" in line: 54 | counts[line.split('http://')[1].split('/')[0]] += 1 55 | if "amazon.com" in line.lower(): 56 | amazon.append(line.split('WARC-Target-URI:')[1].strip()) 57 | except: 58 | logging.exception("error while processing file") 59 | error =True 60 | pass 61 | return {'metdata_lines':count, 62 | 'amazon':amazon, 63 | 'counts':[(k,v) for k,v in counts.iteritems() if v>10], 64 | "filename":filename, 65 | "error":error 66 | } 67 | 68 | if __name__ == '__main__': 69 | import sys 70 | if "test" in sys.argv: 71 | test = True 72 | else: 73 | test = False 74 | crawl = commoncrawl.CommonCrawl(CRAWL_ID) 75 | queue = FileQueue(JOB_QUEUE,files=None) 76 | process_queue(queue,crawl,test) -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- 1 | __author__ = 'aub3' 2 | # Put AWS credentials in /etc/boto.cfg for use on local machine 3 | key_filename = '/users/aub3/.ssh/cornellmacos.pem' # please replace this with path to your pem 4 | 5 | # following IAM role is used when launching instance 6 | IAM_ROLE = "ccSpot_role" 7 | IAM_PROFILE = "ccSpot_profile" 8 | IAM_POLICY_NAME = "ccSpt_policy" 9 | IAM_POLICY ="""{ 10 | "Version": "2012-10-17", 11 | "Statement": [ 12 | { 13 | "Sid": "Stmt1399521628000", 14 | "Effect": "Allow", 15 | "Action": [ 16 | "s3:*" 17 | ], 18 | "Resource": [ 19 | "*" 20 | ] 21 | }, 22 | { 23 | "Sid": "Stmt1399521640000", 24 | "Effect": "Allow", 25 | "Action": [ 26 | "sqs:*" 27 | ], 28 | "Resource": [ 29 | "*" 30 | ] 31 | } 32 | ] 33 | }""" 34 | 35 | 36 | ########## 37 | # 38 | # Instance Configuration 39 | # 40 | ######### 41 | price = 0.30 # 30 cents per hour slightly above the reserve price of the r3.8xlarge instance on the spot market 42 | instance_type = 'r3.8xlarge' 43 | image_id = 'ami-978d91fe' # default AMI for Amazon Linux HVM 44 | key_name = 'cornellmacos' # replace with name of your configured key-pair 45 | NUM_WORKERS = 40 # Number of worker processes per machine 46 | VISIBILITY_TIMEOUT = 500 #TODO Seconds during which a worker process has time to process the message 47 | 48 | ########## 49 | # 50 | # Job Configuration 51 | # 52 | ######### 53 | EC2_Tag = "cc_wat_13_2" 54 | JOB_QUEUE = 'wat_stats_2013_2' # SQS queue name 55 | OUTPUT_S3_BUCKET = 'wat_stats_2013_2' # S3 bucket 56 | CODE_BUCKET = "akshay_code" # bucket used to store code & configuration make sure this is different from output bucket 57 | CODE_KEY = "wat_stats_2013_2" # key for storing code which will be downloaded by user-data script 58 | FILE_TYPE = "wat" # Type of files you wish to process choose from {"wat","wet","text","warc"} 59 | CRAWL_ID = "2013_2" # 2nd crawl in 2013 60 | SPOT_REQUEST_VALID = 20 # Minutes within which the spot request must be full filled otherwise it is cancelled 61 | MAX_TIME_MINS = 55 # maxiumum amount of time the instance should run 60 * 10 hours = 600 minutes (This limits the cost in case you forget to terminate the instance) 62 | 63 | 64 | 65 | USER_DATA= """#!/usr/bin/env python 66 | from boto.s3.connection import S3Connection 67 | from boto.s3 import key 68 | import os 69 | 70 | os.system('yum update -y') 71 | # install GCC, Make, Setuptools etc. 72 | os.system('yum install -y gcc-c++') 73 | os.system('yum install -y openssl-devel') 74 | os.system('yum install -y make') 75 | os.system('yum install -y python-devel') 76 | os.system('yum install -y python-setuptools') 77 | os.system('easy_install flask') 78 | os.system('yum install -y gcc-c++ &') 79 | os.system('screen -d -m shutdown -h ; sleep 1') 80 | 81 | S3 = S3Connection() 82 | code_bucket = S3.get_bucket("") # Bucket where code is stored 83 | code = key.Key(code_bucket) 84 | code.key = "" # Key for the code 85 | code.get_contents_to_filename("/root/code.tar.gz") 86 | os.system('cd /root/;tar -xzf code.tar.gz') 87 | os.system('cd /root/code/libs;python setup.py install') 88 | for worker in range(): 89 | os.system('cd /root/;screen -d -m python code/worker.py; sleep 1') 90 | """.replace("",CODE_BUCKET).replace("",CODE_KEY).replace("",str(NUM_WORKERS)).replace("",str(MAX_TIME_MINS)) 91 | 92 | -------------------------------------------------------------------------------- /spotinstance.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | __author__ = 'aub3' 3 | 4 | import boto.ec2,time,datetime 5 | CONN = boto.ec2.connect_to_region("us-east-1") 6 | 7 | class SpotInstance(object): 8 | 9 | @classmethod 10 | def get_spot_instances(cls,EC2_Tag): 11 | """ 12 | Get all spot instances with specified EC2_Tag 13 | """ 14 | requests = CONN.get_all_spot_instance_requests() 15 | instances = [] 16 | for request in requests: 17 | instances.append(SpotInstance(EC2_Tag,request.id,request.instance_id)) 18 | return instances 19 | 20 | def __init__(self,tag,request_id=None,instance_id=None,): 21 | self.request_id = request_id 22 | self.instance_id = instance_id 23 | self.public_dns_name = None 24 | self.price = None 25 | self.instance_type = None 26 | self.image_id = None 27 | self.key_name = None 28 | self.fulfilled = False 29 | self.instance_object = None 30 | self.valid_until = None 31 | self.tag = tag 32 | self.instance_profile = None 33 | self.user_data = "" 34 | if self.instance_id: 35 | self.fulfilled = True 36 | self.get_instance() 37 | 38 | def add_tag(self): 39 | if self.request_id: 40 | CONN.create_tags([self.request_id], {"Tag":self.tag}) 41 | 42 | 43 | def request_instance(self,price,instance_type,image_id,key_name,user_data,instance_profile,valid_mins): 44 | self.price = price 45 | self.instance_type = instance_type 46 | self.image_id = image_id 47 | self.key_name = key_name 48 | self.user_data = user_data 49 | self.instance_profile = instance_profile 50 | print "You are launching a spot instance request." 51 | print "It is important that you closely monitor and cancel unfilled requests using AWS web console." 52 | if raw_input("\n Please enter 'yes' to start >> ")=='yes': 53 | self.valid_until = (datetime.datetime.utcnow()+datetime.timedelta(minutes=valid_mins)).isoformat() # valid for 20 minutes from now 54 | print "request valid until UTC: ", self.valid_until 55 | spot_request = CONN.request_spot_instances(price=price,instance_type=instance_type,image_id=image_id,key_name=key_name,valid_until=self.valid_until,user_data=self.user_data,instance_profile_name=self.instance_profile) 56 | self.request_id = spot_request[0].id 57 | time.sleep(4) # wait for some time, otherwise AWS throws up an error 58 | self.add_tag() 59 | print "requesting a spot instance" 60 | else: 61 | print "Did not request a spot instance" 62 | 63 | def check_allocation(self): 64 | if self.request_id: 65 | instance_id = CONN.get_all_spot_instance_requests(request_ids=[self.request_id])[0].instance_id 66 | while instance_id is None: 67 | print "waiting" 68 | time.sleep(60) # Checking every minute 69 | print "Checking job instance id for this spot request" 70 | instance_id = CONN.get_all_spot_instance_requests(request_ids=[self.request_id])[0].instance_id 71 | self.instance_id = instance_id 72 | self.get_instance() 73 | 74 | def get_instance(self): 75 | reservations = CONN.get_all_reservations() 76 | for reservation in reservations: 77 | instances = reservation.instances 78 | for instance in instances: 79 | if instance.id == self.instance_id: 80 | self.public_dns_name = instance.public_dns_name 81 | self.instance_object = instance 82 | return 83 | def status(self): 84 | return "request",self.request_id,"spot instance",self.instance_id,"with DNS",self.public_dns_name 85 | 86 | def terminate(self): 87 | print "terminating spot instance",self.instance_id,self.public_dns_name 88 | if self.instance_object: 89 | self.instance_object.terminate() -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- 1 | Common Crawl Dev 2 | ================= 3 | A simple app for mining common crawl data 4 | 5 | Author 6 | -------- 7 | Akshay Uday Bhat (www.akshaybhat.com) 8 | 9 | 10 | Quick Demo and Documentation 11 | -------- 12 | You can view a quick demo and documentation [on ipython notebook viewer](http://nbviewer.ipython.org/github/AKSHAYUBHAT/CommonCrawl/blob/master/Demo.ipynb) . 13 | 14 | [http://nbviewer.ipython.org/github/AKSHAYUBHAT/CommonCrawl/blob/master/Demo.ipynb](http://nbviewer.ipython.org/github/AKSHAYUBHAT/CommonCrawl/blob/master/Demo.ipynb) 15 | 16 | Description: 17 | -------- 18 | This repo contains code for accessing Common Crawl crawls (2013 & later) & code for launching spot instances for analyzing the crawl data. 19 | The code follows most of the best practices, such as: 20 | 21 | 1. An SQS queue is used to track progress of the job. 22 | 23 | 2. Output is stored in an S3 Bucket with reduced redundancy to reduce costs 24 | 25 | 3. Permissions are passed to EC2 instances via IAM roles and instance profiles. Only required services S3 & SQS are authorized. 26 | 27 | 4. Code is stored in an S3 bucket and is downloaded by the spot instance when instance is allocated via user_data script. 28 | 29 | 5. Fabric is used to run tasks to get information, execute code and terminate instances. 30 | 31 | 32 | The current worker.py implements a simple function which stores count of urls and domains with at least 10 urls in the file. 33 | The function and configuration can be easily modified to support more complex analysis. 34 | 35 | Dependancies 36 | -------- 37 | - Boto (latest) 38 | - Fabric (1.8.1) 39 | - Flask (Optional) 40 | 41 | 42 | 43 | Configuration 44 | -------- 45 | 46 | - Access & Security 47 | - Put boto configuration in /etc/boto.cfg on your local machine, note that this information is never sent to EC2 machines 48 | - key_filename = Path to your private key file 49 | - IAM_ROLE = "ccSpot_role" # Role name, no need to change 50 | - IAM_PROFILE = "ccSpot_profile" # Profile name, no need to change 51 | - IAM_POLICY_NAME = "ccSpt_policy" # Policy name, no need to change 52 | - IAM_POLICY = # Policy, no need to change unless you are accessing other services such as SNS etc. 53 | 54 | - Instance Configuration 55 | - price = price in dollars for a spot instance 56 | - instance_type = 57 | - image_id = # Amazon Machine Image (AMI) ID 58 | - key_name = name of your configured key-pair, should be same key as the pem file above 59 | - NUM_WORKERS = Number of worker processes per machine depends on the instance type & memory foot print 60 | - VISIBILITY_TIMEOUT = Seconds during which a worker process has time to process the message, this value should be the maximum time a worker process will take to process a single process 61 | - MAX_TIME_MINS = 230 # maxiumum amount of time the instance should run 60 * 3 + 50 mins = 230 minutes (This limits the cost in case you forget to terminate the instance) 62 | 63 | - Job Configuration 64 | - EC2_Tag = "cc_wat_13_2" 65 | - JOB_QUEUE = SQS queue name 66 | - OUTPUT_S3_BUCKET = S3 bucket 67 | - CODE_BUCKET = bucket used to store code & configuration make sure this is different from output bucket above 68 | - CODE_KEY = key for storing code which will be downloaded by user-data script 69 | - FILE_TYPE = "wat" # Type of files you wish to process choose from {"wat","wet","text","warc"} 70 | - CRAWL_ID = crawl id choose from { '2013_1','2013_2','2014_1',"ALL"} 71 | - USED_DATA = script run by the spot instance the "first time" it is booted up 72 | 73 | 74 | Instructions / Tasks 75 | -------- 76 | 1. AWS credentials should be stored in /etc/boto.cfg, the credentials are not transferred 77 | 2. To install library locally run "fab update_lib" 78 | 3. To set up job run "fab setup_job", this will create IAM roles, S3 output bucket and SQS queue. 79 | 4. To test worker script run "fab test_worker" 80 | 5. To save code to S3 run "fab push_code" 81 | 6. To request spot instances run "fab request_spot_instance" the spot instance once allocated will start running code automatically. 82 | 7. To list current spot instances run "fab ls_instances" 83 | 8. To terminate all instances run "fab terminate_instances" (NOTE its important that you manually terminate all instances.) 84 | 85 | Optional 86 | -------- 87 | * Use "fab ls_bucket" to check status of the output bucket and to download one randomly selected key to temp.json. 88 | * Use "fab rm_bucket:bucket_name" to delete a bucket and all keys inside it. 89 | 90 | Files 91 | -------- 92 | * libs/setup.py 93 | 94 | * libs/cclib/commoncrawl13.py 95 | 96 | * libs/cclib/data/*.gz pickle files containing list of keys/files in each crawl 97 | 98 | * config.py Contains configuration for launching job, identifiers for bucket, queue etc. 99 | 100 | * worker.py Code executed on each file in the crawl 101 | 102 | * fabfile.py Contains tasks for setting up, running, monitoring and terminating jobs. 103 | 104 | * spotinstance.py A small class to keep track of spot instance requests. 105 | 106 | * filequeue.py A small class to keep track of files in SQS queue. 107 | 108 | * example.json Example of output stored in the bucket from one file, using current worker.py -------------------------------------------------------------------------------- /libs/cclib/commoncrawl.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | __author__ = 'aub3' 3 | import pickle,gzip,os 4 | from boto.s3.connection import S3Connection 5 | from boto.s3.key import Key 6 | from StringIO import StringIO 7 | 8 | 9 | class CommonCrawl(object): 10 | file_types = ["wat","wet","warc","text"] 11 | crawl_prefix = { 12 | '2013_1':'common-crawl/crawl-data/CC-MAIN-2013-20/segments/', 13 | '2013_2':'common-crawl/crawl-data/CC-MAIN-2013-48/segments/', 14 | '2014_1':'common-crawl/crawl-data/CC-MAIN-2014-10/segments/', 15 | } 16 | crawl_id_list = ['2013_1','2013_2','2014_1',"ALL"] 17 | 18 | def __init__(self,crawl_id,aws_key=None,aws_secret=None,generate=False): 19 | """ 20 | You can either provide a pickle with list of files or iterate over the segments. 21 | """ 22 | self.crawl_id = crawl_id 23 | self.aws_key = aws_key 24 | self.aws_secret = aws_secret 25 | self.files = [] 26 | if self.crawl_id == 'ALL': 27 | for cid in CommonCrawl.crawl_id_list: 28 | if cid != 'ALL': 29 | self.get_index(generate,cid) 30 | else: 31 | self.get_index(generate,crawl_id) 32 | self.warc = [key for key in self.files if '/warc/' in key] 33 | self.text = [key for key in self.files if '/text/' in key] 34 | self.wet = [key for key in self.files if '/wet/' in key] 35 | self.wat = [key for key in self.files if '/wat/' in key] 36 | self.CONN = None 37 | self.bucket = None 38 | 39 | def get_index(self,generate,cid): 40 | if generate: 41 | self.download() 42 | else: 43 | filename = os.path.dirname(__file__)+'/data/crawl_index_'+cid+'.gz' 44 | fh = gzip.open(filename) 45 | self.files += pickle.load(fh) 46 | fh.close() 47 | 48 | def get_file_list(self,file_type): 49 | if file_type == 'warc': 50 | return self.warc 51 | elif file_type == 'text': 52 | return self.text 53 | elif file_type == 'wet': 54 | return self.wet 55 | elif file_type == 'wat': 56 | return self.wat 57 | else: 58 | raise ValueError,"unknown file type" 59 | 60 | 61 | 62 | def download(self): 63 | """ 64 | Downloads list of files iterating through all segments 65 | """ 66 | if self.aws_key and self.aws_secret: 67 | self.CONN = S3Connection(self.aws_key,self.aws_secret) 68 | else: 69 | self.CONN = S3Connection() 70 | self.bucket = self.CONN.get_bucket('aws-publicdatasets',validate=False) 71 | self.files += [key.name.encode('utf-8') for key in self.bucket.list(CommonCrawl.crawl_prefix[crawl_id])] 72 | 73 | def store(self): 74 | """ 75 | Stores list of files in a local pickle file. 76 | """ 77 | filename = os.path.dirname(__file__)+'/data/crawl_index_'+self.crawl_id+'.gz' 78 | fh = gzip.open(filename,'w') 79 | pickle.dump(self.files,fh) 80 | fh.close() 81 | 82 | def get_file(self,key,compressed_string=False,headers=None): 83 | """ 84 | Downloads file from AWS S3 and returns a GzipFile object. 85 | Optionally if compressed_string == True then it can return the compressed data as a string. 86 | """ 87 | if not self.CONN: 88 | if self.aws_key and self.aws_secret: 89 | self.CONN = S3Connection(self.aws_key,self.aws_secret) 90 | else: 91 | self.CONN = S3Connection() 92 | if not self.bucket: 93 | self.bucket = self.CONN.get_bucket('aws-publicdatasets',validate=False) 94 | item = Key(self.bucket) 95 | item.key = key 96 | if compressed_string: 97 | if headers: 98 | return item.get_contents_as_string(headers=headers) 99 | else: 100 | return item.get_contents_as_string() 101 | else: 102 | if headers: 103 | return gzip.GzipFile(fileobj=StringIO(item.get_contents_as_string(headers=headers))) 104 | else: 105 | return gzip.GzipFile(fileobj=StringIO(item.get_contents_as_string())) 106 | 107 | 108 | if __name__ == '__main__': 109 | # Generating data 110 | crawl_id = 'ALL' 111 | crawl = CommonCrawl(crawl_id) 112 | for file_type in CommonCrawl.file_types: 113 | print file_type,len(crawl.get_file_list(file_type)),crawl.get_file_list(file_type)[:10] 114 | print crawl_id,"finished" 115 | crawl_id = '2013_1' 116 | crawl = CommonCrawl(crawl_id) 117 | for file_type in CommonCrawl.file_types: 118 | print file_type,len(crawl.get_file_list(file_type)),crawl.get_file_list(file_type)[:10] 119 | print crawl_id,"finished" 120 | crawl_id = '2013_2' 121 | crawl = CommonCrawl(crawl_id) 122 | for file_type in CommonCrawl.file_types: 123 | print file_type,len(crawl.get_file_list(file_type)),crawl.get_file_list(file_type)[:10] 124 | print crawl_id,"finished" 125 | crawl_id = '2014_1' 126 | crawl = CommonCrawl(crawl_id) 127 | for file_type in CommonCrawl.file_types: 128 | print file_type,len(crawl.get_file_list(file_type)),crawl.get_file_list(file_type)[:10] 129 | print crawl_id,"finished" 130 | 131 | -------------------------------------------------------------------------------- /fabfile.py: -------------------------------------------------------------------------------- 1 | __author__ = 'aub3' 2 | from fabric.api import env,local,run,sudo,put,cd,lcd 3 | from config import * 4 | from spotinstance import * 5 | import filequeue 6 | import logging,json 7 | logging.basicConfig(filename='fab.log',level=logging.DEBUG,format='%(asctime)s - %(name)s - %(levelname)s - %(message)s') 8 | 9 | 10 | env.user = 'ec2-user' 11 | env.hosts = [line.strip() for line in file("hosts").readlines()] 12 | env.key_filename = key_filename 13 | 14 | def setup_iam(): 15 | """ 16 | Sets up IAM policy, roles and instance profile 17 | """ 18 | from boto.iam.connection import IAMConnection 19 | IAM = IAMConnection() 20 | profile = IAM.create_instance_profile(IAM_PROFILE) 21 | role = IAM.create_role(IAM_ROLE) 22 | IAM.add_role_to_instance_profile(IAM_PROFILE, IAM_ROLE) 23 | IAM.put_role_policy(IAM_ROLE, IAM_POLICY_NAME, IAM_POLICY) 24 | 25 | def setup_job(): 26 | """ 27 | Sets up the queue adds all files (text or warc or wat or wet), creates bucket to store output 28 | """ 29 | #IAM 30 | try: 31 | setup_iam() 32 | except: 33 | print "Error while setting up IAM PROFILE, most likely due to existing profile" 34 | logging.exception("Error while setting up IAM PROFILE, most likely due to existing profile") 35 | pass 36 | #S3 bucket 37 | from boto.s3.connection import S3Connection 38 | from cclib.commoncrawl import CommonCrawl 39 | logging.getLogger('boto').setLevel(logging.CRITICAL) 40 | import filequeue 41 | S3 = S3Connection() 42 | logging.info("Creating bucket "+OUTPUT_S3_BUCKET) 43 | S3.create_bucket(OUTPUT_S3_BUCKET) 44 | logging.info("bucket created") 45 | # SQS 46 | crawl = CommonCrawl(CRAWL_ID) 47 | file_list = crawl.get_file_list(FILE_TYPE) # Text files 48 | file_queue = filequeue.FileQueue(JOB_QUEUE,VISIBILITY_TIMEOUT,file_list) 49 | logging.debug("Adding "+str(len(file_list))+" "+FILE_TYPE+" files to queue "+JOB_QUEUE) 50 | file_queue.add_files() 51 | logging.debug("Finished adding files") 52 | print "Finished adding files" 53 | 54 | 55 | def setup_instance(home_dir='/home/ec2-user'): 56 | """ 57 | Updates, installs necessary packages on an EC2 instance. 58 | Upload library, boto configuration, worker code. 59 | Make sure that any changes made here are also reflected in USER_DATA script in config 60 | """ 61 | sudo('yum update -y') 62 | sudo('yum install -y gcc-c++') 63 | sudo('yum install -y openssl-devel') 64 | sudo('yum install -y make') 65 | sudo('yum install -y python-devel') 66 | sudo('yum install -y python-setuptools') 67 | sudo('easy_install flask') 68 | try: 69 | sudo('rm -rf '+home_dir+'/*') 70 | except: 71 | pass 72 | put('libs','~') 73 | put('config.py','~/config.py') 74 | put('filequeue.py','~/filequeue.py') 75 | put('worker.py','~/worker.py') 76 | with cd(home_dir+'/libs'): # using ~ causes an error with sudo since ~ turns into /root/ 77 | sudo('python setup.py install') 78 | sudo('rm -rf '+home_dir+'/libs') 79 | 80 | 81 | def push_code(): 82 | """ 83 | Bundles worker code, library & configuration in to a zipped files and store it on S3. 84 | Finally updates 85 | """ 86 | from boto.s3.connection import S3Connection 87 | from boto.s3 import key 88 | try: 89 | local("rm -r code") 90 | except: 91 | pass 92 | local("mkdir code") 93 | local("cp config.py code/config.py") 94 | local("cp filequeue.py code/filequeue.py") 95 | local("cp -r libs code/libs") 96 | local("cp worker.py code/worker.py") 97 | local("tar -zcvf code.tar.gz code") 98 | S3 = S3Connection() 99 | code_bucket = S3.create_bucket(CODE_BUCKET) 100 | code = key.Key(code_bucket) 101 | code.key = CODE_KEY 102 | code.set_contents_from_filename("code.tar.gz") 103 | local("rm code.tar.gz") 104 | local("rm -r code") 105 | logging.info("code pushed to bucket "+CODE_BUCKET+" key "+CODE_KEY) 106 | 107 | 108 | def ls_instances(): 109 | """ 110 | Lists current EC2 instances with current Job tag, and stores their public_dns_name to hosts. 111 | """ 112 | with open('hosts','w') as fh: 113 | for instance in SpotInstance.get_spot_instances(EC2_Tag): 114 | print instance.status() 115 | if instance.public_dns_name: 116 | fh.write(instance.public_dns_name+'\n') 117 | print "Information about current spot instance has been added to hosts.py" 118 | 119 | 120 | def request_spot_instance(): 121 | """ 122 | Lists current EC2 instances 123 | """ 124 | spot = SpotInstance(EC2_Tag) 125 | spot.request_instance(price,instance_type,image_id,key_name,USER_DATA,IAM_PROFILE,SPOT_REQUEST_VALID) 126 | 127 | 128 | def terminate_instances(): 129 | """ 130 | Terminates all spot instances, clear hosts file 131 | """ 132 | for s in SpotInstance.get_spot_instances(EC2_Tag): 133 | print "terminating", s.status() 134 | if s.instance_object and s.instance_object.state_code != 48: 135 | s.terminate() 136 | print "terminated" 137 | with file("hosts","w") as f: 138 | f.write("") 139 | 140 | def update_lib(): 141 | """ 142 | Update & install common crawl library locally 143 | """ 144 | with lcd('libs'): 145 | try: 146 | local('rm -r build') 147 | except: 148 | pass 149 | local('python setup.py install') 150 | local('rm -r build') 151 | 152 | def run_workers(N=NUM_WORKERS,IAM=False,home_dir='/home/ec2-user'): 153 | """ 154 | Starts N process running AWS/worker.py 155 | """ 156 | with cd(home_dir): 157 | for _ in range(N): 158 | run('screen -d -m python worker.py; sleep 1') 159 | 160 | 161 | def rm_bucket(bucket_name): 162 | """ 163 | Deletes the specified bucket 164 | bucket_name : str 165 | """ 166 | import os 167 | os.system('aws s3 rb s3://'+bucket_name+' --force') 168 | 169 | def ls_bucket(bucket_name=OUTPUT_S3_BUCKET): 170 | """ 171 | Selects one key from the bucket store locally and runs less command 172 | """ 173 | from boto.s3.connection import S3Connection 174 | from boto.s3 import key 175 | logging.getLogger('boto').setLevel(logging.CRITICAL) 176 | import random 177 | S3 = S3Connection() 178 | bucket = S3.get_bucket(bucket_name) 179 | keys = [example_key for example_key in bucket.list()] 180 | if keys: 181 | example = key.Key(bucket) 182 | example.key = random.sample(keys,1)[0] 183 | example.get_contents_to_filename("temp.json") 184 | with open("output_keys.json",'w') as fh: 185 | fh.write(json.dumps(keys)) 186 | print "Number of keys in the output bucket ",len(keys) 187 | print "a randomly selected key is written to temp.json" 188 | print "list of keys are stored in output_keys.json" 189 | 190 | def kill_python_processes(): 191 | """ 192 | Kills all python processes on remote hosts 193 | """ 194 | sudo("killall python") 195 | 196 | def test_worker(): 197 | """ 198 | Runs worker.py in test mode after updating the local version of the common crawl library 199 | """ 200 | update_lib() 201 | try: 202 | local("rm worker.log") 203 | except: 204 | pass 205 | local("python worker.py test") 206 | 207 | -------------------------------------------------------------------------------- /Monitor.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "metadata": { 3 | "name": "", 4 | "signature": "sha256:4d28f1686e8299d8a0ba7db1fd003ffd93eb3bcd3d13a27f35f8ce87780818c0" 5 | }, 6 | "nbformat": 3, 7 | "nbformat_minor": 0, 8 | "worksheets": [ 9 | { 10 | "cells": [ 11 | { 12 | "cell_type": "heading", 13 | "level": 2, 14 | "metadata": {}, 15 | "source": [ 16 | "Monitor the current state of the job using this notebook." 17 | ] 18 | }, 19 | { 20 | "cell_type": "code", 21 | "collapsed": false, 22 | "input": [ 23 | "import random,logging,config,spotinstance\n", 24 | "from boto.s3.connection import S3Connection\n", 25 | "from boto.s3 import key\n", 26 | "from boto.sqs.connection import SQSConnection\n", 27 | "logging.getLogger('boto').setLevel(logging.CRITICAL)" 28 | ], 29 | "language": "python", 30 | "metadata": {}, 31 | "outputs": [], 32 | "prompt_number": 9 33 | }, 34 | { 35 | "cell_type": "heading", 36 | "level": 4, 37 | "metadata": {}, 38 | "source": [ 39 | "List of currently running instances" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "collapsed": false, 45 | "input": [ 46 | "for instance in spotinstance.SpotInstance.get_spot_instances(config.EC2_Tag):\n", 47 | " print instance.status()" 48 | ], 49 | "language": "python", 50 | "metadata": {}, 51 | "outputs": [], 52 | "prompt_number": 10 53 | }, 54 | { 55 | "cell_type": "heading", 56 | "level": 4, 57 | "metadata": {}, 58 | "source": [ 59 | "Contents of the SQS queue" 60 | ] 61 | }, 62 | { 63 | "cell_type": "code", 64 | "collapsed": false, 65 | "input": [], 66 | "language": "python", 67 | "metadata": {}, 68 | "outputs": [], 69 | "prompt_number": 10 70 | }, 71 | { 72 | "cell_type": "heading", 73 | "level": 4, 74 | "metadata": {}, 75 | "source": [ 76 | "Contents of the output bucket" 77 | ] 78 | }, 79 | { 80 | "cell_type": "code", 81 | "collapsed": false, 82 | "input": [ 83 | "S3 = S3Connection()\n", 84 | "bucket = S3.get_bucket(config.OUTPUT_S3_BUCKET)\n", 85 | "keys = [example_key for example_key in bucket.list()]\n", 86 | "with open(\"output_keys.json\",'w') as fh:\n", 87 | " fh.write(json.dumps(keys))\n", 88 | "print \"list of keys are stored in output_keys.json\"\n", 89 | "print \"Number of keys in the output bucket \",len(keys)" 90 | ], 91 | "language": "python", 92 | "metadata": {}, 93 | "outputs": [ 94 | { 95 | "ename": "S3ResponseError", 96 | "evalue": "S3ResponseError: 403 Forbidden\n", 97 | "output_type": "pyerr", 98 | "traceback": [ 99 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[0;31mS3ResponseError\u001b[0m Traceback (most recent call last)", 100 | "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mS3\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mS3Connection\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mbucket\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mS3\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_bucket\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mOUTPUT_S3_BUCKET\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mkeys\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mexample_key\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mexample_key\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mbucket\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"output_keys.json\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'w'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mfh\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mfh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdumps\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", 101 | "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/boto/s3/connection.pyc\u001b[0m in \u001b[0;36mget_bucket\u001b[0;34m(self, bucket_name, validate, headers)\u001b[0m\n\u001b[1;32m 469\u001b[0m \"\"\"\n\u001b[1;32m 470\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mvalidate\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 471\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhead_bucket\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbucket_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mheaders\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 472\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 473\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbucket_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbucket_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", 102 | "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/boto/s3/connection.pyc\u001b[0m in \u001b[0;36mhead_bucket\u001b[0;34m(self, bucket_name, headers)\u001b[0m\n\u001b[1;32m 502\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_code\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'AccessDenied'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 503\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_message\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'Access Denied'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 504\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 505\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstatus\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m404\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 506\u001b[0m \u001b[0;31m# For backward-compatibility, we'll populate part of the exception\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", 103 | "\u001b[0;31mS3ResponseError\u001b[0m: S3ResponseError: 403 Forbidden\n" 104 | ] 105 | } 106 | ], 107 | "prompt_number": 11 108 | }, 109 | { 110 | "cell_type": "heading", 111 | "level": 4, 112 | "metadata": {}, 113 | "source": [ 114 | "Randomly selected key from the bucket" 115 | ] 116 | }, 117 | { 118 | "cell_type": "code", 119 | "collapsed": false, 120 | "input": [ 121 | "if keys:\n", 122 | " example = key.Key(bucket)\n", 123 | " example.key = random.sample(keys,1)[0]\n", 124 | " data = example.get_contents_to_string()" 125 | ], 126 | "language": "python", 127 | "metadata": {}, 128 | "outputs": [ 129 | { 130 | "ename": "NameError", 131 | "evalue": "name 'keys' is not defined", 132 | "output_type": "pyerr", 133 | "traceback": [ 134 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", 135 | "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mif\u001b[0m \u001b[0mkeys\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mexample\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mKey\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbucket\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mexample\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msample\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mexample\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_contents_to_string\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", 136 | "\u001b[0;31mNameError\u001b[0m: name 'keys' is not defined" 137 | ] 138 | } 139 | ], 140 | "prompt_number": 7 141 | }, 142 | { 143 | "cell_type": "code", 144 | "collapsed": false, 145 | "input": [], 146 | "language": "python", 147 | "metadata": {}, 148 | "outputs": [] 149 | } 150 | ], 151 | "metadata": {} 152 | } 153 | ] 154 | } -------------------------------------------------------------------------------- /Demo.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "metadata": { 3 | "name": "", 4 | "signature": "sha256:d02efa218ae5097c242030dfff5a3a993f7fccb9ef9239a7c8355959200ddf75" 5 | }, 6 | "nbformat": 3, 7 | "nbformat_minor": 0, 8 | "worksheets": [ 9 | { 10 | "cells": [ 11 | { 12 | "cell_type": "heading", 13 | "level": 1, 14 | "metadata": {}, 15 | "source": [ 16 | "Common Crawl demo" 17 | ] 18 | }, 19 | { 20 | "cell_type": "heading", 21 | "level": 6, 22 | "metadata": {}, 23 | "source": [ 24 | "To run this demo you must install and configure boto library. Ensure that boto has access to your AWS credentials." 25 | ] 26 | }, 27 | { 28 | "cell_type": "code", 29 | "collapsed": false, 30 | "input": [ 31 | "from cclib import commoncrawl" 32 | ], 33 | "language": "python", 34 | "metadata": {}, 35 | "outputs": [], 36 | "prompt_number": 1 37 | }, 38 | { 39 | "cell_type": "heading", 40 | "level": 3, 41 | "metadata": {}, 42 | "source": [ 43 | "Listing Crawls & Crawl Identifiers" 44 | ] 45 | }, 46 | { 47 | "cell_type": "markdown", 48 | "metadata": {}, 49 | "source": [ 50 | "Common Crawl project crawls the web every few months. Following is a list of Crawls which can be currently retrived using the library. Note that craws before 2013 used Hadoop Sequence file format instead of the current WARC format and cannot be retrived using this library" 51 | ] 52 | }, 53 | { 54 | "cell_type": "code", 55 | "collapsed": false, 56 | "input": [ 57 | "print 'Crawl ID'\n", 58 | "print '\\n'.join(commoncrawl.CommonCrawl.crawl_id_list)" 59 | ], 60 | "language": "python", 61 | "metadata": {}, 62 | "outputs": [ 63 | { 64 | "output_type": "stream", 65 | "stream": "stdout", 66 | "text": [ 67 | "Crawl ID\n", 68 | "2013_1\n", 69 | "2013_2\n", 70 | "2014_1\n", 71 | "ALL\n" 72 | ] 73 | } 74 | ], 75 | "prompt_number": 2 76 | }, 77 | { 78 | "cell_type": "markdown", 79 | "metadata": {}, 80 | "source": [ 81 | "The 'ALL' identifiers contains files from all crawls." 82 | ] 83 | }, 84 | { 85 | "cell_type": "code", 86 | "collapsed": false, 87 | "input": [ 88 | "CRAWLS = { crawl_id : commoncrawl.CommonCrawl(crawl_id) for crawl_id in commoncrawl.CommonCrawl.crawl_id_list }" 89 | ], 90 | "language": "python", 91 | "metadata": {}, 92 | "outputs": [], 93 | "prompt_number": 3 94 | }, 95 | { 96 | "cell_type": "heading", 97 | "level": 3, 98 | "metadata": {}, 99 | "source": [ 100 | "Getting list of files in each crawl" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "collapsed": false, 106 | "input": [ 107 | "print '\\t'.join(['ID','WARC','WET','WAT','text(only first crawl in 2013)'])\n", 108 | "for crawlid, crawl in CRAWLS.iteritems():\n", 109 | " print '\\t'.join([crawlid,str(len(crawl.warc)),str(len(crawl.wet)),str(len(crawl.wat)),str(len(crawl.text))])" 110 | ], 111 | "language": "python", 112 | "metadata": {}, 113 | "outputs": [ 114 | { 115 | "output_type": "stream", 116 | "stream": "stdout", 117 | "text": [ 118 | "ID\tWARC\tWET\tWAT\ttext(only first crawl in 2013)\n", 119 | "ALL\t139200\t132462\t132462\t31600\n", 120 | "2014_1\t55700\t55699\t55699\t0\n", 121 | "2013_1\t31600\t31568\t31568\t31600\n", 122 | "2013_2\t51900\t45195\t45195\t0\n" 123 | ] 124 | } 125 | ], 126 | "prompt_number": 4 127 | }, 128 | { 129 | "cell_type": "heading", 130 | "level": 3, 131 | "metadata": {}, 132 | "source": [ 133 | "Accessing Common Crawl files" 134 | ] 135 | }, 136 | { 137 | "cell_type": "markdown", 138 | "metadata": {}, 139 | "source": [ 140 | "Reading a WAT (Metadata) file from the second crawl in 2013 and printing first 25 lines from it." 141 | ] 142 | }, 143 | { 144 | "cell_type": "code", 145 | "collapsed": false, 146 | "input": [ 147 | "import random\n", 148 | "crawl_id = '2013_2'\n", 149 | "example_wat_filename = random.choice(CRAWLS[crawl_id].wat)\n", 150 | "count = 50\n", 151 | "example_wat_fileobject = CRAWLS[crawl_id].get_file(example_wat_filename,headers = {'Range': 'bytes=0-100000'})\n", 152 | "for line in example_wat_fileobject:\n", 153 | " if line.strip():\n", 154 | " count -=1\n", 155 | " if count < 10:\n", 156 | " print line[:100]\n", 157 | " if count == 0:\n", 158 | " break\n" 159 | ], 160 | "language": "python", 161 | "metadata": {}, 162 | "outputs": [ 163 | { 164 | "output_type": "stream", 165 | "stream": "stdout", 166 | "text": [ 167 | "WARC-Record-ID: \r\n", 168 | "\n", 169 | "WARC-Refers-To: \r\n", 170 | "\n", 171 | "Content-Type: application/json\r\n", 172 | "\n", 173 | "Content-Length: 1120\r\n", 174 | "\n", 175 | "{\"Envelope\":{\"Format\":\"WARC\",\"WARC-Header-Length\":\"445\",\"Block-Digest\":\"sha1:VW6RU4CDMZHRI742K45S4SR\n", 176 | "WARC/1.0\r\n", 177 | "\n", 178 | "WARC-Type: metadata\r\n", 179 | "\n", 180 | "WARC-Target-URI: http://0pointer.de/photos/?gallery=Amazon%202010-03&photo=945&exif_style=&show_thum\n", 181 | "WARC-Date: 2013-12-12T23:09:51Z\r\n", 182 | "\n", 183 | "WARC-Record-ID: \r\n", 184 | "\n" 185 | ] 186 | } 187 | ], 188 | "prompt_number": 5 189 | }, 190 | { 191 | "cell_type": "markdown", 192 | "metadata": {}, 193 | "source": [ 194 | "Reading a WET (Text) file from the second crawl in 2013 and printing first 25 lines from it." 195 | ] 196 | }, 197 | { 198 | "cell_type": "code", 199 | "collapsed": false, 200 | "input": [ 201 | "crawl_id = '2013_2'\n", 202 | "example_wet_filename = random.choice(CRAWLS[crawl_id].wet)\n", 203 | "count = 20\n", 204 | "example_wet_fileobject = CRAWLS[crawl_id].get_file(example_wet_filename,headers = {'Range': 'bytes=0-100000'})\n", 205 | "for line in example_wet_fileobject:\n", 206 | " if line.strip():\n", 207 | " count -=1\n", 208 | " print line[:100]\n", 209 | " if count == 0:\n", 210 | " break" 211 | ], 212 | "language": "python", 213 | "metadata": {}, 214 | "outputs": [ 215 | { 216 | "output_type": "stream", 217 | "stream": "stdout", 218 | "text": [ 219 | "WARC/1.0\r\n", 220 | "\n", 221 | "WARC-Type: warcinfo\r\n", 222 | "\n", 223 | "WARC-Date: 2014-01-04T00:18:16Z\r\n", 224 | "\n", 225 | "WARC-Filename: CC-MAIN-20131204134537-00035-ip-10-33-133-15.ec2.internal.warc.wet.gz\r\n", 226 | "\n", 227 | "WARC-Record-ID: \r\n", 228 | "\n", 229 | "Content-Type: application/warc-fields\r\n", 230 | "\n", 231 | "Content-Length: 286\r\n", 232 | "\n", 233 | "Software-Info: ia-web-commons.1.0-SNAPSHOT-20131126084621\r\n", 234 | "\n", 235 | "Extracted-Date: Sat, 04 Jan 2014 00:18:16 GMT\r\n", 236 | "\n", 237 | "robots: classic\r\n", 238 | "\n", 239 | "isPartOf: CC-MAIN-2013-48\r\n", 240 | "\n", 241 | "operator: CommonCrawl Admin\r\n", 242 | "\n", 243 | "description: Wide crawl of the web with URLs provided by Blekko for Winter 2013\r\n", 244 | "\n", 245 | "publisher: CommonCrawl\r\n", 246 | "\n", 247 | "WARC/1.0\r\n", 248 | "\n", 249 | "WARC-Type: conversion\r\n", 250 | "\n", 251 | "WARC-Target-URI: http://02varvara.wordpress.com/2012/12/16/16-december-2012-tomorrow-is-st-barbara-d\n", 252 | "WARC-Date: 2013-12-12T22:14:25Z\r\n", 253 | "\n", 254 | "WARC-Record-ID: \r\n", 255 | "\n", 256 | "WARC-Refers-To: \r\n", 257 | "\n" 258 | ] 259 | } 260 | ], 261 | "prompt_number": 9 262 | }, 263 | { 264 | "cell_type": "heading", 265 | "level": 3, 266 | "metadata": {}, 267 | "source": [ 268 | "Example worker function" 269 | ] 270 | }, 271 | { 272 | "cell_type": "markdown", 273 | "metadata": {}, 274 | "source": [ 275 | "Following is an example of a simple worker function which takes a WAT file and extracts list URLs. Note that this is not part of the library." 276 | ] 277 | }, 278 | { 279 | "cell_type": "code", 280 | "collapsed": false, 281 | "input": [ 282 | "from worker import process_file\n", 283 | "from pprint import pprint\n", 284 | "data = process_file(example_wat_fileobject,example_wat_filename)" 285 | ], 286 | "language": "python", 287 | "metadata": {}, 288 | "outputs": [ 289 | { 290 | "output_type": "stream", 291 | "stream": "stderr", 292 | "text": [ 293 | "ERROR:root:error while processing file\n", 294 | "Traceback (most recent call last):\n", 295 | " File \"worker.py\", line 49, in process_file\n", 296 | " for line in fileobj:\n", 297 | " File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py\", line 450, in readline\n", 298 | " c = self.read(readsize)\n", 299 | " File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py\", line 256, in read\n", 300 | " self._read(readsize)\n", 301 | " File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py\", line 303, in _read\n", 302 | " self._read_eof()\n", 303 | " File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py\", line 342, in _read_eof\n", 304 | " hex(self.crc)))\n", 305 | "IOError: CRC check failed 0xae79b42 != 0xfd137780L\n" 306 | ] 307 | } 308 | ], 309 | "prompt_number": 6 310 | }, 311 | { 312 | "cell_type": "markdown", 313 | "metadata": {}, 314 | "source": [ 315 | "Ignore the error above which is produced due to the fact that only first few thousand bytes were downloaded. " 316 | ] 317 | }, 318 | { 319 | "cell_type": "code", 320 | "collapsed": false, 321 | "input": [ 322 | "pprint(data)" 323 | ], 324 | "language": "python", 325 | "metadata": {}, 326 | "outputs": [ 327 | { 328 | "output_type": "stream", 329 | "stream": "stdout", 330 | "text": [ 331 | "{'amazon': [],\n", 332 | " 'counts': [],\n", 333 | " 'error': True,\n", 334 | " 'filename': 'common-crawl/crawl-data/CC-MAIN-2013-48/segments/1386164746201/wat/CC-MAIN-20131204134546-00047-ip-10-33-133-15.ec2.internal.warc.wat.gz',\n", 335 | " 'metdata_lines': 40}\n" 336 | ] 337 | } 338 | ], 339 | "prompt_number": 7 340 | } 341 | ], 342 | "metadata": {} 343 | } 344 | ] 345 | } -------------------------------------------------------------------------------- /example.json: -------------------------------------------------------------------------------- 1 | {"count": 