get_nyt_comments.py

import requests as r
import json
import datetime

# Docs: http://developer.nytimes.com/docs
# Try at: http://developer.nytimes.com/io-docs

srch_api_key = "Your key <check docs>"
keyphrase = 'anything_you_want'
srch_api_result = r.get("http://api.nytimes.com/svc/search/v2/articlesearch.json?q="+keyphrase+"&api-key="+srch_api_key)
hits = int(srch_api_result.json()["response"]["meta"]["hits"]) # first get related articles.

article_list = [] # The list of the articles
for p in range(int(hits/10)+1):
    srch_api_result = r.get("http://api.nytimes.com/svc/search/v2/articlesearch.json?q=rohingya&api-key="+srch_api_key+"&page="+str(p))
    article_list += srch_api_result.json()["response"]["docs"]
len(article_list) 
# An article contains the following fields:
# 'abstract', 'print_page', 'subsection_name', '_id', 'source', 'blog', 'byline', 'news_desk', 'headline', 'snippet', 
# 'keywords', 'multimedia', 'document_type', 'web_url', 'type_of_material', 'word_count', 'pub_date', 'lead_paragraph', 
# 'section_name', 'slideshow_credits'

article_dict = {}
for a in article_list:
    article_dict[a["_id"]] = a # duplicate articles will be represented just once in a dictionary which has the Article ID as key.

cmmnt_api_key = "Comment API key. It is different from the Search API key!"
cmmnts_dict = {}

for a_id, a in article_dict.items():
    cmmnt_api_result = r.get("http://api.nytimes.com/svc/community/v3/user-content/url.json?url="+a["web_url"]+"&api-key="+cmmnt_api_key)
    a["comments"] = cmmnt_api_result.json()["results"]["comments"]
    article_dict[a_id] = a # Each article ID will be associated with the comments of that article.