使用Python爬取Json數(shù)據(jù)的示例代碼

更新時間：2020年12月07日 15:27:06 作者：pengjunlee

這篇文章主要介紹了使用Python爬取Json數(shù)據(jù)的示例代碼,本文給大家介紹的非常詳細，對大家的學習或工作具有一定的參考借鑒價值，需要的朋友可以參考下

一年一度的雙十一即將來臨，臨時接到了一個任務：統(tǒng)計某品牌數(shù)據(jù)銀行中自己品牌分別在2017和2018的10月20日至10月31日之間不同時間段的AIPL（“認知”(Aware)、“興趣”(Interest)、“購買”(Purchase)、“忠誠”(Loyalty)）流轉(zhuǎn)率。

使用Fiddler獲取到目標地址為：

https://databank.yushanfang.com/api/ecapi?path=/databank/crowdFullLink/flowInfo&fromCrowdId=3312&beginTheDate=20181020&endTheDate=20181031&toCrowdIdList[0]=3312&toCrowdIdList[1]=3313&toCrowdIdList[2]=3314&toCrowdIdList[3]=3315

本文中以爬取其中的AI流轉(zhuǎn)率數(shù)據(jù)為例。

該地址返回的響應內(nèi)容為Json類型，其中紅框標記的項即為AI流轉(zhuǎn)率值：

實現(xiàn)代碼如下：

import requests
import json
import csv
 
# 爬蟲地址
url = 'https://databank.yushanfang.com/api/ecapi?path=/databank/crowdFullLink/flowInfo&fromCrowdId=3312&beginTheDate=201810{}&endTheDate=201810{}&toCrowdIdList[0]=3312&toCrowdIdList[1]=3313&toCrowdIdList[2]=3314&toCrowdIdList[3]=3315'
 
# 攜帶cookie進行訪問
headers = {
'Host':'databank.yushanfang.com',
'Referer':'https://databank.yushanfang.com/',
'Connection':'keep-alive',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',
'Cookie':'_tb_token_=iNkDeJLdM3MgvKjhsfdW; bs_n_lang=zh_CN; cna=aaj1EViI7x0CATo9kTKvjzgS; ck2=072de851f1c02d5c7bac555f64c5c66d; c_token=c74594b486f8de731e2608cb9526a3f2; an=5YWo5qOJ5pe25Luj5a6Y5pa55peX6Iiw5bqXOnpmeA%3D%3D; lg=true; sg=\"=19\"; lvc=sAhojs49PcqHQQ%3D%3D; isg=BPT0Md7dE_ic5Ie3Oa85RxaMxbLK3UqJMMiN6o5VjH8C-ZRDtt7aRXb3fXGEAVAP',
}
 
rows = []
for n in range(20, 31):
  row = []
  row.append(n)
  for m in range (21, 32):
    if m < n + 1:
      row.append("")
    else:
      
      # 格式化請求地址，更換請求參數(shù)
      reqUrl = url.format(n, m)
      
      # 打印本次請求地址
      print(url)
      
      # 發(fā)送請求，獲取響應結(jié)果
      response = requests.get(url=reqUrl, headers=headers, verify=False)
      text = response.text
      
      # 打印本次請求響應內(nèi)容
      print(text)
      
      # 將響應內(nèi)容轉(zhuǎn)換為Json對象
      jsonobj = json.loads(text)
      
      # 從Json對象獲取想要的內(nèi)容
      toCntPercent = jsonobj['data']['interCrowdInfo'][1]['toCntPercent']
      
      # 生成行數(shù)據(jù)
      row.append(str(toCntPercent)+"%")
      
  # 保存行數(shù)據(jù)    
  rows.append(row)
  
# 生成Excel表頭
header = ['AI流轉(zhuǎn)率', '21', '22', '23', '24', '25', '26', '27', '28', '29', '30', '31']
 
# 將表頭數(shù)據(jù)和爬蟲數(shù)據(jù)導出到Excel文件
with open('D:\\res\\pachong\\tmall.csv', 'w', encoding='gb18030') as f :
  f_csv = csv.writer(f)
  f_csv.writerow(header)
  f_csv.writerows(rows)

import csv
import json
import ssl
import urllib.request
 
# 爬蟲地址
url = 'https://databank.yushanfang.com/api/ecapi?path=/databank/crowdFullLink/flowInfo&fromCrowdId=3312&beginTheDate=201810{}&endTheDate=201810{}&toCrowdIdList[0]=3312&toCrowdIdList[1]=3313&toCrowdIdList[2]=3314&toCrowdIdList[3]=3315'
 
# 不校驗證書
ssl._create_default_https_context = ssl._create_unverified_context
 
# 攜帶cookie進行訪問
headers = {
'Host':'databank.yushanfang.com',
'Referer':'https://databank.yushanfang.com/',
'Connection':'keep-alive',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',
'Cookie':'_tb_token_=iNkDeJLdM3MgvKjhsfdW; bs_n_lang=zh_CN; cna=aaj1EViI7x0CATo9kTKvjzgS; ck2=072de851f1c02d5c7bac555f64c5c66d; c_token=c74594b486f8de731e2608cb9526a3f2; an=5YWo5qOJ5pe25Luj5a6Y5pa55peX6Iiw5bqXOnpmeA%3D%3D; lg=true; sg=\"=19\"; lvc=sAhojs49PcqHQQ%3D%3D; isg=BPT0Md7dE_ic5Ie3Oa85RxaMxbLK3UqJMMiN6o5VjH8C-ZRDtt7aRXb3fXGEAVAP',
}
 
rows = []
n = 20
while n <31:
  row = []
  row.append(n)
  
  m =21
  while m <32:
    
    if m < n + 1:
      row.append("")
    else:
      
      # 格式化請求地址，更換請求參數(shù)
      reqUrl = url.format(n, m)
      
      # 打印本次請求地址
      print(reqUrl)
      
      # 發(fā)送請求，獲取響應結(jié)果
      request = urllib.request.Request(url=reqUrl, headers=headers)
      response = urllib.request.urlopen(request)
      text = response.read().decode('utf8')
      
      # 打印本次請求響應內(nèi)容
      print(text)
      
      # 將響應內(nèi)容轉(zhuǎn)換為Json對象
      jsonobj = json.loads(text)
      
      # 從Json對象獲取想要的內(nèi)容
      toCntPercent = jsonobj['data']['interCrowdInfo'][1]['toCntPercent']
      
      # 生成行數(shù)據(jù)
      row.append(str(toCntPercent) + "%")
      
    m = m+1
    
  rows.append(row)    
  n = n+1
  
# 生成Excel表頭
header = ['AI流轉(zhuǎn)率', '21', '22', '23', '24', '25', '26', '27', '28', '29', '30', '31']
 
# 將表頭數(shù)據(jù)和爬蟲數(shù)據(jù)導出到Excel文件
with open('D:\\res\\pachong\\tmall.csv', 'w', encoding='gb18030') as f :
  f_csv = csv.writer(f)
  f_csv.writerow(header)
  f_csv.writerows(rows)

導出內(nèi)容如下：