ValueError：dictにはif文でもフィールド名に含まれないフィールドが含まれています

Question

TimesのAPIを使用して「経済」という単語が含まれている2016年のNY Timesの記事をすべて取り込もうとしています。

はとValueErrorが

：

from nytimesarticle import articleAPI 
api = articleAPI('0282db2f333f4f4095edd19f0660c978') 

articles = api.search(q = 'economy', 
fq = {'headline':'economy', 'source':['Reuters','AP', 'The New 
YorkTimes']}, 
begin_date = 20151231) 

def parse_articles(articles): 

news = [] 
for i in articles['response']['docs']: 
    dic = {} 
    dic['id'] = i['_id'] 
if i['abstract'] is not None: 
     dic['abstract'] = i['abstract'].encode("utf8") 
    dic['headline'] = i['headline']['main'].encode("utf8") 
    dic['desk'] = i['news_desk'] 
    dic['date'] = i['pub_date'][0:10] # cutting time of day. 
    dic['section'] = i['section_name'] 
    if i['snippet'] is not None: 
     dic['snippet'] = i['snippet'].encode("utf8") 
    dic['source'] = i['source'] 
    dic['type'] = i['type_of_material'] 
    dic['url'] = i['web_url'] 
    dic['word_count'] = i['word_count'] 

    locations = [] 
    for x in range(0,len(i['keywords'])): 
     if 'glocations' in i['keywords'][x]['name']: 
      locations.append(i['keywords'][x]['value']) 
    dic['locations'] = locations 

    subjects = [] 
    for x in range(0,len(i['keywords'])): 
     if 'subject' in i['keywords'][x]['name']: 
      subjects.append(i['keywords'][x]['value']) 
    dic['subjects'] = subjects 
    news.append(dic) 
return(news) 

def get_articles(date,query): 

all_articles = [] 
for i in range(0,100): 
    articles = api.search(q = query, 
      fq = {'source':['Reuters','AP', 'The New York Times']}, 
      begin_date = 20151231, 
      end_date = 20160715, 
      sort='oldest', 
      page = str(i)) 
    articles = parse_articles(articles) 
    all_articles = all_articles + articles 
return(all_articles) 

econ_all = [] 
for i in range(2015,2016): 
print 'Processing' + str(i) + '...' 
econ_year = get_articles(str(i),'economy') 
econ_all = econ_all + econ_year 


import csv 
keys = econ_all[0].keys() 
with open('econ-mentions.csv', 'wb') as output_file: 

dict_writer = csv.DictWriter(output_file, keys) 
dict_writer.writeheader() 
dict_writer.writerows(econ_all) 

それは私の場合はそうです：dictのは、フィールド名でないフィールドが含まれています：「抽象」

そしてここでは私のコードで私は自分のコードの末尾に次のエラーメッセージが表示されますステートメントは、エラーを防ぐ必要があります。また、私が "writerow"を使用すると、ここで時々言及したように、CSVを作成せずに詳細のリスト全体を取得できます。どんな助けもありがとう！

Answer 1

あなたの問題は何か分かりませんが、このコードはコンテンツ付きのecon-mentions.csvファイルを作成します。

from nytimesarticle import articleAPI 


def parse_articles(articles): 
    news = [] 
    for i in articles['response']['docs']: 
     dic = {} 
     dic['id'] = i['_id'] 
    if i['abstract'] is not None: 
     dic['abstract'] = i['abstract'].encode("utf8") 
     dic['headline'] = i['headline']['main'].encode("utf8") 
     dic['desk'] = i['news_desk'] 
     dic['date'] = i['pub_date'][0:10] # cutting time of day. 
     dic['section'] = i['section_name'] 
     if i['snippet'] is not None: 
      dic['snippet'] = i['snippet'].encode("utf8") 
     dic['source'] = i['source'] 
     dic['type'] = i['type_of_material'] 
     dic['url'] = i['web_url'] 
     dic['word_count'] = i['word_count'] 

     locations = [] 
     for x in range(0,len(i['keywords'])): 
      if 'glocations' in i['keywords'][x]['name']: 
       locations.append(i['keywords'][x]['value']) 
     dic['locations'] = locations 

     subjects = [] 
     for x in range(0,len(i['keywords'])): 
      if 'subject' in i['keywords'][x]['name']: 
       subjects.append(i['keywords'][x]['value']) 
     dic['subjects'] = subjects 
     news.append(dic) 
    return(news) 

def get_articles(date,query): 
    all_articles = [] 
    for i in range(0,100): 
     articles = api.search(q = query, 
       fq = {'source':['Reuters','AP', 'The New York Times']}, 
       begin_date = 20151231, 
       end_date = 20160715, 
       sort='oldest', 
       page = str(i)) 
     articles = parse_articles(articles) 
     all_articles = all_articles + articles 
    return(all_articles) 



if __name__ == "__main__": 
    api = articleAPI('0282db2f333f4f4095edd19f0660c978') 

    articles = api.search(q = 'economy', 
    fq = {'headline':'economy', 'source':['Reuters','AP', 'The New YorkTimes']}, 
    begin_date = 20151231) 

    econ_all = [] 
    for i in range(2015,2016): 
     print 'Processing' + str(i) + '...' 
     econ_year = get_articles(str(i),'economy') 
     econ_all = econ_all + econ_year 

    import csv 
    keys = econ_all[0].keys() 
    with open('econ-mentions.csv', 'wb') as output_file: 
     dict_writer = csv.DictWriter(output_file, keys) 
     dict_writer.writeheader() 
     dict_writer.writerows(econ_all)