[英]Having trouble getting nested ojects from json array in python
您好,我有一個 jsonLines 文件,我正在嘗試從此處的 jsonline 文件中獲取所有主題標簽(以及應該是相同過程的提及): https://github.com/THsTestingGround/JsonL_Quest_SO/blob/master/output-2020- 01-21.jsonl (所以不允許我放網址,而且有很多)
這是一個獲取單個鍵對象的可重現示例。 我將如何繼續獲得多個主題標簽(提及將相同)? 目前我必須手動指定。 無論如何要把它們都放在一個 go 之類的東西里? 我可以在這里使用此代碼獲得 csv :
import json
import csv
import io
# creates a .csv file using a Twitter .json file
# the fields have to be set manually
def extract_json(fileobj):
# Iterates over an open JSONL file and yields
# decoded lines. Closes the file once it has been
# read completely.
with fileobj:
for line in fileobj:
yield json.loads(line)
#path to the jsonl file
data_json = io.open('output-2020-01-21.json', mode='r', encoding='utf-8') # Opens in the JSONL file
data_python = extract_json(data_json)
csv_out = io.open('tweets_out_utf8.csv', mode='w', encoding='utf-8') #opens csv file
#if you're adding additional columns please don't forget to add them here
fields = u'created_at,text,full_text, screen_name,followers,friends,rt,fav' #field names
csv_out.write(fields)
csv_out.write(u'\n')
for line in data_python:
#because retweet is not common, sometimes jsonl won't have the key, so this is safer
try:
retweeted_status_full_text = '"' +line.get('retweeted_status').get('full_text').replace('"','""') + '"'
except:
retweeted_status_full_text = 'NA'
#gets me only one hastags even when there are more than one
try:
entities= '"' + line.get('entities').get('hashtags')[0].get('text').replace('"', '""') + '"'
except:
entities = 'NA'
#writes a row and gets the fields from the json object
#screen_name and followers/friends are found on the second level hence two get methods
row = [line.get('created_at'),
'"' + line.get('full_text').replace('"','""') + '"', #creates double quotes
retweeted_status_full_text,
line.get('user').get('screen_name'),
str(line.get('user').get('followers_count')),
str(line.get('user').get('friends_count')),
str(line.get('retweet_count')),
str(line.get('favorite_count'))]
row_joined = u','.join(row)
csv_out.write(row_joined)
csv_out.write(u'\n')
csv_out.close()
我確實嘗試過,但它給了我一個錯誤。 我似乎也無法在 SO 中找到解決方案。 目前 json 稍弱一些,因此我將不勝感激。 謝謝。
import json
import csv
import io
def extract_json(fileobj):
with fileobj:
for line in fileobj:
yield json.loads(line)
data_json = io.open('a.json', mode='r', encoding='utf-8')
data_python = extract_json(data_json)
csv_out = io.open('tweets_out_utf8.csv', mode='w', encoding='utf-8')
fields = u'created_at,text,full_text, screen_name,followers,friends,rt,fav'
csv_out.write(fields)
csv_out.write(u'\n')
for line in data_python:
try:
retweeted_status_full_text = '"' +line.get('retweeted_status').get('full_text').replace('"','""') + '"'
except:
retweeted_status_full_text = 'NA'
try:
temp = line.get('entities').get('hashtags')
entities = ""
for val in temp:
entities += '"' + val.get('text').replace('"', '""') + '"' + ' '
except:
entities = ""
row = [line.get('created_at'),
'"' + line.get('full_text').replace('"','""') + '"',
retweeted_status_full_text,
line.get('user').get('screen_name'),
str(line.get('user').get('followers_count')),
str(line.get('user').get('friends_count')),
str(line.get('retweet_count')),
str(line.get('favorite_count'))]
print('entities' + ' ' + str(entities))
row_joined = u','.join(row)
csv_out.write(row_joined)
csv_out.write(u'\n')
csv_out.close()
我嘗試過這樣的事情。 我用entities = ''替換了空實體
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.