从 json.loads 返回的字典中提取数据

Question

这是我想要做的：提示输入 URL，使用 urllib 从该 URL 读取 JSON 数据，然后从 JSON 数据中解析和提取评论计数并计算它们的总和。

这是我目前在 Python 中所拥有的：

import json
import urllib

serviceurl = 'http://python-data.dr-chuck.net/comments_42.json'

while True:
    url = serviceurl + urllib.urlencode(('sensor':'false', 'address' : address))
    print "Retrieving", url
    uh = urllib.urlopen(url)
    data = uh.read()
    print "Retrieved", len(data), "characters"

    try:    js = json.loads(str(data))
    except:     js = None

    print js.dumps(js, indent = 4)

    js = ["comment"][0]["count"]
    lst = list()
    lst.append(js)
    print sum(lst)

JSON 数据如下所示：

{
  comments: [
    {
      name: "Matthias"
      count: 97
    },
    {
      name: "Geomer"
      count: 97
    }
    ...
  ]
}

我正在使用 Python 2。这是我第一次这样做，因此您可以给我的任何反馈都会有所帮助，尤其是在 try/except 语句之后。提前致谢。

Answer 1

js 是一个看起来像这样的字典：

{'comments': [{'count': 97, 'name': 'Matthias'}, {'count': 97, 'name': 'Geomer'}]}

您可以像这样得到所有'count' 值的总和：

sum(nested_dict['count'] for nested_dict in js['comments'])

如果列表中的字典有可能没有'count' 键，请使用默认值为0 的dict.get：

sum(nested_dict.get('count', 0) for nested_dict in js['comments'])

Answer 2

我也完成了相同的课程并完成了相同的任务。 timgeb 的答案将以更小的代码完成工作。或者，您也可以尝试以下方法：

import json
import urllib
counts = list()
inp = raw_input('Enter a URL: ')

url = urllib.urlopen(inp)
data = url.read()
print len(data)

try:
    js = json.loads(data)
except:
js = None

comments = js['comments']
for comment in comments:
    counts.append(comment['count'])

print sum(counts)

#print sum(nested_dict['count'] for nested_dict in js['comments'])

您不需要对 url 进行任何编码，也不需要 while 循环。该代码段用于使用 google map API。

Answer 3

我的代码版本：

import json
import urllib.request, urllib.parse, urllib.error
total = 0

url = input('Enter URL: ')
data = urllib.request.urlopen(url).read().decode()

info = json.loads(data)
number = info["comments"] #getting list of all the dictinaries
for i in number: #in each dictionary...
    needed = i.get('count') #... we are getting numbers from "count"
    total = total + int(needed) #summ all the numbers
print(total)

Answer 4

基于 Mudit Sahni 的代码，但为 Python3

编写

import urllib.request
import json

url = input("Enter URL: ")
response = urllib.request.urlopen(urllib.request.Request(url)).read().decode('utf-8')
data = json.loads(response)
counts = list()

comments = data['comments']
for comment in comments:
    counts.append(comment['count'])

print (sum(counts))

Answer 5

import urllib.request, urllib.parse, urllib.error
import json
import ssl

# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

url = input('Enter - ')
print('Retrieving', url)
uh = urllib.request.urlopen(url, context=ctx)
data = uh.read()

info = json.loads(data)
#print(info) #to see the info dictionary/object
#print(json.dumps(info, indent=2))  

count = 0
sum = 0

for item in info['comments']:
    num = item['count']
    sum = sum + int(num)
    count = count + 1

print('Count: ', count)
print('Sum: ', sum)

Answer 6

##  http://py4e-data.dr-chuck.net/comments_42.json       total= 2553
## http://py4e-data.dr-chuck.net/comments_802780.json    total= 2670
import ssl
import urllib.request, urllib.parse, urllib.error
import json
total= list()

## Ignore SSL certification
ctx= ssl.create_default_context
ctx.check_hostname= False
ctx.verify_mode= ssl.CERT_NONE

## Access url
url= input('Enter URL: ')
req= urllib.request.urlopen(url, context=ctx)
html= req.read().decode()
print('Retrieving URL:', url)
print('Retrieved', len(html),'characters')

##accessing data
js= json.loads(html)
#print(json.dumps(js, indent=3))
for counts in js["comments"]:
    #print('Counts:', counts['count'])
    total.append(counts['count'])
print(sum(total))

Answer 7

import urllib.request, urllib.parse, urllib.error
import ssl
import json

# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

while True:
    count = sum = 0
    url = input('Enter location: ')
    if len(url) < 1: break
    print('Retrieving', url)
    uh = urllib.request.urlopen(url, context=ctx)
    
    data = uh.read()
    print('Retrieved', len(data), 'characters')
    
    info = json.loads(data)

    for item in info['comments']:
        count+=1
        sum+=int(item['count'])
    
    print('count:',count)
    print('sum',sum)

Answer 8

from urllib.request import urlopen
import json

while True:
    url = input('Enter url: ')
    if len(url) < 1:
        break
    print("Retrieving", url)
    uh = urlopen(url)
    data = uh.read().decode()
    print("Retrieved", len(data), "characters")
    try:
        js = json.loads(data)
    except:
        js = None

    count = 0
    lst = list()
    for comment in js["comments"]:
        count += 1
        lst.append(comment["count"])
    print("count:", count)
    print(sum(lst))

Answer 9

import urllib.request, urllib.parse, urllib.error
import json

url = "http://py4e-data.dr-chuck.net/comments_1418532.json"
info = json.loads(urllib.request.urlopen(url).read())

comm=info['comments']
counts_list = [int(items['count']) for items in comm]

print(sum(counts_list))

Answer 10

import json
import urllib

url=raw_input('Enter location:')
print 'Retrieving',url
uh=urllib.urlopen(url)
data=uh.read()


info = json.loads(data)
print 'Retrieved', len(info)
sum=0
counts=0
for item in info['comments']:
    sum=sum+item['count']
    counts=counts+1
print 'Counts:',counts
print 'Sum:',sum

Answer 11

import urllib.request, urllib.parse, urllib.error
import ssl
import json

#to ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

url = input('Enter - ')
data = urllib.request.urlopen(url, context=ctx).read()
info = json.loads(data)
sum_count = 0
for a in info["comments"]:
    sum_count += int(a["count"])
print(sum)