124657, "filename": "common-crawl/crawl-data/CC-MAIN-2013-48/segments/1386163047523/wat/CC-MAIN-20131204131727-00053-ip-10-33-133-15.ec2.internal.warc.wat.gz", "tumblr": ["http://0uterspaceallstar.tumblr.com/post/10711459413", "http://0uterspaceallstar.tumblr.com/post/10711459413", "http://0uterspaceallstar.tumblr.com/post/10711459413", "http://ab-fab-treasures.tumblr.com/tagged/fruits", "http://ab-fab-treasures.tumblr.com/tagged/fruits", "http://ab-fab-treasures.tumblr.com/tagged/fruits", "http://abbyella.tumblr.com/post/22001200950/eatsleepdraw-abstract-painting-project", "http://abbyella.tumblr.com/post/22001200950/eatsleepdraw-abstract-painting-project", "http://abbyella.tumblr.com/post/22001200950/eatsleepdraw-abstract-painting-project", "http://absolutleeleer.tumblr.com/post/54179732444/myth-1-introverts-dont-like-to-talk-this-is", "http://absolutleeleer.tumblr.com/post/54179732444/myth-1-introverts-dont-like-to-talk-this-is", "http://absolutleeleer.tumblr.com/post/54179732444/myth-1-introverts-dont-like-to-talk-this-is", "http://acid-beach.tumblr.com/post/21423076854", "http://acid-beach.tumblr.com/post/21423076854", "http://acid-beach.tumblr.com/post/21423076854", "http://addictedtoyourtoxiclove.tumblr.com/post/35847510502/modelsjam-abbey-lee-paris-october-2011", "http://addictedtoyourtoxiclove.tumblr.com/post/35847510502/modelsjam-abbey-lee-paris-october-2011", "http://addictedtoyourtoxiclove.tumblr.com/post/35847510502/modelsjam-abbey-lee-paris-october-2011", "http://adrianhickman.tumblr.com/archive/2011/6", "http://adrianhickman.tumblr.com/archive/2011/6", "http://adrianhickman.tumblr.com/archive/2011/6", "http://aizaaat.tumblr.com/post/62788614231", "http://aizaaat.tumblr.com/post/62788614231", "http://aizaaat.tumblr.com/post/62788614231", "http://ali0cha.tumblr.com/archive/2011/6", "http://ali0cha.tumblr.com/archive/2011/6", "http://ali0cha.tumblr.com/archive/2011/6", "http://alittletiger.tumblr.com/post/25788214996", "http://alittletiger.tumblr.com/post/25788214996", "http://alittletiger.tumblr.com/post/25788214996", "http://allisonbamcat.tumblr.com/post/40870478435/hifructosemag-for-her-upcoming-solo-show-in", "http://allisonbamcat.tumblr.com/post/40870478435/hifructosemag-for-her-upcoming-solo-show-in", "http://allisonbamcat.tumblr.com/post/40870478435/hifructosemag-for-her-upcoming-solo-show-in", "http://animalesco.tumblr.com/archive/2010/9", "http://animalesco.tumblr.com/archive/2010/9", "http://animalesco.tumblr.com/archive/2010/9", "http://arcade-fan.tumblr.com/archive/2011/4", "http://arcade-fan.tumblr.com/archive/2011/4", "http://arcade-fan.tumblr.com/archive/2011/4", "http://archiviocaltari.tumblr.com/post/27123887105/angeloricci-quando-bob-guccione-pubblicava", "http://archiviocaltari.tumblr.com/post/27123887105/angeloricci-quando-bob-guccione-pubblicava", "http://archiviocaltari.tumblr.com/post/27123887105/angeloricci-quando-bob-guccione-pubblicava", "http://arkadelphia.tumblr.com/tagged/francoise-hardy", "http://arkadelphia.tumblr.com/tagged/francoise-hardy", "http://arkadelphia.tumblr.com/tagged/francoise-hardy", "http://artpockets.tumblr.com/tagged/creative", "http://artpockets.tumblr.com/tagged/creative", "http://artpockets.tumblr.com/tagged/creative", "http://askboggle.tumblr.com/post/2535281859", "http://askboggle.tumblr.com/post/2535281859", "http://askboggle.tumblr.com/post/2535281859", "http://asongfortheend.tumblr.com/post/41329566830/two-mermaids-ring-with-pearl-by", "http://asongfortheend.tumblr.com/post/41329566830/two-mermaids-ring-with-pearl-by", "http://asongfortheend.tumblr.com/post/41329566830/two-mermaids-ring-with-pearl-by", "http://astonishmagazine.tumblr.com/post/22657745730/jean-paul-gaultier", "http://astonishmagazine.tumblr.com/post/22657745730/jean-paul-gaultier", "http://astonishmagazine.tumblr.com/post/22657745730/jean-paul-gaultier", "http://astroed.tumblr.com/archive/2011/2", "http://astroed.tumblr.com/archive/2011/2", "http://astroed.tumblr.com/archive/2011/2", "http://b-timo.tumblr.com/post/25010438279", "http://b-timo.tumblr.com/post/25010438279", "http://b-timo.tumblr.com/post/25010438279", "http://babyteezy.tumblr.com/post/28252531095", "http://babyteezy.tumblr.com/post/28252531095", "http://babyteezy.tumblr.com/post/28252531095", "http://baraslut.tumblr.com/post/25410915826/sooooooooo-cuuuuuuuuuuuute", "http://baraslut.tumblr.com/post/25410915826/sooooooooo-cuuuuuuuuuuuute", "http://baraslut.tumblr.com/post/25410915826/sooooooooo-cuuuuuuuuuuuute", "http://basalite24.tumblr.com/post/28176559892/mr-bean-and-bond-were-great-branagh-too-of", "http://basalite24.tumblr.com/post/28176559892/mr-bean-and-bond-were-great-branagh-too-of", "http://basalite24.tumblr.com/post/28176559892/mr-bean-and-bond-were-great-branagh-too-of", "http://beaconhillshasthechills.tumblr.com/", "http://beaconhillshasthechills.tumblr.com/", "http://beaconhillshasthechills.tumblr.com/", "http://beautydemons.tumblr.com/post/21725147347", "http://beautydemons.tumblr.com/post/21725147347", "http://beautydemons.tumblr.com/post/21725147347", "http://bebelestrange.tumblr.com/post/35389828181", "http://bebelestrange.tumblr.com/post/35389828181", "http://bebelestrange.tumblr.com/post/35389828181", "http://bentheillustrator.tumblr.com/tagged/article", "http://bentheillustrator.tumblr.com/tagged/article", "http://bentheillustrator.tumblr.com/tagged/article", "http://bikinigals.tumblr.com/post/50113177297/skimpy-bikini", "http://bikinigals.tumblr.com/post/50113177297/skimpy-bikini", "http://bikinigals.tumblr.com/post/50113177297/skimpy-bikini", "http://blogthegoodbike.tumblr.com/post/16579787151/the-good-bike-project-is-going-out-with-a-bang", "http://blogthegoodbike.tumblr.com/post/16579787151/the-good-bike-project-is-going-out-with-a-bang", "http://blogthegoodbike.tumblr.com/post/16579787151/the-good-bike-project-is-going-out-with-a-bang", "http://breathtakinglandscapes.tumblr.com/post/43146636520/the-northern-lights-route-by-the-aurora-zone-on", "http://breathtakinglandscapes.tumblr.com/post/43146636520/the-northern-lights-route-by-the-aurora-zone-on", "http://breathtakinglandscapes.tumblr.com/post/43146636520/the-northern-lights-route-by-the-aurora-zone-on", "http://breeekachu.tumblr.com/post/27456384782/barleytea-o-no", "http://breeekachu.tumblr.com/post/27456384782/barleytea-o-no", "http://breeekachu.tumblr.com/post/27456384782/barleytea-o-no", "http://buubbleteaa.tumblr.com/post/20330583382", "http://buubbleteaa.tumblr.com/post/20330583382", "http://buubbleteaa.tumblr.com/post/20330583382", "http://caixadefotografias.tumblr.com/", "http://caixadefotografias.tumblr.com/", "http://caixadefotografias.tumblr.com/", "http://calldownthethunder.tumblr.com/tagged/japan", "http://calldownthethunder.tumblr.com/tagged/japan", "http://calldownthethunder.tumblr.com/tagged/japan", "http://carlburton.tumblr.com/tagged/path", "http://carlburton.tumblr.com/tagged/path", "http://carlburton.tumblr.com/tagged/path", "http://cati-cole1.tumblr.com/", "http://cati-cole1.tumblr.com/", "http://cati-cole1.tumblr.com/", "http://celesti-ca.tumblr.com/", "http://celesti-ca.tumblr.com/", "http://celesti-ca.tumblr.com/", "http://chirosangaku.tumblr.com/archive/2011/10", "http://chirosangaku.tumblr.com/archive/2011/10", "http://chirosangaku.tumblr.com/archive/2011/10", "http://chloeaftel.tumblr.com/post/33525111694", "http://chloeaftel.tumblr.com/post/33525111694", "http://chloeaftel.tumblr.com/post/33525111694", "http://chocolaterebellion.tumblr.com/rss", "http://chocolaterebellion.tumblr.com/rss", "http://chocolaterebellion.tumblr.com/rss", "http://choes.tumblr.com/post/57646883861/i-spent-a-month-photographing-in-south-side", "http://choes.tumblr.com/post/57646883861/i-spent-a-month-photographing-in-south-side", "http://choes.tumblr.com/post/57646883861/i-spent-a-month-photographing-in-south-side", "http://chrisheads365.tumblr.com/post/35673775259", "http://chrisheads365.tumblr.com/post/35673775259", "http://chrisheads365.tumblr.com/post/35673775259", "http://closetofindingtruth.tumblr.com/tagged/me", "http://closetofindingtruth.tumblr.com/tagged/me", "http://closetofindingtruth.tumblr.com/tagged/me", "http://coastin-thru-life.tumblr.com/", "http://coastin-thru-life.tumblr.com/", "http://coastin-thru-life.tumblr.com/", "http://communicon.tumblr.com/post/36906851997/communicon-teaser", "http://communicon.tumblr.com/post/36906851997/communicon-teaser", "http://communicon.tumblr.com/post/36906851997/communicon-teaser", "http://completelyincomplete.tumblr.com/post/55501706002/shannon-leto-piazzola-sul-brenta-padova", "http://completelyincomplete.tumblr.com/post/55501706002/shannon-leto-piazzola-sul-brenta-padova", "http://completelyincomplete.tumblr.com/post/55501706002/shannon-leto-piazzola-sul-brenta-padova", "http://completepeanuts.tumblr.com/page/3", "http://completepeanuts.tumblr.com/page/3", "http://completepeanuts.tumblr.com/page/3", "http://confrontmag.tumblr.com/post/50210575084/interview-joshua-radin", "http://confrontmag.tumblr.com/post/50210575084/interview-joshua-radin", "http://confrontmag.tumblr.com/post/50210575084/interview-joshua-radin", "http://connecticuthardcore.tumblr.com/post/18750954871/cold-snap-eighties-bc-at-the-wallingford", "http://connecticuthardcore.tumblr.com/post/18750954871/cold-snap-eighties-bc-at-the-wallingford", "http://connecticuthardcore.tumblr.com/post/18750954871/cold-snap-eighties-bc-at-the-wallingford", "http://corbieres.tumblr.com/", "http://corbieres.tumblr.com/", "http://corbieres.tumblr.com/", "http://curnbread.tumblr.com/post/48164730347", "http://curnbread.tumblr.com/post/48164730347", "http://curnbread.tumblr.com/post/48164730347", "http://d0minus.tumblr.com/post/45839206928/g-l-a-m-effspots-gulf-livery-aston-martin", "http://d0minus.tumblr.com/post/45839206928/g-l-a-m-effspots-gulf-livery-aston-martin", "http://d0minus.tumblr.com/post/45839206928/g-l-a-m-effspots-gulf-livery-aston-martin", "http://daddygreenjeans.tumblr.com/post/25535903681", "http://daddygreenjeans.tumblr.com/post/25535903681", "http://daddygreenjeans.tumblr.com/post/25535903681", "http://dancersaretheathletesofgod.tumblr.com/post/15619390728", "http://dancersaretheathletesofgod.tumblr.com/post/15619390728", "http://dancersaretheathletesofgod.tumblr.com/post/15619390728", "http://deannazandt.tumblr.com/post/29142426264/is-he-on-the-island-on-the-lack-of-professional", "http://deannazandt.tumblr.com/post/29142426264/is-he-on-the-island-on-the-lack-of-professional", "http://deannazandt.tumblr.com/post/29142426264/is-he-on-the-island-on-the-lack-of-professional", "http://debbysiswono.tumblr.com/", "http://debbysiswono.tumblr.com/", "http://debbysiswono.tumblr.com/", "http://deereye.tumblr.com/ask", "http://deereye.tumblr.com/ask", "http://deereye.tumblr.com/ask", "http://deiteitespitch.tumblr.com/post/13552609414/actually-well-im-like-a-slowpoke", "http://deiteitespitch.tumblr.com/post/13552609414/actually-well-im-like-a-slowpoke", "http://deiteitespitch.tumblr.com/post/13552609414/actually-well-im-like-a-slowpoke", "http://denamilf.tumblr.com/", "http://denamilf.tumblr.com/", "http://denamilf.tumblr.com/", "http://denomnom.tumblr.com/tagged/ps3", "http://denomnom.tumblr.com/tagged/ps3", "http://denomnom.tumblr.com/tagged/ps3", "http://desinvolture.tumblr.com/post/21919107356/wylie-hays-by-claire-thomas-for-luv-aj", "http://desinvolture.tumblr.com/post/21919107356/wylie-hays-by-claire-thomas-for-luv-aj", "http://desinvolture.tumblr.com/post/21919107356/wylie-hays-by-claire-thomas-for-luv-aj", "http://deztini.tumblr.com/post/17597194852/collegehumor-today-in-awesome-internet-finds", "http://deztini.tumblr.com/post/17597194852/collegehumor-today-in-awesome-internet-finds", "http://deztini.tumblr.com/post/17597194852/collegehumor-today-in-awesome-internet-finds", "http://dianaparkhouse.tumblr.com/tagged/cartoon", "http://dianaparkhouse.tumblr.com/tagged/cartoon", "http://dianaparkhouse.tumblr.com/tagged/cartoon", "http://doctorwho.tumblr.com/post/4988296638/the-prequel-to-the-impossible-astronaut", "http://doctorwho.tumblr.com/post/4988296638/the-prequel-to-the-impossible-astronaut", "http://doctorwho.tumblr.com/post/4988296638/the-prequel-to-the-impossible-astronaut", "http://dou-glas.tumblr.com/post/22591351672", "http://dou-glas.tumblr.com/post/22591351672", "http://dou-glas.tumblr.com/post/22591351672", "http://dreadpics.tumblr.com/tagged/hippie/page/2", "http://dreadpics.tumblr.com/tagged/hippie/page/2", "http://dreadpics.tumblr.com/tagged/hippie/page/2", "http://edenoflove.tumblr.com/post/46530174940/adela-and-tessie-jumpers-on-we-heart-it", "http://edenoflove.tumblr.com/post/46530174940/adela-and-tessie-jumpers-on-we-heart-it", "http://edenoflove.tumblr.com/post/46530174940/adela-and-tessie-jumpers-on-we-heart-it", "http://eliiizza.tumblr.com/post/27490968018", "http://eliiizza.tumblr.com/post/27490968018", "http://eliiizza.tumblr.com/post/27490968018", "http://elmattcorrigan.tumblr.com/post/49841830426", "http://elmattcorrigan.tumblr.com/post/49841830426", "http://elmattcorrigan.tumblr.com/post/49841830426", "http://emilyforafriend.tumblr.com/", "http://emilyforafriend.tumblr.com/", "http://emilyforafriend.tumblr.com/", "http://empatheticvegan.tumblr.com/post/35796832523/i-got-to-make-a-sweet-sign-for-work", "http://empatheticvegan.tumblr.com/post/35796832523/i-got-to-make-a-sweet-sign-for-work", "http://empatheticvegan.tumblr.com/post/35796832523/i-got-to-make-a-sweet-sign-for-work", "http://enchanting-world.tumblr.com/", "http://enchanting-world.tumblr.com/", "http://enchanting-world.tumblr.com/", "http://epic-steve.tumblr.com/post/9554042292/lmao", "http://epic-steve.tumblr.com/post/9554042292/lmao", "http://epic-steve.tumblr.com/post/9554042292/lmao", "http://erikjmac.tumblr.com/post/37132714791", "http://erikjmac.tumblr.com/post/37132714791", "http://erikjmac.tumblr.com/post/37132714791", "http://eurovisiontime.tumblr.com/rss", "http://eurovisiontime.tumblr.com/rss", "http://eurovisiontime.tumblr.com/rss", "http://evaporated-jellyfish.tumblr.com/", "http://evaporated-jellyfish.tumblr.com/", "http://evaporated-jellyfish.tumblr.com/", "http://everything-groovy.tumblr.com/", "http://everything-groovy.tumblr.com/", "http://everything-groovy.tumblr.com/", "http://familyfugue.tumblr.com/", "http://familyfugue.tumblr.com/", "http://familyfugue.tumblr.com/", "http://federalaudio-blog.tumblr.com/post/23385460436/heres-the-audio-technology-review-of-the-adam", "http://federalaudio-blog.tumblr.com/post/23385460436/heres-the-audio-technology-review-of-the-adam", "http://federalaudio-blog.tumblr.com/post/23385460436/heres-the-audio-technology-review-of-the-adam", "http://feedthembitches.tumblr.com/post/52765450054", "http://feedthembitches.tumblr.com/post/52765450054", "http://feedthembitches.tumblr.com/post/52765450054", "http://fireinfreetown.tumblr.com/tagged/African-designs", "http://fireinfreetown.tumblr.com/tagged/African-designs", "http://fireinfreetown.tumblr.com/tagged/African-designs", "http://fivecentimeterspersecond.tumblr.com/post/12260006215/come-to-fairy-tail", "http://fivecentimeterspersecond.tumblr.com/post/12260006215/come-to-fairy-tail", "http://fivecentimeterspersecond.tumblr.com/post/12260006215/come-to-fairy-tail", "http://flashbazinga.tumblr.com/post/39924252885", "http://flashbazinga.tumblr.com/post/39924252885", "http://flashbazinga.tumblr.com/post/39924252885", "http://fruit-porn.tumblr.com/post/60092648445/grapes-and-more-fruits", "http://fruit-porn.tumblr.com/post/60092648445/grapes-and-more-fruits", "http://fruit-porn.tumblr.com/post/60092648445/grapes-and-more-fruits", "http://fuckyeahelectraheart.tumblr.com/post/31482643675", "http://fuckyeahelectraheart.tumblr.com/post/31482643675", "http://fuckyeahelectraheart.tumblr.com/post/31482643675", "http://fuckyeahnozuka.tumblr.com/post/40059988952", "http://fuckyeahnozuka.tumblr.com/post/40059988952", "http://fuckyeahnozuka.tumblr.com/post/40059988952", "http://fuckyeahwearehungry.tumblr.com/post/34021201366", "http://fuckyeahwearehungry.tumblr.com/post/34021201366", "http://fuckyeahwearehungry.tumblr.com/post/34021201366", "http://fukyourprettyface.tumblr.com/post/29727081863", "http://fukyourprettyface.tumblr.com/post/29727081863", "http://fukyourprettyface.tumblr.com/post/29727081863", "http://funinthesunvballextravaganza.tumblr.com/", "http://funinthesunvballextravaganza.tumblr.com/", "http://funinthesunvballextravaganza.tumblr.com/", "http://funkitude.tumblr.com/tagged/new-zealand", "http://funkitude.tumblr.com/tagged/new-zealand", "http://funkitude.tumblr.com/tagged/new-zealand", "http://fweecarter.tumblr.com/post/52501202593/get-spittin", "http://fweecarter.tumblr.com/post/52501202593/get-spittin", "http://fweecarter.tumblr.com/post/52501202593/get-spittin", "http://ganond.tumblr.com/tagged/toyota", "http://ganond.tumblr.com/tagged/toyota", "http://ganond.tumblr.com/tagged/toyota", "http://geezeus.tumblr.com/post/15988251044", "http://geezeus.tumblr.com/post/15988251044", "http://geezeus.tumblr.com/post/15988251044", "http://getfitorgohome.tumblr.com/post/31255256047", "http://getfitorgohome.tumblr.com/post/31255256047", "http://getfitorgohome.tumblr.com/post/31255256047", "http://gifs-a-plenty.tumblr.com/post/38217374859", "http://gifs-a-plenty.tumblr.com/post/38217374859", "http://gifs-a-plenty.tumblr.com/post/38217374859", "http://gifsongifs4life.tumblr.com/post/32647475400/click-to-control-gif-http-gifctrl-com-zh", "http://gifsongifs4life.tumblr.com/post/32647475400/click-to-control-gif-http-gifctrl-com-zh", "http://gifsongifs4life.tumblr.com/post/32647475400/click-to-control-gif-http-gifctrl-com-zh", "http://go.tumblr.com/archive/2010/7?before_time=1278954144", "http://go.tumblr.com/archive/2010/7?before_time=1278954144", "http://go.tumblr.com/archive/2010/7?before_time=1278954144", "http://goldenbettywhite.tumblr.com/post/34448639294/betty-white-at-age-fourteen-in-her-beverly-hills", "http://goldenbettywhite.tumblr.com/post/34448639294/betty-white-at-age-fourteen-in-her-beverly-hills", "http://goldenbettywhite.tumblr.com/post/34448639294/betty-white-at-age-fourteen-in-her-beverly-hills", "http://gozurigo.tumblr.com/", "http://gozurigo.tumblr.com/", "http://gozurigo.tumblr.com/", "http://haepol.tumblr.com/ask", "http://haepol.tumblr.com/ask", "http://haepol.tumblr.com/ask", "http://happy-lollipop.tumblr.com/post/37198875087/who-is-your-favourite-little-character-from-all-the", "http://happy-lollipop.tumblr.com/post/37198875087/who-is-your-favourite-little-character-from-all-the", "http://happy-lollipop.tumblr.com/post/37198875087/who-is-your-favourite-little-character-from-all-the", "http://heartbeatoz.tumblr.com/post/19174726991/via-this-is-glamorous-adventures-in-love", "http://heartbeatoz.tumblr.com/post/19174726991/via-this-is-glamorous-adventures-in-love", "http://heartbeatoz.tumblr.com/post/19174726991/via-this-is-glamorous-adventures-in-love", "http://heaven-onlyknows.tumblr.com/", "http://heaven-onlyknows.tumblr.com/", "http://heaven-onlyknows.tumblr.com/", "http://hegemony77.tumblr.com/tagged/doll-dress", "http://hegemony77.tumblr.com/tagged/doll-dress", "http://hegemony77.tumblr.com/tagged/doll-dress", "http://hellbilly-deluxe.tumblr.com/post/24997953073", "http://hellbilly-deluxe.tumblr.com/post/24997953073", "http://hellbilly-deluxe.tumblr.com/post/24997953073", "http://honestly-wtf.tumblr.com/post/5803084818", "http://honestly-wtf.tumblr.com/post/5803084818", "http://honestly-wtf.tumblr.com/post/5803084818", "http://horaciohamlet.tumblr.com/post/39952038403/blacque-ink-lobaton-twins-click-models", "http://horaciohamlet.tumblr.com/post/39952038403/blacque-ink-lobaton-twins-click-models", "http://horaciohamlet.tumblr.com/post/39952038403/blacque-ink-lobaton-twins-click-models", "http://horrorbiz.tumblr.com/post/12334569362", "http://horrorbiz.tumblr.com/post/12334569362", "http://horrorbiz.tumblr.com/post/12334569362", "http://hotphotography.tumblr.com/post/43733274045/http-nextdoormodel-tumblr-com", "http://hotphotography.tumblr.com/post/43733274045/http-nextdoormodel-tumblr-com", "http://hotphotography.tumblr.com/post/43733274045/http-nextdoormodel-tumblr-com", "http://hsanders.tumblr.com/tagged/great-blog-or-greatest-blog", "http://hsanders.tumblr.com/tagged/great-blog-or-greatest-blog", "http://hsanders.tumblr.com/tagged/great-blog-or-greatest-blog", "http://hugsandbuds.tumblr.com/", "http://hugsandbuds.tumblr.com/", "http://hugsandbuds.tumblr.com/", "http://huskernsider.tumblr.com/post/36164579395/presenter-can-identify-with-nebraskas-hero?ATCLID=2731&SPID=76795&DB_LANG=C&DB_OEM_ID=100", "http://huskernsider.tumblr.com/post/36164579395/presenter-can-identify-with-nebraskas-hero?ATCLID=2731&SPID=76795&DB_LANG=C&DB_OEM_ID=100", "http://huskernsider.tumblr.com/post/36164579395/presenter-can-identify-with-nebraskas-hero?ATCLID=2731&SPID=76795&DB_LANG=C&DB_OEM_ID=100", "http://hyperwalrusvsdesklamp.tumblr.com/", "http://hyperwalrusvsdesklamp.tumblr.com/", "http://hyperwalrusvsdesklamp.tumblr.com/", "http://illiara.tumblr.com/", "http://illiara.tumblr.com/", "http://illiara.tumblr.com/", "http://ilovetvmen.tumblr.com/post/16447477008/rob-riggle-2", "http://ilovetvmen.tumblr.com/post/16447477008/rob-riggle-2", "http://ilovetvmen.tumblr.com/post/16447477008/rob-riggle-2", "http://isthespiceoflife.tumblr.com/post/20613466271/music-is-the-spice-of-life-seed-the-black", "http://isthespiceoflife.tumblr.com/post/20613466271/music-is-the-spice-of-life-seed-the-black", "http://isthespiceoflife.tumblr.com/post/20613466271/music-is-the-spice-of-life-seed-the-black", "http://its-lynnze-not-lindsey.tumblr.com/", "http://its-lynnze-not-lindsey.tumblr.com/", "http://its-lynnze-not-lindsey.tumblr.com/", "http://itsjustgab.tumblr.com/post/36288797443/finally-the-long-awaited-movie-rise-of-the", "http://itsjustgab.tumblr.com/post/36288797443/finally-the-long-awaited-movie-rise-of-the", "http://itsjustgab.tumblr.com/post/36288797443/finally-the-long-awaited-movie-rise-of-the", "http://itsmania.tumblr.com/", "http://itsmania.tumblr.com/", "http://itsmania.tumblr.com/", "http://ivahc.tumblr.com/ask", "http://ivahc.tumblr.com/ask", "http://ivahc.tumblr.com/ask", "http://jackie-bush.tumblr.com/post/29234757662", "http://jackie-bush.tumblr.com/post/29234757662", "http://jackie-bush.tumblr.com/post/29234757662", "http://japanesefashionlovers.tumblr.com/post/51309686962", "http://japanesefashionlovers.tumblr.com/post/51309686962", "http://japanesefashionlovers.tumblr.com/post/51309686962", "http://jenmyers.tumblr.com/tagged/towels", "http://jenmyers.tumblr.com/tagged/towels", "http://jenmyers.tumblr.com/tagged/towels", "http://jessersmessers.tumblr.com/post/23016633942/da-fuq", "http://jessersmessers.tumblr.com/post/23016633942/da-fuq", "http://jessersmessers.tumblr.com/post/23016633942/da-fuq", "http://jesseyoucanhavemywife.tumblr.com/submit", "http://jesseyoucanhavemywife.tumblr.com/submit", "http://jesseyoucanhavemywife.tumblr.com/submit", "http://jonconnington.tumblr.com/tagged/Fantastic-Mr.-Fox", "http://jonconnington.tumblr.com/tagged/Fantastic-Mr.-Fox", "http://jonconnington.tumblr.com/tagged/Fantastic-Mr.-Fox", "http://joseph-schlichting.tumblr.com/post/21302567902", "http://joseph-schlichting.tumblr.com/post/21302567902", "http://joseph-schlichting.tumblr.com/post/21302567902", "http://jothelibrarian.tumblr.com/post/36517562422/pretty-medieval-manuscript-of-the-day-is-not", "http://jothelibrarian.tumblr.com/post/36517562422/pretty-medieval-manuscript-of-the-day-is-not", "http://jothelibrarian.tumblr.com/post/36517562422/pretty-medieval-manuscript-of-the-day-is-not", "http://jundennis.tumblr.com/archive/2011/2", "http://jundennis.tumblr.com/archive/2011/2", "http://jundennis.tumblr.com/archive/2011/2", "http://katiescountdown.tumblr.com/", "http://katiescountdown.tumblr.com/", "http://katiescountdown.tumblr.com/", "http://kayethepterodactyl.tumblr.com/post/47954321545", "http://kayethepterodactyl.tumblr.com/post/47954321545", "http://kayethepterodactyl.tumblr.com/post/47954321545", "http://kayseeboiii.tumblr.com/post/30508585214", "http://kayseeboiii.tumblr.com/post/30508585214", "http://kayseeboiii.tumblr.com/post/30508585214", "http://kellylogan.tumblr.com/post/54999524912/made-a-new-backpack-out-of-an-old-alossforwords", "http://kellylogan.tumblr.com/post/54999524912/made-a-new-backpack-out-of-an-old-alossforwords", "http://kellylogan.tumblr.com/post/54999524912/made-a-new-backpack-out-of-an-old-alossforwords", "http://kirinoxd.tumblr.com/", "http://kirinoxd.tumblr.com/", "http://kirinoxd.tumblr.com/", "http://knifey-moloko.tumblr.com/post/22429983141/jthm-by-circusjirkus", "http://knifey-moloko.tumblr.com/post/22429983141/jthm-by-circusjirkus", "http://knifey-moloko.tumblr.com/post/22429983141/jthm-by-circusjirkus", "http://kristypooh.tumblr.com/tagged/ifuckinglovemydogs", "http://kristypooh.tumblr.com/tagged/ifuckinglovemydogs", "http://kristypooh.tumblr.com/tagged/ifuckinglovemydogs", "http://ksjaymes.tumblr.com/post/22301372277", "http://ksjaymes.tumblr.com/post/22301372277", "http://ksjaymes.tumblr.com/post/22301372277", "http://l-ettie.tumblr.com/post/55360362863", "http://l-ettie.tumblr.com/post/55360362863", "http://l-ettie.tumblr.com/post/55360362863", "http://ladeedarr.tumblr.com/", "http://ladeedarr.tumblr.com/", "http://ladeedarr.tumblr.com/", "http://lapaluxmusic.tumblr.com/post/38863309603/lapalux-quartz", "http://lapaluxmusic.tumblr.com/post/38863309603/lapalux-quartz", "http://lapaluxmusic.tumblr.com/post/38863309603/lapalux-quartz", "http://largevocabulary.tumblr.com/post/13722066005", "http://largevocabulary.tumblr.com/post/13722066005", "http://largevocabulary.tumblr.com/post/13722066005", "http://latenightsurf.tumblr.com/", "http://latenightsurf.tumblr.com/", "http://latenightsurf.tumblr.com/", "http://leaderofpenguins.tumblr.com/post/61421529518/when-voting-penguins-do-it-together", "http://leaderofpenguins.tumblr.com/post/61421529518/when-voting-penguins-do-it-together", "http://leaderofpenguins.tumblr.com/post/61421529518/when-voting-penguins-do-it-together", "http://leajb.tumblr.com/", "http://leajb.tumblr.com/", "http://leajb.tumblr.com/", "http://legarcondetoronto.tumblr.com/post/32459767662/ozwald-boateng-fall-winter", "http://legarcondetoronto.tumblr.com/post/32459767662/ozwald-boateng-fall-winter", "http://legarcondetoronto.tumblr.com/post/32459767662/ozwald-boateng-fall-winter", "http://lgbt-equality-for-everyone.tumblr.com/post/60322509489/gay-rights-are-human-rights-there-its-no", "http://lgbt-equality-for-everyone.tumblr.com/post/60322509489/gay-rights-are-human-rights-there-its-no", "http://lgbt-equality-for-everyone.tumblr.com/post/60322509489/gay-rights-are-human-rights-there-its-no", "http://lietometonight.tumblr.com/post/44063848642/rdj-wants-to-haunt-you", "http://lietometonight.tumblr.com/post/44063848642/rdj-wants-to-haunt-you", "http://lietometonight.tumblr.com/post/44063848642/rdj-wants-to-haunt-you", "http://lifeyaya.tumblr.com/post/26814107390", "http://lifeyaya.tumblr.com/post/26814107390", "http://lifeyaya.tumblr.com/post/26814107390", "http://lovechris2-omg.tumblr.com/post/13919630848/cute-chris-colfer", "http://lovechris2-omg.tumblr.com/post/13919630848/cute-chris-colfer", "http://lovechris2-omg.tumblr.com/post/13919630848/cute-chris-colfer", "http://lovelermaniac.tumblr.com/post/19895865127", "http://lovelermaniac.tumblr.com/post/19895865127", "http://lovelermaniac.tumblr.com/post/19895865127", "http://loveyourchaos.tumblr.com/post/30435458394", "http://loveyourchaos.tumblr.com/post/30435458394", "http://loveyourchaos.tumblr.com/post/30435458394", "http://m00ntheory.tumblr.com/post/27424109858/whoizmichael-jeanet-le-on-flickr", "http://m00ntheory.tumblr.com/post/27424109858/whoizmichael-jeanet-le-on-flickr", "http://m00ntheory.tumblr.com/post/27424109858/whoizmichael-jeanet-le-on-flickr", "http://maarzipan.tumblr.com/post/28701638436", "http://maarzipan.tumblr.com/post/28701638436", "http://maarzipan.tumblr.com/post/28701638436", "http://magicalnaturetour.tumblr.com/post/54063447595", "http://magicalnaturetour.tumblr.com/post/54063447595", "http://magicalnaturetour.tumblr.com/post/54063447595", "http://maid-en-china.tumblr.com/post/53527473424", "http://maid-en-china.tumblr.com/post/53527473424", "http://maid-en-china.tumblr.com/post/53527473424", "http://makingupforlostime.tumblr.com/", "http://makingupforlostime.tumblr.com/", "http://makingupforlostime.tumblr.com/", "http://marikapaprika.tumblr.com/post/17696535032/well-so-heres-the-final-piece-i-did-for-my", "http://marikapaprika.tumblr.com/post/17696535032/well-so-heres-the-final-piece-i-did-for-my", "http://marikapaprika.tumblr.com/post/17696535032/well-so-heres-the-final-piece-i-did-for-my", "http://mcgarrygirl78.tumblr.com/post/38980993514", "http://mcgarrygirl78.tumblr.com/post/38980993514", "http://mcgarrygirl78.tumblr.com/post/38980993514", "http://mebeingsocial.tumblr.com/post/57373576398/person-409k-by-matt-vaillette-buy-website", "http://mebeingsocial.tumblr.com/post/57373576398/person-409k-by-matt-vaillette-buy-website", "http://mebeingsocial.tumblr.com/post/57373576398/person-409k-by-matt-vaillette-buy-website", "http://melissaellish.tumblr.com/post/21873552854", "http://melissaellish.tumblr.com/post/21873552854", "http://melissaellish.tumblr.com/post/21873552854", "http://memereve.tumblr.com/post/39713318707/tamara-lichtenstein", "http://memereve.tumblr.com/post/39713318707/tamara-lichtenstein", "http://memereve.tumblr.com/post/39713318707/tamara-lichtenstein", "http://memoriesandidols.tumblr.com/post/54778010510", "http://memoriesandidols.tumblr.com/post/54778010510", "http://memoriesandidols.tumblr.com/post/54778010510", "http://merixcil.tumblr.com/post/40639089999/insert-meaningful-title-here-by-catastrophilia", "http://merixcil.tumblr.com/post/40639089999/insert-meaningful-title-here-by-catastrophilia", "http://merixcil.tumblr.com/post/40639089999/insert-meaningful-title-here-by-catastrophilia", "http://mietteshoppe.tumblr.com/post/23690127477", "http://mietteshoppe.tumblr.com/post/23690127477", "http://mietteshoppe.tumblr.com/post/23690127477", "http://mina-drommar.tumblr.com/tagged/Photography", "http://mina-drommar.tumblr.com/tagged/Photography", "http://mina-drommar.tumblr.com/tagged/Photography", "http://missclassyass.tumblr.com/", "http://missclassyass.tumblr.com/", "http://missclassyass.tumblr.com/", "http://missmeyet92.tumblr.com/tagged/texts", "http://missmeyet92.tumblr.com/tagged/texts", "http://missmeyet92.tumblr.com/tagged/texts", "http://morillas.tumblr.com/archive/2012/6", "http://morillas.tumblr.com/archive/2012/6", "http://morillas.tumblr.com/archive/2012/6", "http://moussaillon.tumblr.com/post/55252312811/untitled-by-monica-forss-on-flickr", "http://moussaillon.tumblr.com/post/55252312811/untitled-by-monica-forss-on-flickr", "http://moussaillon.tumblr.com/post/55252312811/untitled-by-monica-forss-on-flickr", "http://mreeoo.tumblr.com/post/26145763310/my-lil-brother-n-sister", "http://mreeoo.tumblr.com/post/26145763310/my-lil-brother-n-sister", "http://mreeoo.tumblr.com/post/26145763310/my-lil-brother-n-sister", "http://musicinthemiddle.tumblr.com/post/52399039526", "http://musicinthemiddle.tumblr.com/post/52399039526", "http://musicinthemiddle.tumblr.com/post/52399039526", "http://musketusa.tumblr.com/post/9726793768/art-and-science", "http://musketusa.tumblr.com/post/9726793768/art-and-science", "http://musketusa.tumblr.com/post/9726793768/art-and-science", "http://n0-3ll3.tumblr.com/post/27298496386", "http://n0-3ll3.tumblr.com/post/27298496386", "http://n0-3ll3.tumblr.com/post/27298496386", "http://nancyohh.tumblr.com/", "http://nancyohh.tumblr.com/", "http://nancyohh.tumblr.com/", "http://naznails.tumblr.com/", "http://naznails.tumblr.com/", "http://naznails.tumblr.com/", "http://needtherapy.tumblr.com/post/37740344632/nessfraserloves-blurryoutoffocus-60-moments", "http://needtherapy.tumblr.com/post/37740344632/nessfraserloves-blurryoutoffocus-60-moments", "http://needtherapy.tumblr.com/post/37740344632/nessfraserloves-blurryoutoffocus-60-moments", "http://nickbottom.tumblr.com/post/39131535496", "http://nickbottom.tumblr.com/post/39131535496", "http://nickbottom.tumblr.com/post/39131535496", "http://niclafubuki.tumblr.com/post/15693887226/patty-story-of-my-life", "http://niclafubuki.tumblr.com/post/15693887226/patty-story-of-my-life", "http://niclafubuki.tumblr.com/post/15693887226/patty-story-of-my-life", "http://non-volerli-vittime.tumblr.com/post/37816277911/the-we-survived-the-tumblr-12-12-12-apocalypse", "http://non-volerli-vittime.tumblr.com/post/37816277911/the-we-survived-the-tumblr-12-12-12-apocalypse", "http://non-volerli-vittime.tumblr.com/post/37816277911/the-we-survived-the-tumblr-12-12-12-apocalypse", "http://northtowardhome.tumblr.com/post/12639264890/brooke-astors-holly-hill-in-briarcliff-manor", "http://northtowardhome.tumblr.com/post/12639264890/brooke-astors-holly-hill-in-briarcliff-manor", "http://northtowardhome.tumblr.com/post/12639264890/brooke-astors-holly-hill-in-briarcliff-manor", "http://nudebeat.tumblr.com/post/60544288737/abeardedboy-more-hotel-washroom-fun-thanks", "http://nudebeat.tumblr.com/post/60544288737/abeardedboy-more-hotel-washroom-fun-thanks", "http://nudebeat.tumblr.com/post/60544288737/abeardedboy-more-hotel-washroom-fun-thanks", "http://oestranhomundodek.tumblr.com/post/26030461495/pokemon-johto-journeys-check-out-my-other-poke", "http://oestranhomundodek.tumblr.com/post/26030461495/pokemon-johto-journeys-check-out-my-other-poke", "http://oestranhomundodek.tumblr.com/post/26030461495/pokemon-johto-journeys-check-out-my-other-poke", "http://ogaothin.tumblr.com/post/28353243639", "http://ogaothin.tumblr.com/post/28353243639", "http://ogaothin.tumblr.com/post/28353243639", "http://ohh-laurenconrad.tumblr.com/post/25644201201/allure-photoshoot-2012", "http://ohh-laurenconrad.tumblr.com/post/25644201201/allure-photoshoot-2012", "http://ohh-laurenconrad.tumblr.com/post/25644201201/allure-photoshoot-2012", "http://ohmyy-whatamarveloustune.tumblr.com/", "http://ohmyy-whatamarveloustune.tumblr.com/", "http://ohmyy-whatamarveloustune.tumblr.com/", "http://onenonlytita.tumblr.com/", "http://onenonlytita.tumblr.com/", "http://onenonlytita.tumblr.com/", "http://only-good-stuff.tumblr.com/post/19362581618", "http://only-good-stuff.tumblr.com/post/19362581618", "http://only-good-stuff.tumblr.com/post/19362581618", "http://ourlittleterraqueousglobe.tumblr.com/post/28785503380/scott-hazard", "http://ourlittleterraqueousglobe.tumblr.com/post/28785503380/scott-hazard", "http://ourlittleterraqueousglobe.tumblr.com/post/28785503380/scott-hazard", "http://overdresstoimpress.tumblr.com/post/25339845414", "http://overdresstoimpress.tumblr.com/post/25339845414", "http://overdresstoimpress.tumblr.com/post/25339845414", "http://packetimpend.tumblr.com/tagged/brands", "http://packetimpend.tumblr.com/tagged/brands", "http://packetimpend.tumblr.com/tagged/brands", "http://partyelite.tumblr.com/post/5524133856", "http://partyelite.tumblr.com/post/5524133856", "http://partyelite.tumblr.com/post/5524133856", "http://pastryface.tumblr.com/", "http://pastryface.tumblr.com/", "http://pastryface.tumblr.com/", "http://peasantsinapod.tumblr.com/post/60599100153", "http://peasantsinapod.tumblr.com/post/60599100153", "http://peasantsinapod.tumblr.com/post/60599100153", "http://pequenasdosesdeamor.tumblr.com/post/28668378890", "http://pequenasdosesdeamor.tumblr.com/post/28668378890", "http://pequenasdosesdeamor.tumblr.com/post/28668378890", "http://phocks.tumblr.com/post/31514637874", "http://phocks.tumblr.com/post/31514637874", "http://phocks.tumblr.com/post/31514637874", "http://pierce-sama.tumblr.com/post/24665737588/tarscan-sorry-for-the-late-release-memorial", "http://pierce-sama.tumblr.com/post/24665737588/tarscan-sorry-for-the-late-release-memorial", "http://pierce-sama.tumblr.com/post/24665737588/tarscan-sorry-for-the-late-release-memorial", "http://pleoros.tumblr.com/post/54611969488/tom-pfeiffer-eruption-of-anak-krakatau-volcano", "http://pleoros.tumblr.com/post/54611969488/tom-pfeiffer-eruption-of-anak-krakatau-volcano", "http://pleoros.tumblr.com/post/54611969488/tom-pfeiffer-eruption-of-anak-krakatau-volcano", "http://pmsgrrrl.tumblr.com/post/28186523974/tumblr-crushes-bratlyf-touchmybuttplz", "http://pmsgrrrl.tumblr.com/post/28186523974/tumblr-crushes-bratlyf-touchmybuttplz", "http://pmsgrrrl.tumblr.com/post/28186523974/tumblr-crushes-bratlyf-touchmybuttplz", "http://poppyleeandjackie.tumblr.com/", "http://poppyleeandjackie.tumblr.com/", "http://poppyleeandjackie.tumblr.com/", "http://popwiki.tumblr.com/post/55592854828/poptropica-funbrain-game", "http://popwiki.tumblr.com/post/55592854828/poptropica-funbrain-game", "http://popwiki.tumblr.com/post/55592854828/poptropica-funbrain-game", "http://pottiiino.tumblr.com/post/44069815840/yellowflowers-spring", "http://pottiiino.tumblr.com/post/44069815840/yellowflowers-spring", "http://pottiiino.tumblr.com/post/44069815840/yellowflowers-spring", "http://preppystyle.tumblr.com/page/5", "http://preppystyle.tumblr.com/page/5", "http://preppystyle.tumblr.com/page/5", "http://probablysomethingepic.tumblr.com/", "http://probablysomethingepic.tumblr.com/", "http://probablysomethingepic.tumblr.com/", "http://psychojello.tumblr.com/post/44708809504/hot-david-gilmour-in-da-house", "http://psychojello.tumblr.com/post/44708809504/hot-david-gilmour-in-da-house", "http://psychojello.tumblr.com/post/44708809504/hot-david-gilmour-in-da-house", "http://r-evelry.tumblr.com/post/22285493464", "http://r-evelry.tumblr.com/post/22285493464", "http://r-evelry.tumblr.com/post/22285493464", "http://rabbitpeter.tumblr.com/tagged/Religion", "http://rabbitpeter.tumblr.com/tagged/Religion", "http://rabbitpeter.tumblr.com/tagged/Religion", "http://rabbitsong.tumblr.com/post/27043954525", "http://rabbitsong.tumblr.com/post/27043954525", "http://rabbitsong.tumblr.com/post/27043954525", "http://randomitus.tumblr.com/post/35762467024/tamsinjohnson-art-deco-writing-desk", "http://randomitus.tumblr.com/post/35762467024/tamsinjohnson-art-deco-writing-desk", "http://randomitus.tumblr.com/post/35762467024/tamsinjohnson-art-deco-writing-desk", "http://regushispano.tumblr.com/tagged/Monica-Cerda", "http://regushispano.tumblr.com/tagged/Monica-Cerda", "http://regushispano.tumblr.com/tagged/Monica-Cerda", "http://reinohueco.tumblr.com/post/24261772075/zatanna-6-zees-delusion-conjured-up-some", "http://reinohueco.tumblr.com/post/24261772075/zatanna-6-zees-delusion-conjured-up-some", "http://reinohueco.tumblr.com/post/24261772075/zatanna-6-zees-delusion-conjured-up-some", "http://rika-on.tumblr.com/post/45529033713", "http://rika-on.tumblr.com/post/45529033713", "http://rika-on.tumblr.com/post/45529033713", "http://rin-ne.tumblr.com/post/25713428103/microwalrus-sakurako22-photo", "http://rin-ne.tumblr.com/post/25713428103/microwalrus-sakurako22-photo", "http://rin-ne.tumblr.com/post/25713428103/microwalrus-sakurako22-photo", "http://roomfullofstyle.tumblr.com/tagged/fashion-blog", "http://roomfullofstyle.tumblr.com/tagged/fashion-blog", "http://roomfullofstyle.tumblr.com/tagged/fashion-blog", "http://rosetylear.tumblr.com/post/45196597695/all-of-rorys-deaths-requested-by-tennantbooty", "http://rosetylear.tumblr.com/post/45196597695/all-of-rorys-deaths-requested-by-tennantbooty", "http://rosetylear.tumblr.com/post/45196597695/all-of-rorys-deaths-requested-by-tennantbooty", "http://rottentomato31.tumblr.com/", "http://rottentomato31.tumblr.com/", "http://rottentomato31.tumblr.com/", "http://rubber-bullets.tumblr.com/post/10526433601", "http://rubber-bullets.tumblr.com/post/10526433601", "http://rubber-bullets.tumblr.com/post/10526433601", "http://rude-notginger.tumblr.com/", "http://rude-notginger.tumblr.com/", "http://rude-notginger.tumblr.com/", "http://sant-britt.tumblr.com/tagged/glee", "http://sant-britt.tumblr.com/tagged/glee", "http://sant-britt.tumblr.com/tagged/glee", "http://sebastianfolk.tumblr.com/", "http://sebastianfolk.tumblr.com/", "http://sebastianfolk.tumblr.com/", "http://seejackwrite.tumblr.com/post/26844390598/lucks-just-a-combination-of-destiny-and-desire", "http://seejackwrite.tumblr.com/post/26844390598/lucks-just-a-combination-of-destiny-and-desire", "http://seejackwrite.tumblr.com/post/26844390598/lucks-just-a-combination-of-destiny-and-desire", "http://selenadaily.tumblr.com/post/57125056887", "http://selenadaily.tumblr.com/post/57125056887", "http://selenadaily.tumblr.com/post/57125056887", "http://sen-sitvebitch.tumblr.com/post/20719732958", "http://sen-sitvebitch.tumblr.com/post/20719732958", "http://sen-sitvebitch.tumblr.com/post/20719732958", "http://sensualpegging.tumblr.com/post/12778512518", "http://sensualpegging.tumblr.com/post/12778512518", "http://sensualpegging.tumblr.com/post/12778512518", "http://shemale-ladyboy.tumblr.com/tagged/Interracial/page/2", "http://shemale-ladyboy.tumblr.com/tagged/Interracial/page/2", "http://shemale-ladyboy.tumblr.com/tagged/Interracial/page/2", "http://shysailor.tumblr.com/post/26235879188", "http://shysailor.tumblr.com/post/26235879188", "http://shysailor.tumblr.com/post/26235879188", "http://skinthesun.tumblr.com/post/22009024794", "http://skinthesun.tumblr.com/post/22009024794", "http://skinthesun.tumblr.com/post/22009024794", "http://skwarka.tumblr.com/post/10078005918/ronnie-peterson-14-02-1944-11-09-1978-super", "http://skwarka.tumblr.com/post/10078005918/ronnie-peterson-14-02-1944-11-09-1978-super", "http://skwarka.tumblr.com/post/10078005918/ronnie-peterson-14-02-1944-11-09-1978-super", "http://smarmyclothes.tumblr.com/post/26937804740/heres-an-updated-version-of-my-nightmare-before", "http://smarmyclothes.tumblr.com/post/26937804740/heres-an-updated-version-of-my-nightmare-before", "http://smarmyclothes.tumblr.com/post/26937804740/heres-an-updated-version-of-my-nightmare-before", "http://smileironically.tumblr.com/tagged/4th+wall", "http://smileironically.tumblr.com/tagged/4th+wall", "http://smileironically.tumblr.com/tagged/4th+wall", "http://solosoncosas.tumblr.com/post/19786432339", "http://solosoncosas.tumblr.com/post/19786432339", "http://solosoncosas.tumblr.com/post/19786432339", "http://soulbrotherv2.tumblr.com/post/43231376385/trailer-for-the-documentary-negroes-with-guns", "http://soulbrotherv2.tumblr.com/post/43231376385/trailer-for-the-documentary-negroes-with-guns", "http://soulbrotherv2.tumblr.com/post/43231376385/trailer-for-the-documentary-negroes-with-guns", "http://squishyzelo.tumblr.com/", "http://squishyzelo.tumblr.com/", "http://squishyzelo.tumblr.com/", "http://starbucksspelling.tumblr.com/image/43083307778", "http://starbucksspelling.tumblr.com/image/43083307778", "http://starbucksspelling.tumblr.com/image/43083307778", "http://starlingsoftheslipstream.tumblr.com/archive/2009/6", "http://starlingsoftheslipstream.tumblr.com/archive/2009/6", "http://starlingsoftheslipstream.tumblr.com/archive/2009/6", "http://stehboaventura.tumblr.com/post/42430524071", "http://stehboaventura.tumblr.com/post/42430524071", "http://stehboaventura.tumblr.com/post/42430524071", "http://straight-furyo.tumblr.com/submit", "http://straight-furyo.tumblr.com/submit", "http://straight-furyo.tumblr.com/submit", "http://strikewitches-lover.tumblr.com/post/63080883643", "http://strikewitches-lover.tumblr.com/post/63080883643", "http://strikewitches-lover.tumblr.com/post/63080883643", "http://stylishandviewtiful.tumblr.com/post/13102441932/rep-rep-rep-represent", "http://stylishandviewtiful.tumblr.com/post/13102441932/rep-rep-rep-represent", "http://stylishandviewtiful.tumblr.com/post/13102441932/rep-rep-rep-represent", "http://swimmingviolist.tumblr.com/post/9609458672/doctorwho-production-still-from-this-saturdays", "http://swimmingviolist.tumblr.com/post/9609458672/doctorwho-production-still-from-this-saturdays", "http://swimmingviolist.tumblr.com/post/9609458672/doctorwho-production-still-from-this-saturdays", "http://syrupvillageprincess.tumblr.com/post/10284442464", "http://syrupvillageprincess.tumblr.com/post/10284442464", "http://syrupvillageprincess.tumblr.com/post/10284442464", "http://tatertats-photography.tumblr.com/archive", "http://tatertats-photography.tumblr.com/archive", "http://tatertats-photography.tumblr.com/archive", "http://tegan1991.tumblr.com/post/13491921659", "http://tegan1991.tumblr.com/post/13491921659", "http://tegan1991.tumblr.com/post/13491921659", "http://tenrai-f.tumblr.com/", "http://tenrai-f.tumblr.com/", "http://tenrai-f.tumblr.com/", "http://textless.tumblr.com/post/44142599977", "http://textless.tumblr.com/post/44142599977", "http://textless.tumblr.com/post/44142599977", "http://tf2memes.tumblr.com/post/53836830187/shame-there-isnt-a-resistance-to-promotional", "http://tf2memes.tumblr.com/post/53836830187/shame-there-isnt-a-resistance-to-promotional", "http://tf2memes.tumblr.com/post/53836830187/shame-there-isnt-a-resistance-to-promotional", "http://th3kid.tumblr.com/post/15344087233", "http://th3kid.tumblr.com/post/15344087233", "http://th3kid.tumblr.com/post/15344087233", "http://that-mouthy-christian.tumblr.com/post/52309891701/homophobia-where-i-am-at-least-is-not-limited-to", "http://that-mouthy-christian.tumblr.com/post/52309891701/homophobia-where-i-am-at-least-is-not-limited-to", "http://that-mouthy-christian.tumblr.com/post/52309891701/homophobia-where-i-am-at-least-is-not-limited-to", "http://the-thought-of-samy.tumblr.com/", "http://the-thought-of-samy.tumblr.com/", "http://the-thought-of-samy.tumblr.com/", "http://theartofanimation.tumblr.com/post/5178964981/yoko-tanji", "http://theartofanimation.tumblr.com/post/5178964981/yoko-tanji", "http://theartofanimation.tumblr.com/post/5178964981/yoko-tanji", "http://thebigup.tumblr.com/", "http://thebigup.tumblr.com/", "http://thebigup.tumblr.com/", "http://thefuture1026.tumblr.com/post/24990065449", "http://thefuture1026.tumblr.com/post/24990065449", "http://thefuture1026.tumblr.com/post/24990065449", "http://thegirlwhosneverenough.tumblr.com/", "http://thegirlwhosneverenough.tumblr.com/", "http://thegirlwhosneverenough.tumblr.com/", "http://thelcf666.tumblr.com/post/43191455881/art", "http://thelcf666.tumblr.com/post/43191455881/art", "http://thelcf666.tumblr.com/post/43191455881/art", "http://thelingerieaddict.tumblr.com/tagged/style/page/2", "http://thelingerieaddict.tumblr.com/tagged/style/page/2", "http://thelingerieaddict.tumblr.com/tagged/style/page/2", "http://thelionstirs.tumblr.com/post/34077138377/in-case-you-needed-a-reason-to-love-the-far-side", "http://thelionstirs.tumblr.com/post/34077138377/in-case-you-needed-a-reason-to-love-the-far-side", "http://thelionstirs.tumblr.com/post/34077138377/in-case-you-needed-a-reason-to-love-the-far-side", "http://thelittleblackfish.tumblr.com/post/50981875561", "http://thelittleblackfish.tumblr.com/post/50981875561", "http://thelittleblackfish.tumblr.com/post/50981875561", "http://themptybox.tumblr.com/tagged/los-simpsons", "http://themptybox.tumblr.com/tagged/los-simpsons", "http://themptybox.tumblr.com/tagged/los-simpsons", "http://thereallifeofsbrana.tumblr.com/post/53307372115/nas", "http://thereallifeofsbrana.tumblr.com/post/53307372115/nas", "http://thereallifeofsbrana.tumblr.com/post/53307372115/nas", "http://thereisnobox.tumblr.com/tagged/beauty/page/2", "http://thereisnobox.tumblr.com/tagged/beauty/page/2", "http://thereisnobox.tumblr.com/tagged/beauty/page/2", "http://thesunshineseverybodydies.tumblr.com/post/31184347254", "http://thesunshineseverybodydies.tumblr.com/post/31184347254", "http://thesunshineseverybodydies.tumblr.com/post/31184347254", "http://thevintagepalate.tumblr.com/tagged/Red-Wine", "http://thevintagepalate.tumblr.com/tagged/Red-Wine", "http://thevintagepalate.tumblr.com/tagged/Red-Wine", "http://thingswethinkweknow.tumblr.com/", "http://thingswethinkweknow.tumblr.com/", "http://thingswethinkweknow.tumblr.com/", "http://thirdcoastclassic.tumblr.com/post/22188278449/we-interrupt-your-regularly-scheduled-programming", "http://thirdcoastclassic.tumblr.com/post/22188278449/we-interrupt-your-regularly-scheduled-programming", "http://thirdcoastclassic.tumblr.com/post/22188278449/we-interrupt-your-regularly-scheduled-programming", "http://thirteen-ways.tumblr.com/post/22401949615", "http://thirteen-ways.tumblr.com/post/22401949615", "http://thirteen-ways.tumblr.com/post/22401949615", "http://tiffhwangs.tumblr.com/post/54860907313", "http://tiffhwangs.tumblr.com/post/54860907313", "http://tiffhwangs.tumblr.com/post/54860907313", "http://timelightbox.tumblr.com/post/44083136867/lbmdispatch-andy-prokop-2012-stocktonian-of", "http://timelightbox.tumblr.com/post/44083136867/lbmdispatch-andy-prokop-2012-stocktonian-of", "http://timelightbox.tumblr.com/post/44083136867/lbmdispatch-andy-prokop-2012-stocktonian-of", "http://tinyhandsman.tumblr.com/", "http://tinyhandsman.tumblr.com/", "http://tinyhandsman.tumblr.com/", "http://tokyofan.tumblr.com/tagged/bread-pudding", "http://tokyofan.tumblr.com/tagged/bread-pudding", "http://tokyofan.tumblr.com/tagged/bread-pudding", "http://tomhynes.tumblr.com/post/28580319860/stop-whatever-it-is-youre-doing-right-now-and", "http://tomhynes.tumblr.com/post/28580319860/stop-whatever-it-is-youre-doing-right-now-and", "http://tomhynes.tumblr.com/post/28580319860/stop-whatever-it-is-youre-doing-right-now-and", "http://trixibelle.tumblr.com/post/23054118632/oops", "http://trixibelle.tumblr.com/post/23054118632/oops", "http://trixibelle.tumblr.com/post/23054118632/oops", "http://tsox.tumblr.com/mobile", "http://tsox.tumblr.com/mobile", "http://tsox.tumblr.com/mobile", "http://tupacabra.tumblr.com/post/35070876148/if-i-were-to-draw-a-sassy-animal-what-should-it", "http://tupacabra.tumblr.com/post/35070876148/if-i-were-to-draw-a-sassy-animal-what-should-it", "http://tupacabra.tumblr.com/post/35070876148/if-i-were-to-draw-a-sassy-animal-what-should-it", "http://twotoneatl.tumblr.com/image/19771643322", "http://twotoneatl.tumblr.com/image/19771643322", "http://twotoneatl.tumblr.com/image/19771643322", "http://ultramusicfest.tumblr.com/post/24870174898", "http://ultramusicfest.tumblr.com/post/24870174898", "http://ultramusicfest.tumblr.com/post/24870174898", "http://unicornfae.tumblr.com/post/40705857999", "http://unicornfae.tumblr.com/post/40705857999", "http://unicornfae.tumblr.com/post/40705857999", "http://vannegarcia.tumblr.com/post/64439059094/su-sonrisa-es-hermosa-el-es-mi-todo-es-mi", "http://vannegarcia.tumblr.com/post/64439059094/su-sonrisa-es-hermosa-el-es-mi-todo-es-mi", "http://vannegarcia.tumblr.com/post/64439059094/su-sonrisa-es-hermosa-el-es-mi-todo-es-mi", "http://verored.tumblr.com/post/21955231352/vogueweekend-lara-stone-photographed-by-josh", "http://verored.tumblr.com/post/21955231352/vogueweekend-lara-stone-photographed-by-josh", "http://verored.tumblr.com/post/21955231352/vogueweekend-lara-stone-photographed-by-josh", "http://vicemag.tumblr.com/post/54539590674/are-you-a-nerd-by-james-franco-what-is-a-nerd", "http://vicemag.tumblr.com/post/54539590674/are-you-a-nerd-by-james-franco-what-is-a-nerd", "http://vicemag.tumblr.com/post/54539590674/are-you-a-nerd-by-james-franco-what-is-a-nerd", "http://viciouslycyd.tumblr.com/post/29389445617", "http://viciouslycyd.tumblr.com/post/29389445617", "http://viciouslycyd.tumblr.com/post/29389445617", "http://victorianromantic.tumblr.com/", "http://victorianromantic.tumblr.com/", "http://victorianromantic.tumblr.com/", "http://vinniwidayanti.tumblr.com/", "http://vinniwidayanti.tumblr.com/", "http://vinniwidayanti.tumblr.com/", "http://vintageromancing.tumblr.com/post/31456243110/marilyn-monroe-in-some-like-it-hot", "http://vintageromancing.tumblr.com/post/31456243110/marilyn-monroe-in-some-like-it-hot", "http://vintageromancing.tumblr.com/post/31456243110/marilyn-monroe-in-some-like-it-hot", "http://vogueweekend.tumblr.com/tagged/Marie-Piovesan", "http://vogueweekend.tumblr.com/tagged/Marie-Piovesan", "http://vogueweekend.tumblr.com/tagged/Marie-Piovesan", "http://wearepartnersincrime.tumblr.com/post/24661156367", "http://wearepartnersincrime.tumblr.com/post/24661156367", "http://wearepartnersincrime.tumblr.com/post/24661156367", "http://wearingwanderlust.tumblr.com/post/42491653759/my-updated-inspiration-board-my-inspiration-board", "http://wearingwanderlust.tumblr.com/post/42491653759/my-updated-inspiration-board-my-inspiration-board", "http://wearingwanderlust.tumblr.com/post/42491653759/my-updated-inspiration-board-my-inspiration-board", "http://westeastsouthnorth.tumblr.com/post/21247579628/wuyuan-china", "http://westeastsouthnorth.tumblr.com/post/21247579628/wuyuan-china", "http://westeastsouthnorth.tumblr.com/post/21247579628/wuyuan-china", "http://whats-a-stiles24.tumblr.com/", "http://whats-a-stiles24.tumblr.com/", "http://whats-a-stiles24.tumblr.com/", "http://whatthefinnick.tumblr.com/post/26718259422", "http://whatthefinnick.tumblr.com/post/26718259422", "http://whatthefinnick.tumblr.com/post/26718259422", "http://whatwouldjustinado.tumblr.com/", "http://whatwouldjustinado.tumblr.com/", "http://whatwouldjustinado.tumblr.com/", "http://whiterabbitmarichi.tumblr.com/", "http://whiterabbitmarichi.tumblr.com/", "http://whiterabbitmarichi.tumblr.com/", "http://whlr.tumblr.com/tagged/Laax", "http://whlr.tumblr.com/tagged/Laax", "http://whlr.tumblr.com/tagged/Laax", "http://whoneedswhat.tumblr.com/post/28822028167", "http://whoneedswhat.tumblr.com/post/28822028167", "http://whoneedswhat.tumblr.com/post/28822028167", "http://wickedtaste.tumblr.com/post/51094778002", "http://wickedtaste.tumblr.com/post/51094778002", "http://wickedtaste.tumblr.com/post/51094778002", "http://windups.tumblr.com/post/25012279508", "http://windups.tumblr.com/post/25012279508", "http://windups.tumblr.com/post/25012279508", "http://www.tumblr.com/tagged/garry?language=de_DE", "http://www.tumblr.com/tagged/garry?language=de_DE", "http://www.tumblr.com/tagged/garry?language=de_DE", "http://www.tumblr.com/tagged/rosemary-pilkington", "http://www.tumblr.com/tagged/rosemary-pilkington", "http://www.tumblr.com/tagged/rosemary-pilkington", "http://x-meninyourface.tumblr.com/post/28491218624", "http://x-meninyourface.tumblr.com/post/28491218624", "http://x-meninyourface.tumblr.com/post/28491218624", "http://xltrocks.tumblr.com/", "http://xltrocks.tumblr.com/", "http://xltrocks.tumblr.com/", "http://yeeeww.tumblr.com/post/31087681188/matt-wilko", "http://yeeeww.tumblr.com/post/31087681188/matt-wilko", "http://yeeeww.tumblr.com/post/31087681188/matt-wilko", "http://yellow-dress.tumblr.com/post/42666014753/hey-sexy-nice-tits-woah-why-are-you-so-upset", "http://yellow-dress.tumblr.com/post/42666014753/hey-sexy-nice-tits-woah-why-are-you-so-upset", "http://yellow-dress.tumblr.com/post/42666014753/hey-sexy-nice-tits-woah-why-are-you-so-upset", "http://youknowyourefromindianawhen.tumblr.com/post/7725441404/submission", "http://youknowyourefromindianawhen.tumblr.com/post/7725441404/submission", "http://youknowyourefromindianawhen.tumblr.com/post/7725441404/submission", "http://zadill.tumblr.com/post/15512247217/today-is-the-day-i-leave-on-my-next-chapeter-of", "http://zadill.tumblr.com/post/15512247217/today-is-the-day-i-leave-on-my-next-chapeter-of", "http://zadill.tumblr.com/post/15512247217/today-is-the-day-i-leave-on-my-next-chapeter-of", "http://zidapi.tumblr.com/post/3079039225", "http://zidapi.tumblr.com/post/3079039225", "http://zidapi.tumblr.com/post/3079039225", "http://zombiecardgame.tumblr.com/tagged/Horror-movie", "http://zombiecardgame.tumblr.com/tagged/Horror-movie", "http://zombiecardgame.tumblr.com/tagged/Horror-movie"], "amazon": ["http://aws.amazon.com/customerapps/295", "http://aws.amazon.com/customerapps/295", "http://aws.amazon.com/customerapps/295", "http://www.amazon.com/Assange-Julian-Modern-Inside-WikiLeaks/dp/B004I8WN32", "http://www.amazon.com/Assange-Julian-Modern-Inside-WikiLeaks/dp/B004I8WN32", "http://www.amazon.com/Assange-Julian-Modern-Inside-WikiLeaks/dp/B004I8WN32", "http://www.amazon.com/Breakfast-Bed-Joan-Osborne/dp/B000O78KZG", "http://www.amazon.com/Breakfast-Bed-Joan-Osborne/dp/B000O78KZG", "http://www.amazon.com/Breakfast-Bed-Joan-Osborne/dp/B000O78KZG", "http://www.amazon.com/Closing-Time/dp/B003A0IAQI", "http://www.amazon.com/Closing-Time/dp/B003A0IAQI", "http://www.amazon.com/Closing-Time/dp/B003A0IAQI", "http://www.amazon.com/Crisis-Intervention-Handbook-Assessment-Treatment/dp/0195179919", "http://www.amazon.com/Crisis-Intervention-Handbook-Assessment-Treatment/dp/0195179919", "http://www.amazon.com/Crisis-Intervention-Handbook-Assessment-Treatment/dp/0195179919", "http://www.amazon.com/Not-Just-Beatles-Autobiography-Bernstein/dp/0970610106", "http://www.amazon.com/Not-Just-Beatles-Autobiography-Bernstein/dp/0970610106", "http://www.amazon.com/Not-Just-Beatles-Autobiography-Bernstein/dp/0970610106", "http://www.amazon.com/forum/playstation%203?asin=B007M6W3A0&cdForum=Fx2VG4XY5OWU8OI&cdPage=1&cdSort=newest&cdThread=Tx2WR49V0OKUTGD", "http://www.amazon.com/forum/playstation%203?asin=B007M6W3A0&cdForum=Fx2VG4XY5OWU8OI&cdPage=1&cdSort=newest&cdThread=Tx2WR49V0OKUTGD", "http://www.amazon.com/forum/playstation%203?asin=B007M6W3A0&cdForum=Fx2VG4XY5OWU8OI&cdPage=1&cdSort=newest&cdThread=Tx2WR49V0OKUTGD", "http://www.amazon.com/forum/textbook%20buyback?cdAnchor=0345472322&cdForum=Fx3QLVRL4OTAZTD&cdPage=1", "http://www.amazon.com/forum/textbook%20buyback?cdAnchor=0345472322&cdForum=Fx3QLVRL4OTAZTD&cdPage=1", "http://www.amazon.com/forum/textbook%20buyback?cdAnchor=0345472322&cdForum=Fx3QLVRL4OTAZTD&cdPage=1", "http://www.amazon.com/review/R1IF2JYR6P4QYG", "http://www.amazon.com/review/R1IF2JYR6P4QYG", "http://www.amazon.com/review/R1IF2JYR6P4QYG", "http://www.amazon.com/s?ie=UTF8&page=1&rh=i%3Aaps%2Ck%3AFemales%20Weight%20And%20Height%20Chart", "http://www.amazon.com/s?ie=UTF8&page=1&rh=i%3Aaps%2Ck%3AFemales%20Weight%20And%20Height%20Chart", "http://www.amazon.com/s?ie=UTF8&page=1&rh=i%3Aaps%2Ck%3AFemales%20Weight%20And%20Height%20Chart", "http://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A163856011%2Ck%3AMaps%20%26%20Atlases", "http://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A163856011%2Ck%3AMaps%20%26%20Atlases", "http://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A163856011%2Ck%3AMaps%20%26%20Atlases", "http://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A5174%2Ck%3AJoe%20Ely%20%3A%3A%20Roll%20Again", "http://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A5174%2Ck%3AJoe%20Ely%20%3A%3A%20Roll%20Again", "http://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A5174%2Ck%3AJoe%20Ely%20%3A%3A%20Roll%20Again"], "error": false, "counts": [["www.vesalia.de", 15], ["www.bellaonline.com", 15], ["boards.fool.com", 12], ["www.europarl.europa.eu", 15], ["www.995wmag.com", 15], ["doctor.webmd.com", 27], ["httpd.apache.org", 12], ["www.charlestondailymail.com", 15], ["www.whitepages.com", 45], ["www.gettyimages.co.jp", 12], ["www.rootsweb.ancestry.com", 21], ["www.investopedia.com", 15], ["www.kbb.com", 15], ["www.saukvalley.com", 15], ["www.alibris.com", 15], ["www.serebiiforums.com", 33], ["www.tahoedailytribune.com", 18], ["arkivverket.no", 12], ["pittsburgh.cbslocal.com", 12], ["www.registercitizen.com", 12], ["www.ultimate-guitar.com", 21], ["www.artpromos.com", 15], ["www.starbucksstore.com", 12], ["www.thegreenoffice.com", 24], ["www.tomshardware.com", 12], ["radaris.com", 24], ["www.1075wzrx.com", 12], ["www.atoygarden.com", 36], ["www.memecenter.com", 18], ["www.ramforumz.com", 15], ["www.shipwreckbeads.com", 21], ["www.underarmour.com", 12], ["www.gaiaonline.com", 12], ["www.globalindustrial.com", 15], ["www.usingenglish.com", 21], ["consumerist.com", 15], ["www.dot.ca.gov", 18], ["www.africahunting.com", 18], ["www.twitch.tv", 21], ["www.fanzz.com", 12], ["www.shoptrailblazer.com", 12], ["vilda.alaska.edu", 15], ["www.tripadvisor.se", 21], ["itknowledgeexchange.techtarget.com", 15], ["www.tripadvisor.it", 45], ["www.herveleger.com", 21], ["www.islandpacket.com", 15], ["www.wowace.com", 15], ["reason.com", 12], ["www.unep-wcmc.org", 15], ["www.jensonusa.com", 21], ["www.baseballamerica.com", 18], ["www.biospace.com", 39], ["www.reuters.com", 27], ["www.cagle.com", 18], ["www.airbus.com", 12], ["www.chegg.com", 15], ["www.wfaa.com", 18], ["www.blackberryforums.com", 24], ["www.fender.com", 12], ["www.gameboomers.com", 42], ["direct.asda.com", 18], ["www.shiekhshoes.com", 18], ["www.officesupersavers.com", 12], ["developer.nokia.com", 18], ["www.cosplay.com", 39], ["www.tradingcardcentral.com", 27], ["www.visitestonia.com", 18], ["www.huffingtonpost.ca", 12], ["www.coursesmart.com", 12], ["www.faz.net", 12], ["www.petland.com", 15], ["www.virtualtourist.com", 27], ["programmers.stackexchange.com", 54], ["www.bluefly.com", 18], ["www.psypokes.com", 15], ["www.pointstreak.com", 12], ["www.popmatters.com", 12], ["www.cdrinfo.com", 15], ["es.wikipedia.org", 33], ["www.pornhub.com", 27], ["www.8notes.com", 15], ["themagicwarehouse.com", 12], ["www.personalizationmall.com", 15], ["www.kirksvilledailyexpress.com", 15], ["www.magnetstreet.com", 24], ["www.chazhound.com", 15], ["www.drsfostersmith.com", 12], ["www.thewhoshop.com", 12], ["www.securitystoreusa.com", 15], ["www.movieposter.com", 21], ["www.news-gazette.com", 18], ["www.ruralking.com", 12], ["hauntedhouses.com", 21], ["austin.citysearch.com", 12], ["forum.africanhiphop.com", 15], ["www.shure.com", 12], ["www.big1059.com", 15], ["www.metoperashop.org", 21], ["www.guitarcenter.com", 15], ["www.landsend.com", 60], ["digital.library.louisville.edu", 21], ["www.x17online.com", 15], ["www.tenmanga.com", 24], ["www.zalando.de", 12], ["www.taringa.net", 15], ["lists.opensuse.org", 12], ["cruises.orbitz.com", 12], ["www.radionomy.com", 12], ["www.vayama.com", 15], ["marketplace.xbox.com", 12], ["www.greenpeace.org", 36], ["classifieds.syracuse.com", 15], ["contentdm.ad.umbc.edu", 12], ["www.handgunforum.net", 15], ["www.bizjournals.com", 27], ["forum.e46fanatics.com", 51], ["www.mix1077.com", 18], ["www.techspot.com", 18], ["www.racer.com", 18], ["www.kmjm.com", 12], ["mail-index.netbsd.org", 24], ["hockey.dobbersports.com", 24], ["www.sevenforums.com", 21], ["www.surffanatics.com", 21], ["www.skinstore.com", 12], ["www.wkot.com", 27], ["www.lomography.com", 18], ["www.dickssportinggoods.com", 30], ["www.fabsugar.com", 24], ["lists.gnu.org", 15], ["www.jdate.com", 18], ["www.bathandbodyworks.com", 21], ["www.autograph-supply.com", 12], ["www.backtrack-linux.org", 24], ["www.lastfm.de", 36], ["www.drdavidwilliams.com", 21], ["forums.webmd.com", 12], ["www.digitalhorizonsonline.org", 15], ["www.build.com", 12], ["digital.sfasu.edu", 15], ["www.newlook.com", 15], ["claz.org", 21], ["skinbotanica.com", 12], ["librarydigitalcollections.weber.edu", 12], ["www.boyscoutstore.com", 18], ["www.crunchyroll.com", 30], ["www.jegem.com", 12], ["www.artslant.com", 12], ["www.tripadvisor.es", 51], ["www.ticketsinventory.com", 12], ["collections.lib.uwm.edu", 21], ["xfinity.comcast.net", 54], ["www.publicsurplus.com", 15], ["forums.llli.org", 21], ["www.timeout.com", 12], ["www.twistedthrottle.com", 24], ["www.startribune.com", 18], ["skateparkoftampa.com", 12], ["www.ozarksfirst.com", 21], ["www.weatheronline.co.uk", 30], ["www.stylemepretty.com", 27], ["www.charlestonnaturally.com", 12], ["www.dartmouthsports.com", 12], ["www.blindsaver.com", 21], ["www.globalgolf.com", 12], ["www.celebuzz.com", 12], ["freerepublic.com", 12], ["www.ign.com", 12], ["www.ewtn.com", 12], ["www.dailyregister.com", 12], ["www.uvm.edu", 12], ["www.firstcoastnews.com", 12], ["www.costco.com", 15], ["www.backcountryedge.com", 18], ["www.designnews.com", 18], ["www.surlatable.com", 12], ["sanfrancisco.citysearch.com", 15], ["www.classifiedsgiant.com", 30], ["www.kudzu.com", 48], ["www.delmarfans.com", 30], ["www.aeropostale.com", 12], ["www.starcourier.com", 15], ["perlguru.com", 12], ["dictionary.reference.com", 60], ["www.1aauto.com", 18], ["www.csindy.com", 12], ["www.forensicswiki.org", 15], ["www.designsponge.com", 18], ["www.nato.int", 24], ["www.giftcards.com", 18], ["socialitelife.com", 12], ["www.gunbroker.com", 12], ["store.steampowered.com", 27], ["www.urbandecay.com", 12], ["www.kgw.com", 27], ["www.oldies941.com", 15], ["www.bimmerfest.com", 21], ["www.kcbd.com", 12], ["www.orafaq.com", 15], ["www.charlotte49ers.com", 18], ["shop.ccs.com", 33], ["www.oper-frankfurt.de", 27], ["www.worldcat.org", 51], ["www.eileenfisher.com", 21], ["bartleby.com", 12], ["www.mowtownusa.com", 15], ["www.drugstore.com", 12], ["www.charityblossom.org", 21], ["mountainproject.com", 12], ["www.cnn.com", 48], ["www.costcentral.com", 21], ["www.newbelgium.com", 24], ["www.ip-adress.com", 12], ["www.controlglobal.com", 12], ["blog.timesunion.com", 12], ["www.fragrancex.com", 27], ["www.tvfanatic.com", 15], ["www.gmtruckclub.com", 24], ["www.staples.com", 27], ["mathforum.org", 15], ["www.wesh.com", 12], ["www.iheart.com", 42], ["evols.library.manoa.hawaii.edu", 12], ["www.andriasang.com", 18], ["www.local8now.com", 12], ["no.tripadvisor.com", 39], ["www.ridgecrestca.com", 12], ["us.macmillan.com", 12], ["247sports.com", 12], ["www.designhotels.com", 84], ["www.kiddicare.com", 15], ["bmgf.bulbagarden.net", 30], ["muscleandbrawn.com", 21], ["metmuseum.org", 27], ["www.travelpod.com", 24], ["www.vueling.com", 21], ["www.drinkstuff.com", 12], ["www.tv.com", 15], ["www.celebrateexpress.com", 12], ["www.purplepride.org", 27], ["www.faniq.com", 18], ["tvrhl.com", 12], ["www.textbooks.com", 12], ["www.funnyjunk.com", 27], ["www.gifts.com", 27], ["www.pbnation.com", 21], ["www.oreck.com", 27], ["www.njdevs.com", 12], ["www.travelandleisure.com", 12], ["www.ato.gov.au", 15], ["www.opentip.com", 12], ["www.osnews.com", 39], ["www.vitaminlife.com", 12], ["www.meritbadge.org", 12], ["www.iwindsurf.com", 15], ["www.cbc.ca", 12], ["www.therecordherald.com", 12], ["profile.cheezburger.com", 18], ["www.the-house.com", 12], ["www.conceptart.org", 27], ["www.truecar.com", 27], ["www.jcpenney.com", 24], ["bleacherreport.com", 33], ["www.jaeger.co.uk", 36], ["www.drgnews.com", 18], ["www.accuweather.com", 93], ["www.grhealth.org", 24], ["www.recchiuti.com", 33], ["www.stjohns.edu", 24], ["www.lynda.com", 30], ["www.askart.com", 12], ["www.nytimes.com", 45], ["www.ktvb.com", 21], ["en.wiktionary.org", 30], ["thefutoncritic.com", 12], ["yahoosports.teamfanshop.com", 18], ["www.draftcountdown.com", 27], ["prsguitars.com", 21], ["io9.com", 36], ["www.lds.org", 18], ["www.lanvin.com", 15], ["cdnc.ucr.edu", 18], ["www.astm.org", 18], ["www.channel3000.com", 15], ["www.techdirt.com", 12], ["www.bellacor.com", 12], ["www.broadwayworld.com", 21], ["esupport.sony.com", 15], ["forums.macrumors.com", 27], ["digital.library.villanova.edu", 15], ["www.wrdu.com", 12], ["cookeatshare.com", 12], ["www.deadfred.com", 24], ["www.invasive.org", 21], ["www.buckle.com", 30], ["www.net-a-porter.com", 27], ["www.chocolatetradingco.com", 18], ["www.cheapassgamer.com", 18], ["www.tripadvisor.com", 39], ["www.wvgazette.com", 24], ["www.marketwatch.com", 24], ["www.craftsman.com", 12], ["www.kimatv.com", 12], ["www.reverbnation.com", 39], ["shop.idwpublishing.com", 15], ["www.thelawyer.com", 12], ["www.seetickets.com", 12], ["www.barrystickets.com", 12], ["www.jny.com", 12], ["www.footsmart.com", 18], ["rotunda.upress.virginia.edu", 18], ["www.metrolyrics.com", 48], ["www.boonvilledailynews.com", 21], ["www.sailmagazine.com", 12], ["www.cancer.gov", 39], ["www.wikinvest.com", 39], ["repairpal.com", 21], ["psychology.wikia.com", 24], ["www.bikefriday.com", 18], ["outpersonals.com", 18], ["www.nba.com", 15], ["www.streetsideauto.com", 18], ["www.nrl.com", 12], ["www.tylerpaper.com", 33], ["www.runnersworld.co.uk", 12], ["www.hatcountry.com", 18], ["www.carters.com", 12], ["www.racorstoragesolutions.com", 18], ["gamingtrend.com", 15], ["draftcountdown.com", 51], ["www.target.com", 36], ["sourceforge.net", 57], ["www.popsugar.com", 15], ["www.deliaonline.com", 12], ["www.streetinsider.com", 12], ["www.wolfgangsvault.com", 18], ["beeradvocate.com", 21], ["www.pcgs.com", 15], ["inhabitat.com", 18], ["www.kicker.de", 12], ["www.appbrain.com", 27], ["www.thehorse.com", 15], ["usa.frenchconnection.com", 27], ["shine.yahoo.com", 15], ["www.stylebistro.com", 24], ["www.dogster.com", 12], ["www.gettyimages.de", 12], ["www.walmart.com", 39], ["www.food.com", 27], ["www.rediff.com", 18], ["www.tennisexpress.com", 12], ["www.blackberryos.com", 15], ["www.gamefaqs.com", 81], ["query.nytimes.com", 30], ["www.abbreviations.com", 24], ["www.skymall.com", 12], ["www.igrandtheftauto.com", 12], ["www.sonsofstevegarvey.com", 12], ["www.clubcorp.com", 18], ["maintankadin.failsafedesign.com", 27], ["www.wikidata.org", 33], ["everything2.com", 30], ["www.westmichiganstar.com", 15], ["www.apartmentguide.com", 15], ["library.thinkquest.org", 12], ["www.menstennisforums.com", 36], ["www.caller.com", 15], ["www.marylandpublicschools.org", 42], ["www.jdc.org", 12], ["www.plumdistrict.com", 12], ["www.newsleader.com", 15], ["www.he-man.org", 36], ["public.fotki.com", 18], ["www.simplemachines.org", 12], ["www.wildflower.org", 12], ["www.gourmetstation.com", 18], ["www.afr.com", 18], ["docs.spring.io", 15], ["sharepoint.stackexchange.com", 12], ["www.cfbdatawarehouse.com", 12], ["www.unog.ch", 12], ["www.edenfoods.com", 78], ["www.crash.net", 39], ["www.familytreecircles.com", 12], ["www.modelmayhem.com", 36], ["www.saratogawine.com", 30], ["www.horchow.com", 18], ["www.marriott.com", 30], ["www.xbox360achievements.org", 54], ["www.zedge.net", 27], ["www.sgccard.com", 12], ["www.fandango.com", 18], ["www.allvoices.com", 18], ["www.pentel.com", 24], ["www.khnr.com", 12], ["www.perfectgame.org", 12], ["mocpages.com", 12], ["www.thestate.com", 21], ["thenumbers.marketplace.org", 21], ["www.scielo.br", 12], ["www.phonedog.com", 15], ["www.geni.com", 27], ["newyork.citysearch.com", 15], ["www.break.com", 24], ["www.theflyfishingforum.com", 18], ["www.gotapex.com", 18], ["timesfreepress.com", 12], ["sv.wikipedia.org", 27], ["www.georgiasuperads.com", 18], ["www.java-gaming.org", 12], ["cheezburger.com", 18], ["www.mathisfunforum.com", 18], ["football.fantasysports.yahoo.com", 12], ["judaism.stackexchange.com", 18], ["www.dailypaul.com", 33], ["www.ephotozine.com", 12], ["daytimeroyaltyonline.com", 27], ["www.audi-sport.net", 15], ["www.sportingnews.com", 21], ["www.bpa.gov", 12], ["www.democraticunderground.com", 21], ["www.summithut.com", 15], ["www.fm106.com", 12], ["www.mangahere.com", 15], ["www.motortopia.com", 15], ["www.dgcoursereview.com", 33], ["www.golf.com", 42], ["ufdc.ufl.edu", 18], ["snf.stanford.edu", 12], ["www.wowdb.com", 39], ["www.allposters.com", 30], ["www.payless.com", 15], ["www.wordans.com", 12], ["movies.yahoo.com", 12], ["on.aol.com", 12], ["www.dharmawheel.net", 15], ["phoronix.com", 33], ["www.ptg.org", 18], ["www.careerbuilder.com", 15], ["www.krem.com", 21], ["orangecounty.citysearch.com", 18], ["www.sierratradingpost.com", 12], ["www.hardwarecanucks.com", 18], ["cdm16001.contentdm.oclc.org", 15], ["football.epicsports.com", 21], ["www.newstribune.com", 21], ["www.wndu.com", 45], ["freesound.org", 12], ["www.coupons.com", 18], ["www.notonthehighstreet.com", 12], ["www.formapuraliving.com", 15], ["www.topix.com", 33], ["www.syracuse.com", 12], ["www.lastfm.it", 21], ["forums.applecentral.com", 24], ["gastateparks.org", 21], ["www.dooyoo.co.uk", 18], ["www.lanebryant.com", 15], ["www.neagle.com", 15], ["www.fashionfabricsclub.com", 15], ["www.knex.com", 21], ["www.vectorstock.com", 24], ["www.campsaver.com", 18], ["www.onlinecarstereo.com", 18], ["www.brainyquote.com", 12], ["www.baseballprospectus.com", 21], ["www.gamespot.com", 12], ["www.govacuum.com", 12], ["www.antiquesnavigator.com", 12], ["www.jjill.com", 21], ["www.paddling.net", 15], ["www.osti.gov", 15], ["www.runnersworld.com", 12], ["www.myhot105.com", 12], ["www.thesweetscience.com", 12], ["www.verabradley.com", 27], ["www.travelocity.com", 18], ["www.alice955.com", 12], ["boxofficemojo.com", 39], ["www.automd.com", 15], ["www.islamicfinder.org", 36], ["cdm16066.contentdm.oclc.org", 12], ["www.helmutlang.com", 27], ["www.millerwelds.com", 15], ["www.currentcatalog.com", 12], ["www.agoda.com", 96], ["www.massvacation.com", 12], ["content.time.com", 18], ["cleveland.indians.mlb.com", 12], ["alibi.com", 12], ["www.vitacost.com", 18], ["www.observer-reporter.com", 24], ["www.u2.com", 12], ["www.mediabistro.com", 30], ["sandiego.citysearch.com", 15], ["www.deseretnews.com", 15], ["www.acclaimimages.com", 18], ["www.mythtv.org", 24], ["www.motorcyclistonline.com", 12], ["www.netbuilders.org", 24], ["www.bostonglobe.com", 15], ["www.buildingscience.com", 12], ["www.zales.com", 39], ["www.usatoday.com", 30], ["packages.ubuntu.com", 30], ["www.youtube.com", 60], ["www.wincustomize.com", 18], ["www.hemmings.com", 30], ["www.sportsposterwarehouse.com", 12], ["twiends.com", 15], ["www.sfgate.com", 15], ["www.forever21.com", 21], ["forums.amd.com", 36], ["www.capcitybank.com", 24], ["www.ted.com", 18], ["mathhelpforum.com", 15], ["www.montenews.com", 15], ["ecom.datajoe.com", 21], ["www.news-press.com", 27], ["www.daedalus-books.com", 30], ["www.z104fm.com", 12], ["www.americanpoems.com", 15], ["www.collegehumor.com", 15], ["www.tvrage.com", 33], ["www.kitchenknifeforums.com", 12], ["www.radley.co.uk", 12], ["pt.dreamstime.com", 12], ["www.scuba.com", 12], ["www.orlandosentinel.com", 24], ["www.wakeworld.com", 39], ["www.news4jax.com", 12], ["www.scavengeinc.com", 12], ["www.nvnews.net", 24], ["www.arrowfunds.com", 12], ["www.chordie.com", 15], ["www.journeys.com", 42], ["www.ufc.com", 12], ["www.luggagepros.com", 39], ["www.diychatroom.com", 33], ["chowhound.chow.com", 15], ["www.askmen.com", 12], ["www.theiet.org", 12], ["openclipart.org", 21], ["www.jsonline.com", 15], ["www.poemhunter.com", 30], ["www.doorcountycoffee.com", 15], ["www.bookrenter.com", 21], ["deltafarmpress.com", 12], ["www.dollartree.com", 63], ["www.rapha.cc", 15], ["basketball.epicsports.com", 27], ["www.eagleoptics.com", 15], ["www.pianoworld.com", 15], ["www.sage.edu", 36], ["www.cnycentral.com", 12], ["www.pbase.com", 30], ["www.glassdoor.com", 30], ["www.tripadvisor.com.ve", 39], ["www.diapers.com", 12], ["openwetware.org", 21], ["www.scientificsonline.com", 12], ["www.hallmark.com", 36], ["www.babyage.com", 27], ["cms.iucn.org", 12], ["quizlet.com", 21], ["www.firemountaingems.com", 15], ["www3.unfccc.int", 24], ["store.chicagobears.com", 21], ["www.animenewsnetwork.com", 18], ["hothardware.com", 18], ["www.cemeteryscribes.com", 15], ["www.raptorsrepublic.com", 27], ["www.terrysvillage.com", 39], ["wiki.eclipse.org", 36], ["rentalo.com", 12], ["www.edugeek.net", 12], ["www.bloomberg.com", 24], ["o3.aolcdn.com", 12], ["www.bmwblog.com", 15], ["www.tomtom.com", 15], ["www.murraysworld.com", 12], ["www.951thebrew.com", 18], ["www.realwatersports.com", 18], ["www.medpedia.com", 12], ["www.canada.com", 12], ["archive.wgrz.com", 18], ["www.ipadforums.net", 18], ["www.canterbury.co.uk", 24], ["www.buddytv.com", 18], ["www.gunco.net", 27], ["www.fireplacesnow.com", 24], ["www.babycenter.com", 24], ["www.britannica.com", 48], ["www.replacements.com", 15], ["www.backseatbangers.com", 12], ["www.llbean.com", 27], ["www.christianmingle.com", 18], ["www.ripoffreport.com", 21], ["www.tankspot.com", 27], ["www.zappos.com", 15], ["www.filmitown.com", 15], ["www.sportsmansguide.com", 15], ["www.ababy.com", 12], ["askubuntu.com", 42], ["www.jcrew.com", 30], ["www.carolineprogress.com", 12], ["www.mcall.com", 33], ["www.figures.com", 15], ["catchmyparty.com", 15], ["www.kitsapsun.com", 21], ["www.americangreetings.com", 18], ["www.bulbtronics.com", 18], ["www.pamf.org", 12], ["www.klbjfm.com", 12], ["www.birthdayexpress.com", 18], ["www.trusnow.com", 18], ["www.basehorinfo.com", 12], ["www.whatdigitalcamera.com", 15], ["www.totalfilm.com", 15], ["stores.ebay.com", 15], ["itp.nyu.edu", 15], ["www.thestreet.com", 57], ["abcvacuumwarehouse.com", 12], ["www.goldenskate.com", 21], ["www.idahostatesman.com", 18], ["www.totalbeauty.com", 18], ["www.thehindu.com", 15], ["archive.wkyc.com", 12], ["www.proboardshop.com", 12], ["observer.com", 21], ["twittercounter.com", 18], ["www.caprinesupply.com", 15], ["www.sitemeter.com", 24], ["www.poets.org", 12], ["www.webelements.com", 30], ["en.wordpress.com", 18], ["www.knoxnews.com", 15], ["www.faithwriters.com", 21], ["www.hotelplanner.com", 21], ["viaf.org", 15], ["alfred.stlouisfed.org", 12], ["www.huffingtonpost.com", 21], ["www.bicycles.net.au", 15], ["www.canonrumors.com", 18], ["www.lasvegas.com", 36], ["www.cricketarchive.com", 15], ["electro-music.com", 21], ["www.defense.gov", 12], ["mobile.brainyquote.com", 12], ["www.dooney.com", 21], ["pinpoint.microsoft.com", 15], ["www.thewalkingcompany.com", 18], ["www.sex.com", 30], ["earthquake.usgs.gov", 12], ["www.crucial.com", 12], ["www.metacafe.com", 21], ["www.kentucky.com", 30], ["www.tripadvisor.com.tw", 39], ["www.tripadvisor.com.tr", 48], ["www.360cities.net", 21], ["www.sunadvocate.com", 15], ["www.nwitimes.com", 15], ["www.simplefloors.com", 12], ["www.horseracingnation.com", 15], ["www.islamicity.com", 15], ["www.accurist.co.uk", 18], ["media.photobucket.com", 12], ["www.biomedcentral.com", 15], ["www.twice.com", 12], ["www.javaprogrammingforums.com", 12], ["www.wusa9.com", 15], ["www.y100.com", 15], ["www.yesterdaystractors.com", 12], ["www.pga.com", 15], ["www.therealtechn9ne.com", 12], ["www.departmentofgoods.com", 12], ["www.ccc.edu", 45], ["www.magazines.com", 24], ["www.fluevog.com", 24], ["www.snagajob.com", 54], ["www.videosexarchive.com", 12], ["deadspin.com", 15], ["www.java-forums.org", 21], ["www.westelm.com", 21], ["www.marksdailyapple.com", 21], ["kde-apps.org", 36], ["www.discountgoalie.com", 12], ["www.wyndhamvacationrentals.com", 27], ["ytmnd.com", 24], ["www.parkaveliquor.com", 15], ["www.nj.com", 21], ["ficwad.com", 12], ["www.mangaupdates.com", 39], ["www.fansofrealitytv.com", 12], ["www.medicinenet.com", 21], ["www.tndeer.com", 30], ["www.ecmrecords.com", 24], ["www.doleta.gov", 33], ["www.tripadvisor.com.my", 27], ["www.redstate.com", 12], ["www.amazon.co.jp", 15], ["www.linuxforums.org", 24], ["us.fotolia.com", 24], ["www.bestwestern.com", 12], ["getglue.com", 12], ["atlanta.cbslocal.com", 12], ["www.wtvm.com", 12], ["www.carsurvey.org", 33], ["www.nurse.com", 15], ["www.chaptercheats.com", 18], ["www.redszone.com", 45], ["indiancountrytodaymedianetwork.com", 18], ["www.aikenstandard.com", 21], ["www.panoramio.com", 15], ["louisdl.louislibraries.org", 15], ["www.nhl.com", 18], ["www.myswitzerland.com", 21], ["www.originalpenguin.com", 36], ["www.spankwire.com", 12], ["www.adobe.com", 12], ["www.toyotapartszone.com", 12], ["products.cherrymoonfarms.com", 12], ["www.visitscotland.com", 12], ["www.sabian.com", 12], ["www.matchmaker.com", 12], ["www.prnewswire.com", 24], ["www.crocs.com", 15], ["www.wfmf.com", 12], ["www.snooth.com", 18], ["www.nbc15.com", 21], ["www.digtriad.com", 15], ["menards.com", 18], ["www.pizzamaking.com", 18], ["forum.linuxmce.org", 12], ["www.drjays.com", 21], ["www.charlotteobserver.com", 27], ["www.chs.ca", 12], ["www.esa.int", 15], ["www.anagrammer.com", 12], ["mybrands.com", 21], ["textsfromlastnight.com", 12], ["topics.nytimes.com", 12], ["www.godlikeproductions.com", 39], ["www.kesq.com", 15], ["buddypress.org", 18], ["www.apa.org", 27], ["www.thecarconnection.com", 12], ["www.kavx.org", 15], ["www.thewrestlingtalk.com", 21], ["wkzo.com", 12], ["www.baxterboo.com", 15], ["www.webmasterworld.com", 30], ["www.uu.edu", 15], ["www.ksl.com", 48], ["www.keezmovies.com", 18], ["reflections.mndigital.org", 12], ["www.germanshepherds.com", 12], ["www.criticaltool.com", 15], ["www.kiteforum.com", 24], ["www.blueridgenow.com", 36], ["www.xvideos.com", 15], ["www.bet.com", 18], ["www.pbteen.com", 24], ["www2b.abc.net.au", 21], ["kvpr.org", 12], ["www.as.utexas.edu", 15], ["autos.aol.com", 27], ["forums.gingerscraps.net", 24], ["www.homeenergy.org", 15], ["www.mrporter.com", 21], ["www.autoevolution.com", 15], ["numismaster.com", 15], ["reviews.cnet.com", 42], ["www.ebel.com", 21], ["www.ticketsnow.com", 15], ["themeforest.net", 39], ["www.gandermountain.com", 15], ["www.motortrend.com", 24], ["www.lyricsfreak.com", 24], ["www.opentable.com", 27], ["www.callingcards.com", 15], ["philadelphia.phillies.mlb.com", 12], ["www.stillen.com", 12], ["www.kwtx.com", 30], ["www.henle.de", 12], ["community.babycenter.com", 15], ["www.mmo-champion.com", 39], ["www.collectspace.com", 12], ["www.oesf.org", 27], ["www.eonline.com", 18], ["www.allaboutjazz.com", 15], ["www.apug.org", 33], ["espn.go.com", 42], ["knowyourmeme.com", 18], ["blog.nola.com", 15], ["www.philly.com", 21], ["www.tcm.com", 27], ["www.walmartstationery.com", 15], ["fedoraproject.org", 27], ["baseball.epicsports.com", 18], ["www.greenopia.com", 27], ["www.jbs.org", 12], ["www.toledoblade.com", 15], ["www.footballfanatics.com", 57], ["fortlauderdale.citysearch.com", 12], ["petoftheday.com", 12], ["www.local.com", 15], ["www.nbc.com", 18], ["www.easports.com", 12], ["www.oucs.ox.ac.uk", 18], ["www.directorio-foros.com", 51], ["www.bookrags.com", 36], ["www.lohud.com", 18], ["www.codeproject.com", 21], ["www.petstore.com", 15], ["imgv2-3.scribdassets.com", 30], ["www.newsplex.com", 21], ["www.neoseeker.com", 21], ["www.fourwheeler.com", 12], ["rcdb.com", 15], ["www.discgolfscene.com", 30], ["www.greatlakes4x4.com", 24], ["www.wsaz.com", 42], ["www.miashoes.com", 12], ["www.christianbook.com", 21], ["www.americantraveler.com", 12], ["www.leathercoatsetc.com", 24], ["www.boxingscene.com", 24], ["www.nasponline.org", 30], ["www.cfbstats.com", 27], ["m.mobango.com", 12], ["www.chicos.com", 18], ["www.flora2000.com", 12], ["www.carolinalive.com", 18], ["www.americanidol.com", 18], ["www.rhino3d.com", 21], ["www.lib.umd.edu", 15], ["www.fingertipformulary.com", 42], ["www.iboats.com", 15], ["www.crateandbarrel.com", 18], ["www.informationweek.com", 15], ["www.ridershack.com", 12], ["www.ebeanstalk.com", 18], ["www.m3post.com", 33], ["vimeo.com", 21], ["www.shangri-la.com", 12], ["pichunter.com", 18], ["www.aikiweb.com", 18], ["forum.arduino.cc", 36], ["shopper.cnet.com", 15], ["www.webmd.com", 18], ["www.tripadvisor.co.id", 57], ["www.steamboattoday.com", 12], ["www.searchquotes.com", 12], ["abcnews.go.com", 42], ["www.sportinglife.com", 15], ["www.h-online.com", 21], ["www.superiorpromos.com", 27], ["www.dailycandy.com", 12], ["www.icpsr.umich.edu", 36], ["www.sothebysrealty.com", 12], ["www.wikileaks.org", 12], ["www.gigmasters.com", 21], ["www.stonesthrow.com", 12], ["morrellwine.com", 15], ["archinte.jamanetwork.com", 12], ["www.concierge.com", 18], ["www.ilovebodykits.com", 21], ["godigitalscrapbooking.com", 12], ["www.genengnews.com", 18], ["www.petco.com", 39], ["www.gigapan.com", 18], ["www.supportforum.philips.com", 15], ["www.realself.com", 30], ["www.madthumbs.com", 18], ["www.webdeveloper.com", 18], ["www.parable.com", 24], ["www.pbreview.com", 21], ["www.nastygal.com", 18], ["www.saucony.com", 15], ["www.reverieworld.com", 12], ["menomonielibrary.org", 15], ["kbia.org", 12], ["www.stata.com", 18], ["www.psu.com", 33], ["www.thespoof.com", 12], ["openaccess.uoc.edu", 15], ["www.screendaily.com", 12], ["blogs.msdn.com", 24], ["www.splitcoaststampers.com", 12], ["www.erepublik.com", 12], ["www.musicradar.com", 12], ["www.indeed.com", 21], ["longisland.craigslist.org", 15], ["profile.yahoo.com", 12], ["www.howtoforge.com", 18], ["www.hydrogenaudio.org", 21], ["www.mpgear.com", 12], ["shop.jaguars.com", 15], ["www.kongregate.com", 24], ["www.compulsivepaintball.com", 18], ["www.beautybar.com", 15], ["www.thestar.com", 12], ["www.rockymountainatvmc.com", 27], ["gnome-look.org", 36], ["www.chiefsplanet.com", 51], ["www.match.com", 45], ["autos.jdpower.com", 24], ["www.faqs.org", 30], ["www.theatlantic.com", 21], ["workingperson.com", 12], ["www.americanstationery.com", 24], ["www.allstarpuzzles.com", 21], ["www.gamestop.com", 15], ["www.tradecardsonline.com", 24], ["www.tvguide.com", 36], ["digitalcollections.lmu.edu", 18], ["www.portlandoregon.gov", 12], ["www.wdaz.com", 18], ["www-947.ibm.com", 12], ["www.wellsphere.com", 21], ["www.animestuffstore.com", 15], ["boxrec.com", 18], ["imageshack.us", 12], ["www.paulfredrick.com", 21], ["en.wikipedia.org", 90], ["www.sportsbusinessdaily.com", 15], ["www.branders.com", 15], ["en.memory-alpha.org", 33], ["www.sonicelectronix.com", 15], ["www.antionline.com", 15], ["www.jegs.com", 12], ["digitalprairie.ok.gov", 15], ["cpansearch.perl.org", 18], ["www.somdnews.com", 18], ["www.lax.com", 12], ["www.tripadvisor.jp", 48], ["www.bulbs.com", 12], ["www.chess.com", 33], ["www.q1019.com", 12], ["digital.libraries.ou.edu", 12], ["www.fao.org", 12], ["www.karmaloop.com", 21], ["www.foxers.com", 15], ["www.aol.com", 27], ["www.midnightbsd.org", 21], ["www.amoeba.com", 21], ["www.whsv.com", 42], ["www.decoruniverse.com", 12], ["www.eastbay.com", 30], ["www.pro-football-reference.com", 27], ["www.keepsakequilting.com", 12], ["store.hbo.com", 12], ["www.gameinformer.com", 15], ["www.mybabypajamas.com", 12], ["www.catalystathletics.com", 18], ["www.royalacademy.org.uk", 12], ["www.bikepics.com", 15], ["www.crestock.com", 12], ["www.wdtkam.com", 12], ["www.villagevoice.com", 18], ["digital.houstonlibrary.org", 21], ["www.wwbw.com", 21], ["weheartit.com", 12], ["www.chefscatalog.com", 21], ["www.postersplease.com", 15], ["www.kraftrecipes.com", 15], ["www.lovefilm.com", 12], ["www.wben.com", 12], ["www.americascup.com", 12], ["www.wboy.com", 12], ["www.footlocker.com", 15], ["www.alldiscountbooks.net", 15], ["www.hardwarecentral.com", 12], ["www.justjared.com", 39], ["forums.wolfram.com", 21], ["www.impawards.com", 12], ["www.angolotesti.it", 18], ["www.seahawks.net", 15], ["www.pikenursery.com", 12], ["digital.lib.usu.edu", 12], ["www.inthefirstperson.com", 15], ["www.sidereel.com", 24], ["www.imore.com", 12], ["www.fanpop.com", 12], ["www.huskers.com", 15], ["www.stageagent.com", 18], ["dcls.org", 15], ["alt.com", 12], ["latimesblogs.latimes.com", 21], ["www.songsterr.com", 18], ["en.wikisource.org", 18], ["www.wsslfm.com", 12], ["www.oac.cdlib.org", 12], ["www.letsgodigital.org", 15], ["www.kiss1023.com", 18], ["www.network54.com", 24], ["www.parents.com", 18], ["www.kmov.com", 27], ["www.nautica.com", 15], ["www.wag.com", 36], ["www.uniprot.org", 12], ["www.portclintonnewsherald.com", 15], ["www.nexusmods.com", 12], ["www.slutload.com", 18], ["www.rochestercitynewspaper.com", 12], ["www.news.com.au", 18], ["www.imagebam.com", 27], ["www.mercedsunstar.com", 21], ["www.adn.com", 12], ["www.upi.com", 15], ["www.bizcommunity.com", 12], ["www.finestationery.com", 27], ["stoptazmo.com", 18], ["www.bhphotovideo.com", 24], ["www.footytube.com", 15], ["www.eventbrite.com", 21], ["www.mobiletechreview.com", 15], ["www.hotelanacapri.co.uk", 15], ["www.vogue.co.uk", 30], ["www.equinenow.com", 18], ["www.marinespecies.org", 18], ["us.levi.com", 12], ["www.commercialappeal.com", 18], ["www.dailysteals.com", 27], ["www.shaneco.com", 15], ["www.songkick.com", 18], ["www.discountmags.com", 24], ["www.scribd.com", 45], ["www.golfgalaxy.com", 15], ["saints.sqpn.com", 24], ["www.rentalhouses.com", 12], ["fpif.org", 15], ["www.gvsu.edu", 15], ["www.arkivverket.no", 12], ["www.urbandictionary.com", 51], ["www.tripadvisor.co.kr", 24], ["www.workwearexpress.com", 12], ["www.horsechannel.com", 15], ["www.grillstuff.com", 12], ["www.slideshare.net", 24], ["www.newkadia.com", 15], ["newboards.theonering.net", 27], ["www.macmillandictionary.com", 18], ["www.frenchtruckers.com", 39], ["www.1800flowers.com", 12], ["ux.stackexchange.com", 15], ["www.gocomics.com", 12], ["www.azfamily.com", 24], ["www.goodhousekeeping.com", 12], ["android.stackexchange.com", 24], ["stores.ebay.de", 12], ["penthouse.com", 27], ["www.textsfromlastnight.com", 15], ["portal.hud.gov", 21], ["www.theinthing.com", 51], ["www.risingsun4x4club.org", 12], ["www.naturallycurly.com", 24], ["marvel.com", 12], ["www.epicurious.com", 33], ["www.politico.com", 21], ["www.chiefscrowd.com", 18], ["lists.freebsd.org", 15], ["seattletimes.com", 12], ["www.thefrisky.com", 15], ["www.youngamerica.com", 12], ["shop.nordstrom.com", 39], ["www.catster.com", 21], ["www.amazon.com", 33], ["www.ticketstogo.com", 15], ["www.breitbart.com", 15], ["www.shutterstock.com", 15], ["www.seventeen.com", 12], ["www.discoverlife.org", 48], ["www.evike.com", 21], ["www.villarenaissance.com", 12], ["forums.poz.com", 18], ["www.espnscrum.com", 15], ["lumberjocks.com", 18], ["www.simplyhired.com", 24], ["www.ticketliquidator.com", 30], ["www.telegraph.co.uk", 12], ["www.homeaway.com", 39], ["www.photoshelter.com", 12], ["slowfood.com", 15], ["secure.numismaster.com", 12], ["www.adforum.com", 15], ["www.badcock.com", 30], ["eur-lex.europa.eu", 15], ["www.redenvelope.com", 15], ["www.heraldonline.com", 15], ["www.hockeyfights.com", 33], ["www.hoopsstats.com", 24], ["openjurist.org", 39], ["snipplr.com", 12], ["www.n-styleid.com", 12], ["video.foxnews.com", 15], ["www.thomann.de", 12], ["philpapers.org", 15], ["www.columbian.com", 15], ["bigcharts.marketwatch.com", 18], ["www.sparkpeople.com", 33], ["www.twopeasinabucket.com", 12], ["www.max1063.com", 15], ["www.uncommongoods.com", 18], ["www.complex.com", 21], ["www.jimcarreyonline.com", 12], ["www.backcountry.com", 15], ["www.floridabar.org", 12], ["www.travellerspoint.com", 24], ["www.fisher-price.com", 12], ["apothica.com", 12], ["forums.qj.net", 15], ["articles.timesofindia.indiatimes.com", 12], ["lists.debian.org", 48], ["www.citysearch.com", 39], ["steamcommunity.com", 27], ["www.glamsham.com", 24], ["seatgeek.com", 39], ["www.donnadowney.com", 12], ["blade.nagaokaut.ac.jp", 12], ["extensions.joomla.org", 12], ["www.zumiez.com", 18], ["www.latimes.com", 24], ["www.avira.com", 24], ["www.jinx.com", 27], ["www.axiomaudio.com", 15], ["tvtropes.org", 57], ["www.quiltersclubofamerica.com", 