In [ ]:

    

import json
import requests

iss_url = 'http://api.open-notify.org/iss-now.json'

data = requests.get(iss_url).json()
print(json.dumps(data, indent=4))


    

In [ ]:

    

# Lattitude and Longitude of C'Ville
LAT = 38.0293
LON = 78.4767

iss_url = 'http://api.open-notify.org/iss-pass.json?lat={}&lon={}'.format(LAT, LON)

print(iss_url)


    

In [ ]:

    

data = requests.get(iss_url).json()
print(json.dumps(data, indent=4))


    

In [ ]:

    

import arrow


    

In [ ]:

    

from arrow.arrow import Arrow


for item in data['response']:
    datetime = Arrow.fromtimestamp(item['risetime'])
    print(
        'The ISS will be visable over Charlottesville on {} at {} for {} seconds.'.format(
            datetime.date(),
            datetime.time(),
            item['duration']
        )
    )


    

In [ ]:

    

pokeapi = 'http://pokeapi.co/api/v2/generation/1/'

pokedata = requests.get(pokeapi).json()

# Take that data, print out a nicely formatted version of the first 5 results
print(json.dumps(pokedata['pokemon_species'][:5], indent=4))


    

In [ ]:

    

# Let's get more info about the first pokemon on the list
# By following the chain of linked data

# Narrow down the url we'd like to get
bulbasaur_url = pokedata['pokemon_species'][0]['url']

# request data from that URL
bulbasaur_data = requests.get(bulbasaur_url).json()

# Let's remove the 'flavor text' because that's really long
del bulbasaur_data['flavor_text_entries']


    

In [ ]:

    

bulbasaur_data


    

In [ ]:

    

from furl import furl


vt_url = furl('http://vtechworks.lib.vt.edu/oai/request')


    

In [ ]:

    

vt_url.args['verb'] = 'ListRecords'
vt_url.args['metadataPrefix'] = 'oai_dc'

vt_url.url


    

In [ ]:

    

data = requests.get(vt_url.url)

data.content


    

In [ ]:

    

from lxml import etree

etree_element = etree.XML(data.content)

etree_element


    

In [ ]:

    

etree_element.getchildren()


    

In [ ]:

    

# A little namespace parsing and cleanup
namespaces = etree_element.nsmap
namespaces['ns0'] = etree_element.nsmap[None]
del namespaces[None]

records = etree_element.xpath('//ns0:record', namespaces=namespaces)

records[:10]


    

In [ ]:

    

# What's inside one of these records?
one_record = records[0]
one_record.getchildren()


    

In [ ]:

    

# We want to check out the "metadata" element, which is the second in the list
# Let's make sure to get those namespaces too
# Here's a cool trick to join 2 dictionaries in python 3!
namespaces = {**namespaces, **one_record[1][0].nsmap}
del namespaces[None]

# Now we have namespaces we can use!
namespaces


    

In [ ]:

    

# Use those namespaces to get titles
titles = records[0].xpath('//dc:title/node()', namespaces=namespaces)
titles[:10]


    

In [ ]:

    

SHARE_SEARCH_API = 'https://staging-share.osf.io/api/search/abstractcreativework/_search'


    

In [ ]:

    

from furl import furl

search_url = furl(SHARE_SEARCH_API)
search_url.args['size'] = 3
recent_results = requests.get(search_url.url).json()

recent_results = recent_results['hits']['hits']


    

In [ ]:

    

recent_results


    

In [ ]:

    

print('The request URL is {}'.format(search_url.url))
print('----------')
for result in recent_results:
    print(
        '{} -- from {}'.format(
            result['_source']['title'],
            result['_source']['sources']
        )
    )


    

In [ ]:

    

import json

def query_share(url, query):
    # A helper function that will use the requests library,
    # pass along the correct headers, and make the query we want

    headers = {'Content-Type': 'application/json'}
    data = json.dumps(query)
    return requests.post(url, headers=headers, data=data).json()


    

In [ ]:

    

search_url.args = None  # reset the args so that we remove our old query arguments.
search_url.url # Show the URL that we'll be requesting to make sure the args were cleared


    

In [ ]:

    

tags_query = {
    "query": {
        "exists": {
            "field": "tags"
        }
    }
}


missing_tags_query = {
    "query": {
        "bool": {
            "must_not": {
                "exists": {
                    "field": "tags"
                }
            }
        }      
    }
}


    

In [ ]:

    

with_tags = query_share(search_url.url, tags_query)
missing_tags = query_share(search_url.url, missing_tags_query)

total_results = requests.get(search_url.url).json()['hits']['total']

with_tags_percent = (float(with_tags['hits']['total'])/total_results)*100
missing_tags_percent = (float(missing_tags['hits']['total'])/total_results)*100


print(
    '{} results out of {}, or {}%, have tags.'.format(
        with_tags['hits']['total'],
        total_results,
        format(with_tags_percent, '.2f')
    )
)

print(
    '{} results out of {}, or {}%, do NOT have tags.'.format(
        missing_tags['hits']['total'],
        total_results,
        format(missing_tags_percent, '.2f')
    )
)

print('------------')
print('As a little sanity check....')
print('{} + {} = {}%'.format(with_tags_percent, missing_tags_percent, format(with_tags_percent + missing_tags_percent, '.2f')))


    

In [ ]:

    

SHARE_API = 'https://staging-share.osf.io/api/'


    

In [ ]:

    

share_endpoints = requests.get(SHARE_API).json()

share_endpoints


    

In [ ]:

    

SHARE_PROVIDERS = 'https://staging-share.osf.io/api/providers/'


    

In [ ]:

    

data = requests.get(SHARE_PROVIDERS).json()
 
data


    

In [ ]:

    

print('Here are the first 10 Providers:')
for source in data['results']:
    print(
        '{}\n{}\n{}\n'.format(
            source['long_title'],
            source['home_page'],
            source['provider_name']
        )
    )


    

In [ ]: