# using an example in the API documentation to confirm that we can get json representation from API

import requests
json_url = "http://opencontext.org/sets/Palestinian+Authority/Tell+en-Nasbeh/.json?proj=Bade+Museum"

r = requests.get(json_url)

# what are the top level keys of response?
r.json().keys()

# Now let's apply same logic to the Asian Stoneware Jars project

json_url = "http://opencontext.org/sets/.json?proj=Asian+Stoneware+Jars"

request = requests.get(json_url)
request_json = request.json()

results= request_json['results']


request_json.keys()

# number of results matches what is on human UI
request_json['numFound']

# we get back the first page of 10
len(results)

results[0]

# list the URLs for the thumbnails
[result.get('thumbIcon') for result in results]

# do a quick display

from IPython.display import HTML
from jinja2 import Template

CSS = """
<style>
  .wrap img {
    margin-left: 0px;
    margin-right: 0px;
    display: inline-block;
  }
</style>
"""

IMAGES_TEMPLATE = CSS + """
<div class="wrap">
 {% for item in items %}<img title="{{item.label}}" src="{{item.thumbIcon}}"/>{% endfor %}
</div>
"""
    
template = Template(IMAGES_TEMPLATE)
HTML(template.render(items=results)) 

import requests
url = "http://opencontext.org/sets/.json"

r = requests.get(url)
r.json().keys()

r.json()['numFound']

r.json()['paging']['prev']

# write a generator for all items in http://opencontext.org/sets/.json

import requests

def opencontext_items():
    
    url = "http://opencontext.org/sets/.json"
    more_items = True
    
    while more_items:
        r = requests.get(url)
        for item in r.json()['results']:
            yield item
    
        url = r.json()['paging']['next']
        if not url:
            more_items = False
                       

from itertools import islice
results = list(islice(opencontext_items(), 25))
HTML(template.render(items=results)) 

import requests
import lxml
from lxml import etree

url = "http://opencontext.org/projects/.atom"
r = requests.get(url)

doc = etree.fromstring(r.content)
doc

# get list of titles

project_titles = [e.find('{http://www.w3.org/2005/Atom}title').text for e in doc.findall('{http://www.w3.org/2005/Atom}entry')]
for (i, title) in enumerate(project_titles):
    print i+1, title