21], ["www.change.org", 15], ["www.courierpress.com", 18], ["www.economist.com", 15], ["www.filehippo.com", 27], ["www.poughkeepsiejournal.com", 18], ["www.advrider.com", 36], ["www.opticsinfobase.org", 21], ["www.tripadvisor.cl", 39], ["xhamster.com", 18], ["groups.yahoo.com", 36], ["www.timeanddate.com", 30], ["www.nasdaq.com", 15], ["www.stlyrics.com", 27], ["www.agweb.com", 15], ["use.perl.org", 12], ["www.q102.com", 18], ["www.theoaklandpress.com", 18], ["www.cricutholiday.com", 15], ["docwiki.cisco.com", 21], ["www.marconews.com", 24], ["www.uefa.com", 24], ["www.jwpepper.com", 15], ["www.dumb.com", 12], ["www.jigidi.com", 21], ["www.hindustantimes.com", 33], ["www.pocket-lint.com", 18], ["espnfc.com", 57], ["www.phoenixnewtimes.com", 15], ["www.xwordinfo.com", 24], ["wow.joystiq.com", 24], ["www.teva.com", 24], ["news.bbc.co.uk", 36], ["id.loc.gov", 12], ["www.modnique.com", 18], ["www.champssports.com", 24], ["www.ifood.tv", 12], ["www.igougo.com", 24], ["www.burton.com", 27], ["www.goantiques.com", 15], ["www.autotrader.com", 24], ["www.fatwallet.com", 24], ["www.neopets.com", 12], ["www.indystar.com", 15], ["wncw.org", 12], ["www.sencha.com", 24], ["www.ritzcamera.com", 39], ["www.wowinterface.com", 21], ["www.rememberthemilk.com", 33], ["www.cvm.okstate.edu", 24], ["techreport.com", 42], ["www.outdoorresearch.com", 12], ["sewing.patternreview.com", 27], ["www.psxextreme.com", 18], ["www.football365.com", 21], ["www.brandsmartusa.com", 18], ["www.cymax.com", 78], ["www.jdsupra.com", 12], ["coolglow.com", 12], ["www.bbq-brethren.com", 39], ["www.connectionnewspapers.com", 12], ["www.theregister.co.uk", 57], ["www.wayfair.com", 24], ["www.peekyou.com", 12], ["fixunix.com", 33], ["www.nolo.com", 18], ["www.androidcentral.com", 15], ["soundcloud.com", 36], ["researchspace.csir.co.za", 12], ["www.urban-rivals.com", 21], ["www.betterphoto.com", 21], ["upcommons.upc.edu", 15], ["www.ticketnetwork.com", 15], ["www.mensunderwearstore.com", 12], ["www.ents24.com", 15], ["www.paysonroundup.com", 12], ["msdn.microsoft.com", 15], ["rubygems.org", 12], ["www.jango.com", 18], ["whc.unesco.org", 15], ["www.mangareader.net", 27], ["www.avsforum.com", 15], ["www.rcgroups.com", 24], ["archive.org", 21], ["www.neoshodailynews.com", 12], ["gigaom.com", 33], ["evpl.org", 15], ["www.expedia.com", 24], ["www.pacersdigest.com", 15], ["www.clubzone.com", 15], ["www.salisburypost.com", 39], ["www.smarthome.com", 21], ["quotationsbook.com", 18], ["www.rent.com", 21], ["www.dailytech.com", 15], ["www.unesco.org", 12], ["www.deviantclip.com", 18], ["www.crystalcruises.com", 12], ["www.foodily.com", 18], ["www.cartographersguild.com", 12], ["wordpress.org", 33], ["windows.microsoft.com", 18], ["www.insidehoops.com", 36], ["www.collegesportingnews.com", 12], ["www.zanesvilletimesrecorder.com", 18], ["www.createforless.com", 21], ["newyork.mets.mlb.com", 12], ["www.woot.com", 12], ["www.sportsfanfare.com", 12], ["www.utah.com", 24], ["www.buzzfeed.com", 15], ["forum.ubuntu-fr.org", 18], ["www.itv.com", 12], ["www.ticketstub.com", 18], ["www.cduniverse.com", 18], ["core.trac.wordpress.org", 15], ["uncyclopedia.wikia.com", 33], ["www.bowhuntingoutlet.com", 18], ["www.wdsu.com", 18], ["fineartamerica.com", 15], ["www.peta.org", 18], ["www.hindu.com", 12], ["www.brookstone.com", 18], ["www.coderanch.com", 24], ["pgfoundry.org", 12], ["www.coldwatercreek.com", 24], ["joannagoddard.blogspot.com", 15], ["www.thepartyworks.com", 30], ["www.stumbleupon.com", 18], ["www.winestuff.com", 12], ["www.rockport.com", 12], ["www.mexicoledger.com", 12], ["www.jimmybeanswool.com", 21], ["annals.org", 15], ["www.allthingschristmas.com", 18], ["obits.dignitymemorial.com", 21], ["pubchem.ncbi.nlm.nih.gov", 24], ["www.grandtheftwiki.com", 30], ["hoopshype.com", 12], ["www.e90post.com", 30], ["www.icc.illinois.gov", 15], ["www.visaliatimesdelta.com", 15], ["www.groworganic.com", 18], ["www.swinglifestyle.com", 21], ["www.couplesseduceteens.com", 18], ["blogs.telegraph.co.uk", 12], ["www.partycity.com", 15], ["www.gamezone.com", 24], ["www.orangemane.com", 30], ["ibnlive.in.com", 12], ["www.turbosquid.com", 18], ["www.duluthnewstribune.com", 15], ["www.hotwire.com", 15], ["www.hamradio.com", 15], ["animaldiversity.ummz.umich.edu", 24], ["www.aliexpress.com", 24], ["stackoverflow.com", 36], ["www.indianasnewscenter.com", 12], ["www.warcraftrealms.com", 18], ["www.gocreighton.com", 21], ["www.conservativeunderground.com", 24], ["www.tripadvisor.com.sg", 24], ["www.a2zdiscountvitamins.com", 12], ["www.footballamerica.com", 12], ["www.californiasportscards.com", 18], ["www.hardwarezone.com", 12], ["www.kent.edu", 15], ["www.progarchives.com", 12], ["www.heraldnet.com", 24], ["www.remax.com", 15], ["www.capetown.travel", 18], ["lookbook.nu", 36], ["www.wineaccess.com", 12], ["guesskids.guess.com", 15], ["www.dexknows.com", 18], ["www2.ed.gov", 18], ["topsy.com", 27], ["www.ikea.com", 33], ["www.astro.com", 21], ["www.cabelas.com", 39], ["www.ebay.com", 54], ["new.livestream.com", 12], ["www.gurufocus.com", 27], ["www.fortwaynehomepage.net", 15], ["www.nbcsandiego.com", 12], ["www.travelblog.org", 15], ["www.evanscycles.com", 15], ["games.espn.go.com", 39], ["www.ft.com", 21], ["www.hotel-zandbergen.com", 18], ["www.remodelista.com", 15], ["www.seatwave.com", 12], ["psx-scene.com", 18], ["www.naplesnews.com", 27], ["www.rawlingsgear.com", 30], ["www.mangashare.com", 24], ["www.bbc.co.uk", 33], ["www.ask.com", 24], ["www.4029tv.com", 15], ["blog.gaiam.com", 12], ["freepages.genealogy.rootsweb.ancestry.com", 30], ["www.cadence.com", 15], ["www.lpga.com", 24], ["www.star-board.com", 12], ["forums.appleinsider.com", 12], ["www.worldarchitecturenews.com", 12], ["www.tigerdroppings.com", 57], ["www.flysaa.com", 12], ["www.tripadvisor.ru", 63], ["www.cafemom.com", 36], ["www.dailycamera.com", 18], ["papers.ssrn.com", 12], ["members.virtualtourist.com", 12], ["audiojungle.net", 36], ["www.janieandjack.com", 12], ["prospect.org", 12], ["www.airliners.net", 15], ["www.quiltingboard.com", 18], ["www.testfreaks.com", 27], ["www.experienceproject.com", 21], ["dribbble.com", 12], ["www.starwoodhotels.com", 36], ["www.gordonsjewelers.com", 21], ["www.bluesnews.com", 18], ["www.webstaurantstore.com", 12], ["www.chamilia.com", 33], ["cowboyszone.com", 12], ["www.faucet.com", 15], ["www.plummarket.com", 15], ["www.camaro5.com", 39], ["absolutepunk.net", 12], ["econsultancy.com", 27], ["blackamericaweb.com", 15], ["www.3balls.com", 18], ["www.nokia.com", 24], ["www.terrylove.com", 39], ["www.qcad.org", 12], ["de.wikipedia.org", 48], ["www.rockcreek.com", 30], ["www.johnlewis.com", 18], ["www.ndnation.com", 12], ["www.mobileread.com", 24], ["www.recipepuppy.com", 15], ["www.binnys.com", 12], ["www.fightingarts.com", 21], ["www.povada.com", 15], ["www.rpgnow.com", 24], ["www.lenconnect.com", 15], ["www.musiciansfriend.com", 39], ["www.wiichat.com", 30], ["www.defensereview.com", 18], ["hppr.org", 12], ["www.stjamesnews.com", 24], ["www.theguardian.com", 60], ["www.pandora.com", 45], ["www.babygaga.com", 18], ["www.dailypuppy.com", 12], ["www.vxb.com", 12], ["metaltabs.com", 18], ["www.pelican.com", 15], ["www.fleaflicker.com", 39], ["www.weau.com", 27], ["northtexascatholic.org", 27], ["www.nobleknight.com", 12], ["tv.swimmingworldmagazine.com", 18], ["www.eurogamer.net", 33], ["www.wkxa.com", 15], ["www.allfordmustangs.com", 18], ["www.lead411.com", 27], ["www.dancingfish.com", 18], ["www.crh.noaa.gov", 15], ["www.societyofrobots.com", 12], ["www.topspeed.com", 24], ["ru.wikipedia.org", 21], ["www.drdobbs.com", 15], ["www.dentistrytoday.com", 18], ["www.righthondaparts.com", 12], ["packages.debian.org", 30], ["content.lib.umt.edu", 21], ["www.annsummers.com", 12], ["www.bitpipe.com", 18], ["global.oup.com", 21], ["www.fes.follett.com", 21], ["www.autotraderclassics.com", 42], ["www.tripadvisor.com.ar", 27], ["www.gaiam.com", 12], ["www.chow.com", 21], ["www.fodors.com", 21], ["pokemon.wikia.com", 15], ["www.iherb.com", 45], ["www.wisn.com", 12], ["www.videobox.com", 12], ["flights.expedia.com", 21], ["www.buysellcommunity.com", 12], ["www.michaelkors.com", 36], ["www2.ljworld.com", 15], ["www.automotion.com", 12], ["www.driverside.com", 18], ["www.jordanfashions.com", 18], ["www.topozone.com", 12], ["www.gojacks.com", 12], ["gawker.com", 42], ["store.scrapbook.com", 27], ["www.comicbookresources.com", 12], ["gis.stackexchange.com", 15], ["translate.reference.com", 15], ["jp.iherb.com", 15], ["kanotix.com", 24], ["www.luther.edu", 24], ["www.harley-davidson.com", 36], ["www.dailypress.com", 15], ["forum.literotica.com", 12], ["www.centralr.com", 24], ["investing.businessweek.com", 12], ["www.astrology.com", 21], ["newyork.yankees.mlb.com", 12], ["www.slpl.org", 15], ["www.ps3news.com", 21], ["www.nowpublic.com", 15], ["www.thenewsstar.com", 12], ["www.funnyordie.com", 18], ["triptych.brynmawr.edu", 18], ["www.sciencedaily.com", 15], ["www.chicagotribune.com", 18], ["www.eders.com", 12], ["www.mousewait.com", 24], ["www.heartlandamerica.com", 18], ["sacmag.com", 15], ["www.boxingforum24.com", 39], ["www.butlercountytimesgazette.com", 27], ["www.bendbulletin.com", 24], ["www.farmallcub.com", 18], ["www.misssixty.com", 15], ["www.clemsontigers.com", 12], ["www.census.gov", 30], ["filehippo.com", 12], ["dblp.uni-trier.de", 15], ["www.americanhunter.org", 12], ["www.hotels.com", 27], ["www.seattlepi.com", 15], ["www.nanettelepore.com", 15], ["www.1160wccs.com", 12], ["www.fibaeurope.com", 15], ["wikitravel.org", 15], ["www.zulily.com", 54], ["www.burlingtoncoatfactory.com", 12], ["www.wadenastatebank.com", 12], ["www.4tube.com", 18], ["www.famousfootwear.com", 27], ["www.offspring.com", 12], ["www.surfride.com", 30], ["www.potterybarnkids.com", 21], ["www.animeonline.net", 24], ["onlinelibrary.wiley.com", 15], ["www.gosanangelo.com", 24], ["www.smogon.com", 21], ["tt.tennis-warehouse.com", 36], ["www.tube8.com", 21], ["www.katespade.com", 15], ["www.technologyevaluation.com", 12], ["dealspl.us", 24], ["www.undergear.com", 24], ["www.isme.com", 18], ["www.kirklands.com", 12], ["www.travelwisconsin.com", 24], ["www.blogtalkradio.com", 30], ["www.unionleader.com", 18], ["www.bonhams.com", 12], ["www.autoanything.com", 18], ["www.superpages.com", 27], ["www.ticketsolutions.com", 15], ["www.wjmt.com", 30], ["commons.wikimedia.org", 30], ["www.fudzilla.com", 15], ["www.stubhub.com", 12], ["www.draftexpress.com", 18], ["www.basspro.com", 36], ["www.flightstats.com", 12], ["www.fannation.com", 33], ["lists.w3.org", 33], ["www.twylah.com", 18], ["www.eetimes.com", 33], ["appleinsider.com", 12], ["www.collectorsweekly.com", 15], ["www.trftimes.com", 12], ["www.mynewplace.com", 15], ["www.beliefnet.com", 33], ["www.peoplefinders.com", 15], ["www.spc.noaa.gov", 12], ["www.repairclinic.com", 18], ["www.thingsremembered.com", 27], ["www.ancientfaces.com", 21], ["serverfault.com", 51], ["www.thinkadvisor.com", 15], ["www.theroyalforums.com", 18], ["msmvps.com", 12], ["fueleconomy.gov", 12], ["www.hot983.com", 12], ["digital.lib.csus.edu", 15], ["www.sheplers.com", 33], ["cl-user.net", 15], ["www.bmwmoa.org", 18], ["www.oxfamamerica.org", 21], ["www.us.elsevierhealth.com", 12], ["searchenginewatch.com", 12], ["www.prosportsblogging.com", 12], ["www.heraldscotland.com", 18], ["epic.awi.de", 12], ["blog.sockdreams.com", 15], ["www.tripadvisor.com.br", 30], ["www.quickship.com", 18], ["www.temptalia.com", 15], ["hollywoodlife.com", 15], ["www.golfdiscount.com", 30], ["www.stb.dot.gov", 12], ["www.nps.gov", 18], ["www.theclevelandfan.com", 18], ["www.computervalley.ca", 12], ["www.acefitness.org", 12], ["www.jostens.com", 12], ["cdm16373.contentdm.oclc.org", 18], ["www.notebookforums.com", 18], ["www.hostelworld.com", 27], ["mail-archives.apache.org", 78], ["www.myfoxphilly.com", 15], ["www.belk.com", 18], ["www.beadingdaily.com", 15], ["www.miamiherald.com", 15], ["articles.latimes.com", 27], ["www.justin.tv", 21], ["fantasynews.cbssports.com", 30], ["bangordailynews.com", 27], ["www.gotgayporn.com", 21], ["www.rock1053.com", 15], ["www.digitalscrapbookingstudio.com", 21], ["www.doggiefood.com", 12], ["social.ford.com", 21], ["gizmodo.com", 39], ["farmprogress.com", 12], ["www.nmnathletics.com", 12], ["www.ilr.cornell.edu", 12], ["www.topix.net", 24], ["www.mcul.org", 24], ["www.metalsetlists.com", 30], ["www.appliancesconnection.com", 12], ["www.spoonflower.com", 12], ["www.partstrain.com", 15], ["it.wikipedia.org", 27], ["nypost.com", 18], ["hfboards.hockeysfuture.com", 15], ["www.thelimited.com", 12], ["www.mmm-online.com", 12], ["www.meijer.com", 54], ["www.starpulse.com", 15], ["www.indyweek.com", 15], ["www.rvguide.com", 21], ["www.absolutepunk.net", 36], ["www.nsbobserver.com", 15], ["www.theouthousers.com", 24], ["www.irishcentral.com", 18], ["www.yachtworld.com", 36], ["gray.ftp.clickability.com", 15], ["www.wowwiki.com", 24], ["www.wunderground.com", 15], ["worthplaying.com", 15], ["cakecentral.com", 18], ["www.epromos.com", 27], ["www.dailyrecord.com", 15], ["www.adsglobe.com", 21], ["www.sing365.com", 12], ["www.kohls.com", 45], ["www.bradsdeals.com", 15], ["www.katu.com", 12], ["csbj.com", 12], ["content.library.ccsu.edu", 12], ["www.uclabruins.com", 21], ["www.wjla.com", 12], ["www.soccergarage.com", 18], ["www.betterworldbooks.com", 42], ["docs.oracle.com", 15], ["www.csmonitor.com", 24], ["www.greatschools.org", 45], ["www.cruisereviews.com", 12], ["www.active.com", 12], ["www.tropicalfishkeeping.com", 18], ["lkml.org", 12], ["www.rockband.com", 30], ["www.christianpost.com", 15], ["www.birthdayinabox.com", 15], ["www.walb.com", 12], ["hvac-talk.com", 21], ["www.fandom.com", 21], ["www.blowoutcards.com", 48], ["www.centerforinquiry.net", 12], ["www.kvue.com", 15], ["www.blackbearsportinggoods.com", 12], ["www.getbig.com", 21], ["www.rockclimbing.com", 33], ["www.greatrentals.com", 15], ["www.scoop.it", 24], ["www.gemplers.com", 15], ["www.gotickets.com", 18], ["www.silive.com", 12], ["www.hasbro.com", 12], ["www.appliancefactoryparts.com", 21], ["www.timesunion.com", 18], ["www.ajmadison.com", 27], ["phys.org", 12], ["www.middletowntranscript.com", 12], ["www.freesound.org", 18], ["wizzair.com", 21], ["common-lisp.net", 15], ["www.tvszone.com", 15], ["ec.europa.eu", 15], ["thechive.com", 30], ["po.st", 69], ["www.jetsinsider.com", 21], ["rep-am.com", 12], ["www.dogfunk.com", 18], ["store.nascar.com", 12], ["www.freshpair.com", 12], ["th.tripadvisor.com", 24], ["www.lancome-usa.com", 21], ["www.figurerealm.com", 12], ["www.ndbc.noaa.gov", 12], ["www.tripadvisor.de", 21], ["www.fastcompany.com", 15], ["www.partsgeek.com", 24], ["twitpic.com", 15], ["www.jeepgarage.org", 36], ["www.adpost.com", 21], ["www.ancestry.com", 12], ["live.wsj.com", 12], ["office.microsoft.com", 12], ["www.barewalls.com", 27], ["shop.lululemon.com", 12], ["wapc.mlb.com", 108], ["www.1043myfm.com", 18], ["forums.linuxmint.com", 12], ["www.grandforksherald.com", 21], ["www.reading.org", 36], ["video.tvguide.com", 15], ["www.wired.com", 27], ["www.news8000.com", 15], ["www.cokesbury.com", 27], ["www.dell.com", 15], ["www.animegalleries.net", 18], ["www.imdb.com", 42], ["www.magicalmemories.com", 15], ["www.animevice.com", 15], ["www.acehardware.com", 12], ["www.dxzone.com", 15], ["www.pitchup.com", 12], ["www.phonearena.com", 21], ["www.uncwsports.com", 12], ["www.ray-ban.com", 27], ["condor.cmich.edu", 15], ["www.tampabay.com", 12], ["www.ratebeer.com", 48], ["www.pexsupply.com", 18], ["www.jcplin.org", 15], ["steepster.com", 21], ["yourdailyglobe.com", 15], ["www.graffitipink.com", 21], ["www.ooga-mooga.com", 24], ["www.egms.de", 15], ["club.dx.com", 15], ["www.mondebio.com", 15], ["imgfave.com", 12], ["townhall.com", 33], ["photos.nextdaypets.com", 21], ["www.ballet-dance.com", 12], ["www.healthypeople.gov", 15], ["www.socialexplorer.com", 12], ["www.flycell.com", 12], ["www.sanuk.com", 18], ["health.usnews.com", 12], ["mypinkfriday.com", 12], ["www.companycasuals.com", 36], ["www.copiersupplystore.com", 15], ["www.care2.com", 15], ["www.forrent.com", 12], ["www.fotothing.com", 30], ["www.jiskha.com", 24], ["www.rustyzipper.com", 12], ["www.businessinsider.com", 18], ["www.goodanime.net", 12], ["www.yoox.com", 30], ["www.dafont.com", 36], ["projects.propublica.org", 24], ["www.statto.com", 15], ["www.cheatsguru.com", 12], ["www.sporcle.com", 30], ["www.wizards.com", 12], ["www.myxer.com", 15], ["gtaforums.com", 21], ["www.photopost.com", 18], ["www.snowboardingforum.com", 33], ["www.gop.gov", 12], ["www.wcnc.com", 30], ["www.beau-coup.com", 27], ["us.strawberrynet.com", 15], ["www.avvo.com", 36], ["www.skysports.com", 15], ["www.catholicculture.org", 12], ["www.biblestudytools.com", 45], ["www.biodiversitylibrary.org", 12], ["www.wtsp.com", 12], ["www.ctnow.com", 27], ["www.forgetaway.com", 24], ["www.slidetoplay.com", 21], ["www.tikiroom.com", 15], ["www.chictopia.com", 15], ["community.midwiferytoday.com", 39], ["tunein.com", 30], ["www.ubuycoffee.com", 12], ["www.myhometownnews.net", 21], ["www.art.com", 33], ["www.lib.utk.edu", 15], ["www.pcconnection.com", 21], ["www.foxbusiness.com", 15], ["wikileaks.org", 12], ["society6.com", 39], ["www.brownells.com", 39], ["www.aviationpros.com", 33], ["www.prweb.com", 24], ["www.bants.co.uk", 12], ["newsbiscuit.com", 12], ["www.spalook.com", 15], ["www.johnbarrowman.com", 12], ["www.floridatoday.com", 33], ["krwg.org", 12], ["oakland.athletics.mlb.com", 12], ["www.xtube.com", 15], ["thinkprogress.org", 18], ["philadelphia.cbslocal.com", 12], ["www.fazq.com", 12], ["www.appliancepartspros.com", 30], ["www.king5.com", 18], ["soccer.epicsports.com", 21], ["www.acemart.com", 15], ["goodquotes.com", 15], ["www.bhg.com", 18], ["www.knobsandhardware.com", 24], ["lifehacker.com", 30], ["web.stagram.com", 15], ["www.itickets.com", 15], ["devlicio.us", 27], ["jalopnik.com", 15], ["directory.fsf.org", 12], ["www.bikepartsexpress.com", 12], ["www.rentals.com", 15], ["www.biotechsciencenews.com", 15], ["linuxcentral.com", 18], ["www.projectwedding.com", 12], ["www.mdpi.com", 12], ["www.knittingdaily.com", 12], ["www.hannibal.net", 12], ["www.tmz.com", 15], ["www.homebrewtalk.com", 12], ["www.beatport.com", 12], ["www.partselect.com", 24], ["www.thomasnelson.com", 27], ["seavenger.com", 15], ["www.musica.com", 12], ["www.fold3.com", 18], ["www.competitivecyclist.com", 18], ["www.eastkingdom.org", 12], ["www.gpb.org", 15], ["www.peakbagger.com", 21], ["www.bohemian.com", 15], ["www.patsfans.com", 21], ["www.clickorlando.com", 15], ["www.shopmaclarenbaby.com", 30], ["recipes.sparkpeople.com", 54], ["www.filestube.to", 21], ["www.boatquest.com", 45], ["www.jmldirect.com", 24], ["payless.com", 12], ["www.puzzlewarehouse.com", 12], ["glocktalk.com", 15], ["www.opensource.apple.com", 21], ["www.pillsbury.com", 18], ["www.fsuniverse.net", 15], ["www.opticsplanet.com", 39], ["forums.gardenweb.com", 12], ["www.texanstalk.com", 45], ["pokedream.com", 15], ["www.virginia.org", 18], ["www.packersproshop.com", 33], ["www.esl.eu", 12], ["www.wellingtondailynews.com", 12], ["eol.org", 42], ["www.backstage.com", 12], ["meta.stackoverflow.com", 33], ["www.polyvore.com", 72], ["www.oyster.com", 36], ["online.wsj.com", 42], ["www.newportindependent.com", 18], ["www.gymsuedoise.com", 24], ["bendbulletin.com", 12], ["www.lastcall.com", 18], ["www.bollywoodlife.com", 12], ["www.denverpost.com", 21], ["www.youporn.com", 39], ["www.pokecommunity.com", 12], ["www.brightroam.com", 12], ["collegeprowler.com", 15], ["www.okcupid.com", 51], ["www.cnet.com", 27], ["www.xe.com", 18], ["athlonsports.com", 12], ["www.tampabaysmix.com", 12], ["www.sports-reference.com", 39], ["www.stonemountainhandbags.com", 30], ["www.wibw.com", 12], ["www.nobelcom.com", 21], ["images.archives.utah.gov", 12], ["www-03.ibm.com", 12], ["www.academy.com", 24], ["kde-look.org", 30], ["images.eurogamer.net", 18], ["www.sanparks.org", 18], ["www.quill.com", 18], ["www.openwetware.org", 18], ["www.canstockphoto.com", 18], ["www.slashgear.com", 12], ["www.persol.com", 12], ["www.law.cornell.edu", 36], ["www.gamerevolution.com", 24], ["www.diamondharmony.com", 18], ["www.bollywoodmantra.com", 12], ["www.flickr.com", 24], ["www.masslive.com", 21], ["www.dragtimes.com", 18], ["www.builderhouseplans.com", 75], ["www.redcrossblood.org", 12], ["uk.eurosport.yahoo.com", 18], ["www.automobilemag.com", 18], ["us.topman.com", 12], ["www.deccaclassics.com", 15], ["www.inforoo.com", 12], ["qna.rediff.com", 12], ["www.nhc.noaa.gov", 12], ["ccdl.libraries.claremont.edu", 12], ["www.wnyc.org", 12], ["dravesarchery.com", 15], ["europa.eu", 21], ["www.intellicast.com", 15], ["hu.wikipedia.org", 12], ["www.schooluniformshop.co.uk", 42], ["www.droidforums.net", 12], ["www.reference.com", 15], ["www.westmarine.com", 15], ["www.supercheats.com", 18], ["support.microsoft.com", 54], ["www.freep.com", 18], ["ilga.org", 24], ["www.pcadvisor.co.uk", 18], ["network.yardbarker.com", 21], ["www.roadbikereview.com", 15], ["contentdm.library.unr.edu", 12], ["www.pets.ca", 33], ["money.usnews.com", 12], ["www.wajk.com", 27], ["www.boxofficemojo.com", 30], ["www.etsy.com", 54], ["www.actionfigureinsider.com", 12], ["www.moultrienews.com", 30], ["www.kcra.com", 15], ["www.mountainhardwear.com", 15], ["tv.yahoo.com", 15], ["www.mysanantonio.com", 18], ["www.perfectplaces.com", 15], ["www.coldwellbanker.com", 24], ["www.nzherald.co.nz", 24], ["www.educationaltoysplanet.com", 24], ["washingtonexaminer.com", 24], ["www.harrypotterfanfiction.com", 18], ["www.the-scientist.com", 27], ["www.apunkachoice.com", 18], ["finance.yahoo.com", 21], ["collections.carli.illinois.edu", 39], ["www.oxforddictionaries.com", 18], ["www.azchords.com", 12], ["www.linux-archive.org", 15], ["www.blindsgalore.com", 21], ["www.wordwebonline.com", 12], ["www.longrangehunting.com", 12], ["www.quotesdaddy.com", 18], ["forums.animesuki.com", 21], ["www.ebay.co.uk", 