Question

    global twitter_user_info
    twitter_user_info=[]    

    def get_user_info(twitter_user):
    """
    An example of using the query_user_info method
    :param twitter_user: the twitter user to capture user data
    :return: twitter_user_data: returns a dictionary of twitter user data
    """

    user_info = query_user_info(user=twitter_user)
    twitter_user_data = {}

    twitter_user_data["user"] = user_info.user
    twitter_user_data["fullname"] = user_info.full_name
    twitter_user_data["location"] = user_info.location
    twitter_user_data["blog"] = user_info.blog
    twitter_user_data["date_joined"] = user_info.date_joined
    twitter_user_data["id"] = user_info.id
    twitter_user_data["num_tweets"] = user_info.tweets
    twitter_user_data["following"] = user_info.following
    twitter_user_data["followers"] = user_info.followers
    twitter_user_data["likes"] = user_info.likes
    twitter_user_data["lists"] = user_info.lists

    return twitter_user_data

    absd=[]
    def main():
      start = time.time()
      csv = pd.read_csv('operationbandar_users.csv')
      users = csv['username']
      pool = Pool(4)

      for user in pool.map(get_user_info,users):
        twitter_user_info.append(user)

      cols=['id','fullname','date_joined','location','blog', 'num_tweets','following','followers','likes','lists']
      data_frame = pd.DataFrame(twitter_user_info, index=absd, columns=cols)
      data_frame.index.name = "Users"
      data_frame.sort_values(by="followers", ascending=False, inplace=True, kind='quicksort', na_position='last')
      elapsed = time.time() - start
      print(f"Elapsed time: {elapsed}")
      display(data_frame)

此代码返回以下错误：

multiprocessing.pool.RemoteTraceback：   “”   追溯（最近一次通话）：     在工作程序中的文件“ /home/nrjkumar/anaconda3/envs/Scraping/lib/python3.7/multiprocessing/pool.py”，第121行       结果=（真，func（* args，* kwds））     在mapstar中，文件“ /home/nrjkumar/anaconda3/envs/Scraping/lib/python3.7/multiprocessing/pool.py”，第44行       返回列表（map（* args））     get_user_info中的文件“ examples / get_twitter_user_data_1.py”，第43行
      twitter_user_data [“ user”] = user_info.user
   AttributeError：“ NoneType”对象没有属性“ user”   “”“
  上面的异常是以下异常的直接原因：
  追溯（最近一次通话）：     在第89行的文件“ examples / get_twitter_user_data_1.py”中       主要（）     主文件中的文件“ examples / get_twitter_user_data_1.py”，第66行       适用于pool.map（get_user_info，users）中的用户：     地图中的文件“ /home/nrjkumar/anaconda3/envs/Scraping/lib/python3.7/multiprocessing/pool.py”，第268行       返回self._map_async（func，可迭代，mapstar，chunksize）.get（）     在get中，文件“ /home/nrjkumar/anaconda3/envs/Scraping/lib/python3.7/multiprocessing/pool.py”       提高自我。_value
   AttributeError：“ NoneType”对象没有属性“ user”

我在这里用pool.map和传递的字典作为参数搜索了可能的情况，但是找不到问题。我是python的新手。有人可以帮忙吗？

query_user_info（）

def query_user_info(user):
"""
Returns the scraped user data from a twitter user page.

:param user: the twitter user to web scrape its twitter page info
"""
try:
    user_info = query_user_page(INIT_URL_USER.format(u=user))
    if user_info:
        logger.info("Got user information from username {}".format(user))
        return user_info

except KeyboardInterrupt:
    logger.info("Program interrupted by user. Returning user information gathered so far...")
except BaseException:
    logger.exception("An unknown error occurred! Returning user information gathered so far...")

logger.info("Got user information from username {}".format(user))
return user_info

query_user_page（）

def query_user_page(url, retry=10, timeout=60):
"""
Returns the scraped user data from a twitter user page.

:param url: The URL to get the twitter user info from (url contains the user page)
:param retry: Number of retries if something goes wrong.
:return: Returns the scraped user data from a twitter user page.
"""
print("reached url:",url)

try:
    proxy = next(proxy_pool)
    logger.info('Using proxy {}'.format(proxy))
    response = requests.get(url, headers=HEADER, proxies={"http": proxy})
    html = response.text or ''

    user_info = User.from_html(html)
    if not user_info:
        return None

    return user_info

except requests.exceptions.HTTPError as e:
    logger.exception('HTTPError {} while requesting "{}"'.format(
        e, url))
except requests.exceptions.ConnectionError as e:
    logger.exception('ConnectionError {} while requesting "{}"'.format(
        e, url))
except requests.exceptions.Timeout as e:
    logger.exception('TimeOut {} while requesting "{}"'.format(
        e, url))

if retry > 0:
    logger.info('Retrying... (Attempts left: {})'.format(retry))
    return query_user_page(url, retry-1)

logger.error('Giving up.')
return None

Nonetype对象没有属性“用户”

0 个答案: