#!/usr/bin/env python
# coding: utf-8

# ---
# ## Let's now play with JSON to access **the NARA Catalog Morgenthau Diary** Vol.696: Jan. 22 - Jan. 26, 1944:
# ### - we use an API call where we specify a NARA fileUnit ID directly: 28277406
# ### - <https://catalog.archives.gov/api/v2/records/search?q=*&abbreviated=true&limit=200&naId=28277406>
# 
# 
# | <center>NARA Catalog Hierarchy</center> | <center>JSON Structure for the Query of FDR FileUnit 28277406:"The Morgenthau Diaries"</center> |
# | ----- | ----- |
# | <img src="Images/FU_hierarchy.png"/> | <img src="Images/FU.png"/> |

# In[22]:


import requests
import json

# Going down the JSON tree to the RESULT section:
response = requests.get("https://catalog.archives.gov/api/v2/records/search?q=*&abbreviated=true&limit=200&naId=28277406", 
                        headers={"Content-Type": "application/json", 
                                 "x-api-key": "API-KEY"})
data = response.json()
with open('data.FU.json', 'w') as f:
    json.dump(data, f)
    
result = data["body"]["hits"]["hits"][0]
fields = result["fields"]
record = result["_source"]["record"]

result


# ## How to extract the TITLE value from the JSON tree

# In[20]:


title_value = record["title"]

# Printing the Title Value
print( "- TITLE VALUE:", title_value )


# ## How to extract the URL value from the FILE section of the objects/object portion of the JSON tree

# In[27]:


# Going down to the fiole section of the objects/object portion of the JSON tree
object = fields["firstDigitalObject"][0]

# Grabbing the @url value
object_url = object["objectUrl"]
# We choose to print the URL key which will give us the location of the file
print( "- URL VALUE:", object_url)

# Grabbing the @name value
object_id = object["objecId"]
# Printing the name value
print( "- NAME VALUE:", object_id)


# ## ==> Follow the URL link and "GET" the actual .PDF file for the entire Morgenthau Diary for Volume 696 and download it locally

# In[29]:


# We then get that URL
r = requests.get(object_url, allow_redirects=True)

# and finally open and write the .PDF file
open('696.pdf', 'wb').write(r.content)


# In[ ]: