Python ValueError:dict包含字段名中不包含的字段，即使使用if语句

我正试图利用《纽约时报》的API，从2016年《纽约时报》的所有文章中提取“经济”一词。我在代码末尾收到以下错误消息：

ValueError:dict包含字段名中不包含的字段：“抽象”

这是我的代码：

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)

---

看来我的if语句应该可以防止这个错误。此外，如果我使用“writerow”，正如我在这里看到的，我会在不创建csv的情况下获得完整的详细信息列表。任何帮助都将不胜感激

我不确定您的问题出在哪里，但这段代码创建了一个包含内容的文件econ-indications.csv

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)

---

我不确定您的问题出在哪里，但这段代码创建了一个包含内容的文件econ-indications.csv

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)

---

谢谢你的帮助！有趣的是，它确实创建了内容，但我不确定它是否捕获了所有包含“经济”一词的文章。但这有帮助…我会继续工作。谢谢你的帮助！有趣的是，它确实创建了内容，但我不确定它是否捕获了所有包含“经济”一词的文章。但这有帮助…我会继续工作。