18], ["www.myotcstore.com", 12], ["www.sirstevesguide.com", 21], ["www.movado.com", 15], ["www.delish.com", 12], ["www.infoplease.com", 39], ["en.forums.wordpress.com", 30], ["www.moddb.com", 30], ["www.tripadvisor.fr", 42], ["www.barneys.com", 15], ["calendars.com", 12], ["www.bullshido.net", 30], ["www.gettyimages.ae", 15], ["digilib.usm.edu", 12], ["starizona.com", 39], ["pubmedcentralcanada.ca", 12], ["www.valuetechdirect.com", 12], ["www.board-directory.net", 21], ["www.icis.com", 12], ["anythingbutipod.com", 12], ["nova.newcastle.edu.au", 12], ["www.haaretz.com", 21], ["www.cpan.org", 21], ["www.swell.com", 18], ["cherrybankguesthouse.com", 24], ["nyjetsfan.com", 12], ["shop.cbssports.com", 18], ["www.glocktalk.com", 18], ["www.tripadvisor.com.au", 84], ["skincarerx.com", 21], ["www.phonezoo.com", 24], ["www.dmoz.org", 24], ["freecode.com", 15], ["www.imagekind.com", 18], ["www.baseball-almanac.com", 15], ["www.stephenking.com", 21], ["pqasb.pqarchiver.com", 27], ["b9.sustatic.com", 15], ["www.abc.net.au", 18], ["www.dreamstime.com", 81], ["forums.prosportsdaily.com", 21], ["www.nakedapartments.com", 24], ["www.rhapsody.com", 33], ["meritbadge.org", 12], ["newsok.com", 51], ["content.wsulibs.wsu.edu", 12], ["www.interpol.int", 12], ["www.sitepoint.com", 39], ["www.musicnotes.com", 45], ["www.lyricsmode.com", 21], ["shopping.hp.com", 27], ["www.fmylife.com", 12], ["www.baseball-reference.com", 15], ["www.northernsun.com", 72], ["www.blockbuster.com", 12], ["www.footwearetc.com", 33], ["www.tripadvisor.ca", 57], ["www.cinewsnow.com", 12], ["www.modbee.com", 12], ["www.bowlingball.com", 15], ["www.touristlink.com", 12], ["www.godtube.com", 15], ["www.idahoptv.org", 21], ["www.basketball-reference.com", 21], ["cricketarchive.com", 12], ["www.bergdorfgoodman.com", 21], ["www.soccerway.com", 21], ["technet.microsoft.com", 24], ["www.3mwater.com", 12], ["www.unscramble.net", 12], ["www.grouprecipes.com", 12], ["www.anandtech.com", 24], ["www.littlewoods.com", 12], ["www.mlive.com", 27], ["www.hitfix.com", 15], ["www.sify.com", 12], ["clio.lib.olemiss.edu", 27], ["www.joystiq.com", 12], ["models.com", 15], ["www.anime-planet.com", 18], ["www.osceolanewsgazette.com", 18], ["www.comicvine.com", 24], ["www.sfstation.com", 36], ["www.genomeweb.com", 12], ["www.mychemicalromance.com", 12], ["www.kltv.com", 12], ["www.uidaho.edu", 12], ["www.audiosparx.com", 15], ["slickdeals.net", 21], ["shop.houstontexans.com", 12], ["www.kissfmseattle.com", 18], ["www.gettyimages.com.au", 18], ["www.haskell.org", 24], ["en.community.dell.com", 18], ["www.m-and-d.com", 12], ["letsgokings.com", 12], ["scitation.aip.org", 15], ["www.linuxformat.com", 12], ["www.trekbbs.com", 21], ["www.shapeways.com", 27], ["www.jigsawplanet.com", 18], ["digital.chipublib.org", 12], ["www.reelz.com", 12], ["www.mrlock.com", 33], ["www.toryburch.com", 48], ["www.z100radio.com", 15], ["www.tucows.com", 15], ["www.cnbc.com", 21], ["www.aggieathletics.com", 21], ["wisplants.uwsp.edu", 15], ["www.nbcnews.com", 15], ["www.biomedsearch.com", 15], ["www.big12sports.com", 24], ["orthodoxwiki.org", 39], ["www.nbcnewyork.com", 18], ["www.craftster.org", 33], ["sasquatchfest.proboards.com", 15], ["jobs.businessweek.com", 18], ["boards.giants.com", 27], ["rivals.yahoo.com", 36], ["www.calfloor.com", 12], ["www.iwsf.com", 12], ["www.automags.org", 12], ["pl.wikipedia.org", 15], ["www.homeplans.com", 12], ["www.phonescoop.com", 18], ["www.cbn.com", 24], ["www.barnesandnoble.com", 54], ["www.realadventures.com", 21], ["www.asos.com", 27], ["www.thelancet.com", 12], ["www.ritzcarlton.com", 12], ["www.mooncostumes.com", 15], ["www.harborfreight.com", 15], ["www.kansas.com", 15], ["www.poetrysoup.com", 33], ["www.bettafish.com", 15], ["imgv2-4.scribdassets.com", 27], ["www.crosswalk.com", 15], ["www.daz3d.com", 15], ["www.weeklystandard.com", 12], ["www.4shared.com", 18], ["www.wine.com", 18], ["www.shopbop.com", 42], ["www.uptontea.com", 12], ["www.ewrestlingnews.com", 33], ["always.ejwsites.net", 15], ["www.strategyinformer.com", 15], ["hackage.haskell.org", 24], ["www.gadventures.com", 24], ["community.active.com", 15], ["www.claryco.com", 12], ["www.govandals.com", 15], ["www.disboards.com", 18], ["www.kunsthaus.ch", 36], ["www.sportsnetwork.com", 18], ["www.retrievertraining.net", 15], ["doc.opalang.org", 15], ["www.newscancook.com", 18], ["www.mapquest.com", 27], ["www.lawnsite.com", 36], ["www.tsn.ca", 12], ["shop.mattel.com", 15], ["www.myfitnesspal.com", 21], ["www.myhighplains.com", 12], ["www.wiihacks.com", 39], ["www.hcn.org", 12], ["www.pennathletics.com", 15], ["www.vitals.com", 21], ["www.onegreatfamily.com", 15], ["www.lids.com", 27], ["imgv2-1.scribdassets.com", 21], ["patrick.net", 12], ["www.remains.com", 12], ["www.straightbourbon.com", 12], ["www.nfpa.org", 15], ["flyingdogales.com", 12], ["reviews.celebrateexpress.com", 21], ["money.cnn.com", 27], ["www.mmawarehouse.com", 18], ["www.myfonts.com", 21], ["www.slickcar.com", 12], ["www.bdtonline.com", 15], ["www.audible.com", 18], ["www.christiancentury.org", 12], ["blog.chron.com", 12], ["marylandpublicschools.org", 21], ["content.lib.washington.edu", 21], ["cemeteryscribes.com", 12], ["www.mass.gov", 15], ["www.pyramydair.com", 39], ["www.inforum.com", 18], ["www.xmfan.com", 15], ["www.mtv.com", 39], ["www.goduke.com", 12], ["www.ohio.com", 27], ["mpora.com", 21], ["www.texasmotorspeedway.com", 21], ["www.mixedmartialarts.com", 24], ["www.taftmidwaydriller.com", 12], ["www.bradfordexchange.com", 24], ["www.defensivecarry.com", 36], ["www.businessweek.com", 36], ["baseball.fantasysports.yahoo.com", 15], ["www.misterart.com", 21], ["careers.joelonsoftware.com", 12], ["www.4allvitamins.com", 21], ["www.rpmfind.net", 12], ["mathewsinc.com", 12], ["www.onthesnow.com", 39], ["www.nascar.com", 15], ["www.chinesemedicinetimes.com", 27], ["www.findagrave.com", 129], ["community.ceramicartsdaily.org", 21], ["www.fornobravo.com", 15], ["mlb.mlb.com", 12], ["nissannews.com", 15], ["www.doitbest.com", 18], ["www.loc.gov", 15], ["www.india-forums.com", 39], ["www.opensecrets.org", 72], ["www.orientaltrading.com", 12], ["www.metacritic.com", 39], ["www.metal-archives.com", 12], ["www.sportsauthority.com", 42], ["hypebeast.com", 21], ["www.weatherbase.com", 12], ["www.stuttgartdailyleader.com", 12], ["www.hendrickmotorsports.com", 12], ["stackexchange.com", 24], ["away.com", 12], ["basketballreference.com", 15], ["www.horseclicks.com", 18], ["www.conquerclub.com", 21], ["www.sharmusic.com", 12], ["www.onlineseats.com", 12], ["www.webcomicsnation.com", 12], ["www.randomhouse.com", 12], ["atlanta.citysearch.com", 15], ["www.worthingtondirect.com", 12], ["www.cricketweb.net", 18], ["www.thenewamerican.com", 12], ["www.moomba.com", 18], ["www.princeton.edu", 24], ["www.healthecareers.com", 15], ["www.walgreens.com", 27], ["www.whitehouseblackmarket.com", 15], ["fr.wikipedia.org", 15], ["estore.honda.com", 15], ["www.hotrodders.com", 36], ["www.andysautosport.com", 12], ["www.tripadvisor.com.eg", 30], ["www.craftsy.com", 57], ["www.fighthype.com", 24], ["www.brickshelf.com", 21], ["www.tripadvisor.nl", 54], ["www.century21.com", 36], ["www.abovetopsecret.com", 12], ["wonderwall.msn.com", 18], ["www.coachella.com", 27], ["www.superstock.com", 21], ["www.pcworld.com", 21], ["www2.census.gov", 12], ["www.emirates.com", 33], ["www.knittinghelp.com", 39], ["www.thecitizennews.com", 12], ["www.malesurvivor.org", 12], ["www.unicef.org", 12], ["distantcousin.com", 12], ["www.budsgunshop.com", 15], ["www.marksandspencer.com", 18], ["virtualglobetrotting.com", 12], ["publishing.cdlib.org", 12], ["www.synonym.com", 15], ["www.nfl.com", 12], ["commons.m.wikimedia.org", 15], ["www.confluence.org", 12], ["www.6pm.com", 39], ["www.sun-sentinel.com", 15], ["www.pier1.com", 12], ["blog.midtowncomics.com", 12], ["www.dailymail.co.uk", 18], ["www.exploretalent.com", 21], ["www.caraudio.com", 33], ["www.apartmentfinder.com", 18], ["harrypotter.wikia.com", 12], ["www.swellinfo.com", 27], ["www.cl-user.net", 15], ["www.movieguide.org", 12], ["openurl.ebscohost.com", 24], ["www.usa.canon.com", 15], ["www.campingworld.com", 36], ["rpg.drivethrustuff.com", 27], ["www.justusboys.com", 21], ["www.kingparsuperstore.com", 15], ["chroniclingamerica.loc.gov", 24], ["utah.com", 15], ["forums.superherohype.com", 18], ["www.vacationroost.com", 24], ["www.cubavera.com", 12], ["www.wtop.com", 27], ["www.wineexpress.com", 30], ["www.cappex.com", 18], ["www.baltimoresun.com", 15], ["www.lowcarbfriends.com", 48], ["samys.com", 15], ["www.1029thelake.com", 12], ["www.southcoast.com", 27], ["www.folica.com", 12], ["www.boosey.com", 15], ["comicbookdb.com", 15], ["www.go4expert.com", 15], ["kotaku.com", 24], ["www.dadamo.com", 12], ["www.brandeis.edu", 12], ["www.bigstockphoto.com", 48], ["www.debenhams.com", 15], ["manga.animea.net", 15], ["www.fresnobee.com", 12], ["shop.panasonic.com", 12], ["weightweenies.starbike.com", 15], ["blogs.wsj.com", 51], ["www.ableammo.com", 12], ["www.adultmatchdoctor.com", 30], ["www.barenecessities.com", 21], ["www.wrestlingforum.com", 27], ["www.sinclairintl.com", 15], ["www.the-athenaeum.org", 12], ["www.play.com", 18], ["www.rpgwatch.com", 15], ["www.fonts.com", 21], ["www.toysrus.com", 24], ["www.engadget.com", 39], ["www.cmt.com", 12], ["www.nataliemaclean.com", 21], ["www.gamershell.com", 24], ["marmot.com", 12], ["sports.yahoo.com", 18], ["www.shacknews.com", 24], ["www.dpreview.com", 42], ["www.reptilechannel.com", 12], ["www.biblegateway.com", 12], ["www.ocweekly.com", 12], ["www.michaels.com", 18], ["www.hattiesburgamerican.com", 12], ["forecast.weather.gov", 48], ["www.claires.com", 27], ["www.bobcatsplanet.com", 15], ["www.redorbit.com", 21], ["www.timbuk2.com", 21], ["www.k9power.com", 12], ["www.midamarhalal.com", 24], ["www.thefutoncritic.com", 15], ["www.eads.com", 12], ["www.dragoart.com", 12], ["www.moviepostershop.com", 15], ["www.autopartswarehouse.com", 12], ["www.yell.com", 12], ["www.hotnewhiphop.com", 21], ["ca.indeed.com", 12], ["www.cenelec.eu", 15], ["www.androidpit.com", 12], ["search.juneauempire.com", 12], ["www.threadless.com", 18], ["www.hvmag.com", 18], ["www.sandiegoreader.com", 27], ["ca.wikipedia.org", 12], ["www.sailnet.com", 39], ["www.forbes.com", 27], ["www.overstock.com", 15], ["www.cpa2biz.com", 12], ["www.mywedding.com", 15], ["emerica.com", 15], ["shop.mlb.com", 57], ["www.cruisecritic.com", 12], ["archives1.dags.hawaii.gov", 12], ["www.ntsb.gov", 12], ["ughh.com", 12], ["www.sperrytopsider.com", 15], ["www.jcwhitney.com", 12], ["www.contactmusic.com", 24], ["www.virtualsheetmusic.com", 12], ["www.bentgate.com", 15], ["www.newgrounds.com", 24], ["duepublico.uni-duisburg-essen.de", 12], ["www.yardbarker.com", 162], ["www.thenation.com", 12], ["www.vrbo.com", 12], ["www.transfermarkt.de", 15], ["www.gizmag.com", 18], ["www.charlierose.com", 21], ["www.peterglenn.com", 21], ["www.itu.int", 12], ["digital.library.unt.edu", 12], ["catherines.lanebryant.com", 27], ["www.adidas.com", 33], ["autos.yahoo.com", 15], ["www.library.illinois.edu", 18], ["www.motorsport.com", 42], ["vi.wikipedia.org", 12], ["gta.wikia.com", 15], ["www.mmanews.com", 15], ["www.midwayusa.com", 12], ["naruto.wikia.com", 12], ["www.allmodern.com", 12], ["investing.money.msn.com", 12], ["www.head-fi.org", 12], ["www.classicandsportscar.com", 15], ["www.autoblog.com", 15], ["www.northerntool.com", 24], ["mail.scipy.org", 18], ["entertainment.oneindia.in", 18], ["www.feedbooks.com", 18], ["my.liveireland.com", 15], ["www.codingforums.com", 24], ["www.neimanmarcus.com", 24], ["toolserver.org", 12], ["nameberry.com", 24], ["www.jeepforum.com", 27], ["www.lufthansa.com", 18], ["www.twellow.com", 15], ["www.rep-am.com", 15], ["www.comc.com", 18], ["www.amm.com", 21], ["www.audiomicro.com", 27], ["www.utsandiego.com", 39], ["www.ars.usda.gov", 15], ["www.mocpages.com", 36], ["www.kake.com", 33], ["www.thenewstribune.com", 12], ["www.lumberliquidators.com", 15], ["forum.realityfanforum.com", 33], ["www.superbiiz.com", 15], ["www.lakeshorelearning.com", 27], ["discsunlimited.net", 12], ["www.nbcwashington.com", 15], ["www.wowprogress.com", 45], ["global.rakuten.com", 15], ["www.birdchannel.com", 15], ["anabolicminds.com", 15], ["www.thetiebar.com", 12], ["www.cellartracker.com", 30], ["pittsburgh.citysearch.com", 12], ["www.comiccollectorlive.com", 18], ["www.smenet.org", 12], ["www.ebookmall.com", 12], ["www.vindy.com", 30], ["www.equine.com", 39], ["comments.startribune.com", 12], ["www.electronista.com", 12], ["kdl.kyvl.org", 36], ["www.harddrivesdirect.com", 24], ["www.aledotimesrecord.com", 12], ["www.nsopr.gov", 12], ["www.mtbr.com", 24], ["www.npr.org", 27], ["developer.cisco.com", 15], ["www.luckybrand.com", 12], ["www.wild955.com", 21], ["www.velocityreviews.com", 39], ["www.selectscience.net", 12], ["docs.joomla.org", 12], ["www.techrepublic.com", 15], ["www.bedbathandbeyond.com", 15], ["www.eastmans.com", 21], ["www.tripadvisor.dk", 24], ["animeonly.org", 21], ["www.powerstroke.org", 12], ["www.colorado.gov", 12], ["southnorfolkguesthouse.co.uk", 12], ["americanwoodworker.com", 15], ["www.gjsentinel.com", 12], ["lb.511.idaho.gov", 18], ["www.tripadvisor.com.gr", 27], ["shadowness.com", 15], ["abclocal.go.com", 15], ["pt.magicseaweed.com", 12], ["www.rightmove.co.uk", 15], ["www.cooking.com", 21], ["www.bedandbreakfast.com", 12], ["www.radioshack.com", 21], ["www.record-eagle.com", 12], ["www.infohub.com", 12], ["www.skateone.com", 21], ["www.acparadise.com", 21], ["www.yourpoolhq.com", 12], ["arstechnica.com", 18], ["www.w3.org", 18], ["dugi-doc.udg.edu", 12], ["www.mikasa.com", 15], ["www.polkaudio.com", 15], ["www.origene.com", 15], ["www.thebody.com", 18], ["www.google.es", 12], ["www.legacy.com", 54], ["store.diesel.com", 12], ["www.lajuntatribunedemocrat.com", 15], ["n4g.com", 12], ["blogs.trailblazers.com", 18], ["www.ihg.com", 15], ["jpgmag.com", 42], ["ps3trophies.com", 18], ["forums.theregister.co.uk", 24], ["durangoherald.com", 15], ["www.artsboston.org", 18], ["www.hondanews.com", 15], ["www.edmunds.com", 42], ["www.pacsun.com", 15], ["www.wvec.com", 18], ["www.wjjs.com", 15], ["nymag.com", 27], ["www.dogbedworks.com", 12], ["www.movietickets.com", 12], ["www.cruisemates.com", 21], ["www.advocate.com", 15], ["www.wsucougars.com", 21], ["www.freshairpro.com", 15], ["www.vg247.com", 12], ["coffeegeek.com", 18], ["www.senat.fr", 12], ["www.artnouveau-net.eu", 15], ["www.kidspot.com.au", 12], ["thefiringline.com", 33], ["www.thekansan.com", 15], ["www.umterps.com", 15], ["www.denpubs.com", 18], ["www.sheetmusicplus.com", 12], ["search.espn.go.com", 36], ["cboard.cprogramming.com", 30], ["www.diyaudio.com", 12], ["www.tennisforum.com", 27], ["www.pof.com", 27], ["www.recreation.gov", 12], ["www.newegg.com", 15], ["www.finishline.com", 27], ["www.saksfifthavenue.com", 21], ["flightaware.com", 24], ["www.tripadvisor.ie", 36], ["www.tripadvisor.in", 45], ["www.matrixgames.com", 24], ["sources.gentoo.org", 12], ["forums.androidcentral.com", 21], ["www.newsobserver.com", 12], ["freethoughtblogs.com", 12], ["www.healthgrades.com", 21], ["www.doggeekz.com", 15], ["cdm16313.contentdm.oclc.org", 12], ["www.wtok.com", 12], ["www.ungift.org", 15], ["www.marymaxim.com", 12], ["www.chillicothenews.com", 21], ["www.ssww.com", 30], ["www.summitpost.org", 33], ["www.frontpagemag.com", 15], ["reviews.cnet.co.uk", 12], ["www.goodreads.com", 27], ["www.usms.org", 12], ["www.thefirearmsforum.com", 15], ["www.linuxquestions.org", 33], ["wiki.openmoko.org", 15], ["www.cvs.com", 33], ["www.horseforum.com", 27], ["perezhilton.com", 33], ["www.ziprealty.com", 15], ["www.tennisw.com", 12], ["www.fleetfarm.com", 18], ["imgur.com", 54], ["courts.delaware.gov", 45], ["www.drummerworld.com", 18], ["sacramento.citysearch.com", 15], ["www.morewords.com", 12], ["www.fatsecret.com", 18], ["www.trocadero.com", 18], ["www.tinyprints.com", 21], ["www.julipa.com", 15], ["appshopper.com", 18], ["www.nileguide.com", 33], ["www.potterybarn.com", 21], ["www.happychefuniforms.com", 18], ["tennisopolis.com", 12], ["www.eviesays.com", 18], ["www.vanguardia.com", 12], ["www.anti.com", 12], ["digitalmedia.fws.gov", 12], ["www.gettyimages.com", 48], ["imgv2-2.scribdassets.com", 21], ["largomedical.com", 12], ["ex2.unixmanga.net", 15], ["www.talkbass.com", 24], ["kidshealth.org", 48], ["nh.craigslist.org", 12], ["www.enotes.com", 12], ["www.fosters.com", 12], ["www.theshoppingchannel.com", 18], ["shop.guess.com", 24], ["www.nespresso.com", 12], ["news.cnet.com", 27], ["www.extremeskins.com", 24], ["www.debian.org", 24], ["www.gnc.com", 21], ["www.soccerloco.com", 15], ["www.kandco.com", 12], ["www.cmuchippewas.com", 21], ["www.murrayscheese.com", 15], ["www.geograph.org.uk", 12], ["www.123rf.com", 33], ["www.press-citizen.com", 12], ["www.thisnext.com", 15], ["stocktwits.com", 15], ["www.1065thelake.com", 15], ["www.openstreetmap.org", 39], ["photobucket.com", 21], ["www.khou.com", 42], ["gay.porn.com", 12], ["www.smartpakequine.com", 21], ["www.giantbomb.com", 12], ["www.apartmenttherapy.com", 21], ["www.morningstar.com", 15], ["www.sermonaudio.com", 15], ["www.nzdl.org", 12], ["www.symantec.com", 30], ["www.plumbersurplus.com", 12], ["modmyi.com", 18], ["www.bible.is", 36], ["jezebel.com", 27], ["www.focusfanatics.com", 18], ["www.beloit.edu", 24], ["www.taltopia.com", 21], ["www.revolveclothing.com", 15], ["forum.naruto.viz.com", 15], ["cinematreasures.org", 21], ["forums.steelersfever.com", 30], ["blog.mlive.com", 15], ["www.buffalonews.com", 12], ["mangahelpers.com", 15], ["www.oprah.com", 18], ["www.thinkquest.org", 12], ["www.marriott.de", 12], ["www.bjs.com", 15], ["www.mothering.com", 30], ["www.deutschegrammophon.com", 18], ["www.factmonster.com", 12], ["www.carolinaguesthouse.co.uk", 12], ["www.mma-core.com", 15], ["www.futuresmag.com", 12], ["www.soma.com", 18], ["www.maxbimmer.com", 42], ["libn.com", 15], ["www.lulu.com", 27], ["idahoptv.org", 33], ["www.gilt.com", 36], ["seekingalpha.com", 33], ["www.werelate.org", 45], ["apidock.com", 12], ["www.merrell.com", 12], ["ideas.repec.org", 48], ["www.boston.com", 21], ["www.theverge.com", 18], ["www.nadaguides.com", 24], ["nycdwellers.com", 12], ["www.rl.tv", 12], ["pt.wikipedia.org", 15], ["www.finheaven.com", 12], ["www.smashwords.com", 18], ["adultfriendfinder.com", 27], ["www.desmoinesregister.com", 24], ["www.bcbg.com", 24], ["www.eventective.com", 21], ["www.energystar.gov", 21], ["www.wutang-corp.com", 36], ["mashable.com", 24], ["www.televisionwithoutpity.com", 12], ["www.seriouseats.com", 15], ["www.bio.net", 39], ["travel.aol.com", 27], ["www.bimmerboost.com", 21], ["kdhx.org", 18], ["feeds.feedburner.com", 12], ["www.movies.com", 21], ["www.sleepys.com", 15], ["www.hindawi.com", 33], ["merrick.library.miami.edu", 30], ["www.hbdirect.com", 15], ["profiles.wordpress.org", 12], ["imagesus.homeaway.com", 27], ["sportsillustrated.cnn.com", 54], ["www.mumsnet.com", 15], ["www.style.com", 12], ["www.promedxpress.com", 12], ["www.merriam-webster.com", 30], ["www1.skysports.com", 30], ["clinicaltrials.gov", 33], ["www.dbasupport.com", 15], ["disney.go.com", 15], ["www.mp3car.com", 39], ["www.dreamincode.net", 12], ["www.perlmonks.org", 12], ["manageyourcellar.com", 12], ["www.campaignlive.co.uk", 24], ["www.albawaba.com", 18], ["www.crosswordpuzzlehelp.net", 12], ["tolkiengateway.net", 30], ["www.auswaertiges-amt.de", 15], ["gcmd.nasa.gov", 15], ["sqlblog.com", 27], ["www.malleries.com", 15], ["www.abebooks.com", 18], ["www.justenergy.com", 12], ["www.territorioscuola.com", 15], ["www.imaging-resource.com", 12], ["moz.com", 12], ["www.wetpaint.com", 24], ["www.solarshop-europe.net", 36], ["www.kchistory.org", 18], ["www.clubwrx.net", 24], ["www.warrior.com", 12], ["forums.autosport.com", 15], ["www.vcstar.com", 33], ["www.brikwars.com", 18], ["www.ofertondelibros.com", 18], ["mcenter.slideshowpro.com", 18], ["apple.stackexchange.com", 30], ["www.dailymotion.com", 63], ["www.sheknows.com", 15], ["www.altrec.com", 24], ["advrider.com", 36], ["www.kitchen-cabinet-hardware.com", 15], ["search.cpan.org", 12], ["www.gq.com", 12], ["www.wwd.com", 36], ["www.diaperswappers.com", 27], ["lcweb2.loc.gov", 12], ["www.artnet.com", 33], ["www.tripadvisor.com.mx", 60], ["www.foodnetwork.com", 21], ["missoulanews.bigskypress.com", 12], ["www.diy.com", 12], ["www.artandculture.com", 12], ["tatoeba.org", 12], ["www.gardeners.com", 21], ["deals.woot.com", 12], ["www.talkphp.com", 24], ["www.cdc.gov", 45], ["www.wordnik.com", 24], ["nl.wikipedia.org", 15], ["www.cyclonefanatic.com", 42], ["thesaurus.com", 24], ["www.taylorandng.com", 12], ["www.rubylane.com", 39], ["www.teenink.com", 12], ["www.warcraftpets.com", 15], ["www.babysupermarket.com", 12], ["www.zoopla.co.uk", 18], ["www.tractorbynet.com", 27], ["www.designed2bsweet.com", 12], ["www.bikeforums.net", 24], ["yosemite.epa.gov", 27], ["www.classiccar.com", 18], ["www.royalyarns.com", 15], ["www.blancotogo.com", 18], ["www.architonic.com", 12], ["www.westsidewholesale.com", 18], ["www.booking.com", 36], ["lists.ansteorra.org", 21], ["www.wlup.com", 12], ["www.lightingshowplace.com", 12], ["www.sheetmusicstock.com", 12], ["www.cortezjournal.com", 27], ["www.biology-online.org", 12], ["hittrackeronline.com", 12], ["votesmart.org", 54], ["www.miaminewtimes.com", 12], ["www.nextdaypets.com", 15], ["www.marinij.com", 12], ["techcrunch.com", 24], ["www.usacycling.org", 18], ["www.ryanair.com", 12], ["okmagazine.com", 12], ["www.979kissfm.com", 12], ["stlouis.citysearch.com", 15], ["www.luxist.com", 18], ["www.plantedtank.net", 21], ["www.ladyfootlocker.com", 36], ["www.slowfood.com", 18], ["forums.nasioc.com", 15], ["www.burdastyle.com", 18], ["forums.codeguru.com", 21], ["docsouth.unc.edu", 15], ["www.knitrowan.com", 12], ["www.kffl.com", 30], ["illinois.edu", 18]]} --------------------------------------------------------------------------------