def search(self):
nyt = NYTAPI("wbWOIDwmGPWGQALhXbfC3BDK3EMtFBMA")
startDate = str(self.startDate) + " 00:00:00"
endDate = str(self.endDate) + " 23:59:59"
articles = nyt.article_search(
query="Covid",
results=10,
dates={
#"begin": datetime.datetime(2020, 6, 24),
#"end": datetime.datetime(2020, 6, 27)
"begin": datetime.strptime(startDate, '%Y-%m-%d %H:%M:%S'),
"end": datetime.strptime(endDate, '%Y-%m-%d %H:%M:%S')
},
options={
"sort":
"relevance",
"sources": [
"New York Times", "AP", "Reuters",
"International Herald Tribune"
],
"type_of_material": ["News"]
})
sorted_articles = sorted(
articles,
key=lambda x: datetime.strptime(x['pub_date'][0:10], '%Y-%m-%d'),
reverse=True)
for x in range(len(sorted_articles)):
sorted_articles[x]['pub_date'] = datetime.strptime(
sorted_articles[x]['pub_date'][0:10],
'%Y-%m-%d').strftime('%d-%b-%Y')
return sorted_articles
def search(self):
nyt = NYTAPI("wbWOIDwmGPWGQALhXbfC3BDK3EMtFBMA")
startDate = str(self.startDate) + " 00:00:00"
endDate = str(self.endDate) + " 23:59:59"
articles = nyt.article_search(
query="Covid",
results=10,
dates={
#"begin": datetime.datetime(2020, 6, 24),
#"end": datetime.datetime(2020, 6, 27)
"begin": datetime.datetime.strptime(startDate,
'%Y-%m-%d %H:%M:%S'),
"end": datetime.datetime.strptime(endDate, '%Y-%m-%d %H:%M:%S')
},
options={
"sort":
"relevance",
"sources": [
"New York Times", "AP", "Reuters",
"International Herald Tribune"
],
"type_of_material": ["News"]
})
return articles
nyt.top_stories(section="science")
nyt.most_viewed(days=30)
time.sleep(5)
nyt.most_shared(days=30, method="email")
nyt.book_reviews(author="Michelle Obama")
time.sleep(5)
nyt.best_sellers_lists()
nyt.best_sellers_list(date=datetime.datetime(2019, 1, 1),
name="hardcover-fiction")
time.sleep(5)
nyt.movie_reviews(keyword="FBI", options={"order": "by-opening-date"})
nyt.article_metadata(
url=
"https://www.nytimes.com/2019/10/20/world/middleeast/erdogan-turkey-nuclear-weapons-trump.html"
)
time.sleep(5)
nyt.tag_query("Pentagon", max_results=20)
nyt.archive_metadata(date=datetime.datetime(2019, 1, 1))
time.sleep(5)
nyt.article_search(query="Trump",
results=20,
dates={
"begin_date": datetime.datetime(2019, 1, 1),
"end_date": datetime.datetime(2019, 2, 1)
},
options={"sort": "oldest"})
end = datetime.datetime.now()
print(end - begin)
class TestNewYorkTimes(unittest.TestCase):
def setUp(self):
self.nyt = NYTAPI(API_KEY, parse_dates=True)
def tearDown(self):
self.nyt.close()
def test_empty_api_key(self):
with self.assertRaises(ValueError):
NYTAPI()
def test_top_stories(self):
top_stories = self.nyt.top_stories()
self.assertIsInstance(top_stories, list)
self.assertGreater(len(top_stories), 0)
for top_story in top_stories:
self.assertIsInstance(top_story, dict)
self.assertIsInstance(top_story["created_date"], datetime.datetime)
self.assertIsInstance(top_story["published_date"],
datetime.datetime)
def test_top_stories_section(self):
section = "world"
top_stories_section = self.nyt.top_stories(section=section)
self.assertIsInstance(top_stories_section, list)
self.assertGreater(len(top_stories_section), 0)
for top_story in top_stories_section:
self.assertIsInstance(top_story, dict)
def test_top_stories_wrong_section(self):
with self.assertRaises(ValueError):
self.nyt.top_stories("abcdfsda")
with self.assertRaises(TypeError):
self.nyt.top_stories(section=123)
def test_most_viewed(self):
most_viewed = self.nyt.most_viewed()
self.assertIsInstance(most_viewed, list)
self.assertGreater(len(most_viewed), 0)
for most in most_viewed:
self.assertIsInstance(most, dict)
self.assertIsInstance(most["media"], list)
def test_most_viewed_invalid_days(self):
with self.assertRaises(ValueError):
self.nyt.most_viewed(2)
with self.assertRaises(TypeError):
self.nyt.most_viewed(days="1")
def test_most_shared(self):
most_shared = self.nyt.most_shared()
self.assertIsInstance(most_shared, list)
self.assertGreater(len(most_shared), 0)
for most in most_shared:
self.assertIsInstance(most, dict)
self.assertIsInstance(most["published_date"], datetime.date)
self.assertIsInstance(most["updated"], datetime.datetime)
self.assertIsInstance(most["media"], list)
def test_most_shared_invalid(self):
with self.assertRaises(ValueError):
self.nyt.most_shared(method="twitter")
with self.assertRaises(ValueError):
self.nyt.most_shared(days=2)
with self.assertRaises(TypeError):
self.nyt.most_shared(days="2")
def test_book_reviews(self):
author = "Barack Obama"
book_reviews = self.nyt.book_reviews(author=author)
self.assertIsInstance(book_reviews, list)
self.assertGreater(len(book_reviews), 0)
for book_review in book_reviews:
self.assertIsInstance(book_review, dict)
self.assertEqual(book_review["book_author"], author)
def test_book_reviews_invalid(self):
with self.assertRaises(ValueError):
self.nyt.book_reviews()
with self.assertRaises(ValueError):
self.nyt.book_reviews(isbn=213789, author="author")
with self.assertRaises(ValueError):
self.nyt.book_reviews(isbn=213789)
def test_best_sellers_lists(self):
best_sellers_lists = self.nyt.best_sellers_lists()
self.assertIsInstance(best_sellers_lists, list)
self.assertGreater(len(best_sellers_lists), 0)
def test_best_seller_list(self):
best_seller_list = self.nyt.best_sellers_list(date=datetime.datetime(
2019, 1, 1),
name="hardcover-fiction")
self.assertIsInstance(best_seller_list, list)
self.assertEqual(best_seller_list[0]["primary_isbn13"],
"9780385544153")
def test_best_seller_list_invalid(self):
with self.assertRaises(ValueError):
self.nyt.best_sellers_list(name="not a name")
with self.assertRaises(TypeError):
self.nyt.best_sellers_list(date="123")
def test_movie_reviews(self):
movie_reviews = self.nyt.movie_reviews()
self.assertIsInstance(movie_reviews, list)
self.assertGreater(len(movie_reviews), 0)
for movie_review in movie_reviews:
self.assertIsInstance(movie_review, dict)
def test_movie_reviews_invalid(self):
with self.assertRaises(TypeError):
self.nyt.movie_reviews(keyword=123)
def test_article_metadata(self):
article_metadata = self.nyt.article_metadata(
"https://www.nytimes.com/live/2021/02/10/us/impeachment-trial/prosecutors-begin-arguments-against-trump-saying-he-became-the-inciter-in-chief-of-a-dangerous-insurrection"
)
self.assertIsInstance(article_metadata, list)
for article in article_metadata:
self.assertIsInstance(article, dict)
title = "Prosecutors argue that Trump ‘became the inciter in chief’ and retell riot with explicit video."
creation_datetime = datetime.datetime(
2021,
2,
10,
11,
4,
8,
tzinfo=datetime.timezone(datetime.timedelta(days=-1,
seconds=68400)),
)
self.assertEqual(article_metadata[0]["title"], title)
self.assertEqual(
article_metadata[0]["created_date"],
creation_datetime,
)
def test_article_metadata_invalid(self):
with self.assertRaises(TypeError):
self.nyt.article_metadata()
with self.assertRaises(TypeError):
self.nyt.article_metadata(123)
with self.assertRaises(ValueError):
self.nyt.article_metadata("text")
def test_archive_metadata(self):
archive_metadata = self.nyt.archive_metadata(
date=datetime.date.today())
self.assertIsInstance(archive_metadata, list)
self.assertGreater(len(archive_metadata), 0)
for metadata in archive_metadata:
self.assertIsInstance(metadata, dict)
self.assertGreaterEqual(
metadata["pub_date"],
datetime.datetime.now(tz=datetime.timezone.utc).replace(
day=1, hour=0, minute=0, second=0, microsecond=0),
)
def test_archive_metadata_invalid(self):
with self.assertRaises(TypeError):
self.nyt.archive_metadata("string")
with self.assertRaises(TypeError):
self.nyt.archive_metadata(123)
def test_article_search(self):
search = self.nyt.article_search("Joe Biden", results=80)
self.assertIsInstance(search, list)
self.assertEqual(80, len(search))
for article in search:
self.assertIsInstance(article, dict)
def test_article_search_invalid(self):
with self.assertRaises(TypeError):
self.nyt.article_search(123)
with self.assertRaises(TypeError):
self.nyt.article_search("query", datetime.date.today())
def test_section_list(self):
section_list = self.nyt.section_list()
self.assertIsInstance(section_list, list)
self.assertGreater(len(section_list), 0)
for section in section_list:
self.assertIsInstance(section, dict)
def test_latest_articles(self):
latest_articles = self.nyt.latest_articles()
self.assertIsInstance(latest_articles, list)
for article in latest_articles:
self.assertIsInstance(article, dict)
def test_latest_articles_invalid(self):
with self.assertRaises(TypeError):
self.nyt.latest_articles(source=123)
def test_tag_query(self):
tags = self.nyt.tag_query("Obama", max_results=2)
self.assertIsInstance(tags, list)
self.assertIs(2, len(tags))
def test_tag_query_invalid(self):
with self.assertRaises(TypeError):
self.nyt.tag_query(123)
with self.assertRaises(TypeError):
self.nyt.tag_query("Obama", max_results="2")
def test_parse_dates_disabled(self):
local_nyt = NYTAPI(API_KEY)
data = local_nyt.article_metadata(
"https://www.nytimes.com/live/2021/02/10/us/impeachment-trial/prosecutors-begin-arguments-against-trump-saying-he-became-the-inciter-in-chief-of-a-dangerous-insurrection"
)
self.assertEqual(data[0]["created_date"], "2021-02-10T11:04:08-05:00")
from pynytimes import NYTAPI
nyt = NYTAPI("YOUR_API_KEY")
articles = nyt.article_search(
"https://api.nytimes.com/svc/search/v2/articlesearch.json?fq=indigo&api-key=YOUR_API_KEY"
)
#print(articles)
news = []
for i in articles:
dic = {}
dic['url'] = i['web_url']
news.append(dic)
#print(news)
urls = []
for new in news:
for key, url in new.items():
urls.append(url)
for url in urls:
print(url)
# article :indigo
"""
https://www.nytimes.com/1889/07/14/archives/no-robbery.html
https://www.nytimes.com/1858/10/29/archives/central-america-crops-and-contracts-in-costa-ricathe-proposed.html
https://www.nytimes.com/1898/08/20/archives/reviews-of-books-dialect-tales-justly-praised.html
https://www.nytimes.com/1890/10/19/archives/anne-bissell.html
https://www.nytimes.com/1859/10/27/archives/european-news-the-jason-at-st-johns-further-by-the-persia-the-great.html
https://www.nytimes.com/1859/06/27/archives/from-the-pacific-coast-nicaragua-rejects-the-american-ultimatum.html
"""
import pandas as pd
nyt = NYTAPI("WxQXsVSaIIlTgEfG0VnrlP7JhOVYYL0j")
search="US Embassy move to Jerusalem"
start_date = datetime(2015, 1, 1)
end_date = datetime(2019, 12, 31)
articles = nyt.article_search(
query = search,
results = 50,
dates = {
"begin": start_date,
"end": end_date
},
options = {
"sort": "relevance",
"sources": [
"New York Times",
],
}
)
def clean(text):
return ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t]) | (\w+:\/\/\S+)", " ", text).split())
headlines = []
pub_dates = []
for article in articles:
headlines.append(article['headline']['main'])
from datetime import date, datetime
from pynytimes import NYTAPI
# Make sure to set parse dates to True so that the dates
# are parsed into datetime.datetime or datetime.date objects
nyt = NYTAPI(
key="Your API Key", # Get your API Key at https://developer.nytimes.com
parse_dates=True,
)
# Search articles about President Biden
biden = nyt.article_search("biden")
# You can optionally define the dates between which you want the articles to be
biden_january = nyt.article_search(query="biden",
dates={
"start": date(2021, 1, 1),
"end": date(2021, 1, 31)
})
# Optionally you can also define
biden = nyt.article_search("biden", )
