Python爬取Json数据的示例-Tutorial Python-php.cn

Python爬取Json数据的示例

coldplay.xixi

Lepaskan： 2020-12-07 17:41:04

ke hadapan

5019 orang telah melayarinya

Python教程栏目介绍爬取Json数据实例

Python爬取Json数据的示例

相关免费学习推荐：python教程（视频）

本文中以爬取其中的AI流转率数据为例。

该地址返回的响应内容为Json类型，其中红框标记的项即为AI流转率值：

实现代码如下：

import requests
import json
import csv
 
# 爬虫地址
url = &#39;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&#39;
 
# 携带cookie进行访问
headers = {
&#39;Host&#39;:&#39;databank.yushanfang.com&#39;,
&#39;Referer&#39;:&#39;https://databank.yushanfang.com/&#39;,
&#39;Connection&#39;:&#39;keep-alive&#39;,
&#39;User-Agent&#39;:&#39;Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36&#39;,
&#39;Cookie&#39;:&#39;_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&#39;,
}
 
rows = []
for n in range(20, 31):
  row = []
  row.append(n)
  for m in range (21, 32):
    if m < n + 1:
      row.append("")
    else:
      
      # 格式化请求地址，更换请求参数
      reqUrl = url.format(n, m)
      
      # 打印本次请求地址
      print(url)
      
      # 发送请求，获取响应结果
      response = requests.get(url=reqUrl, headers=headers, verify=False)
      text = response.text
      
      # 打印本次请求响应内容
      print(text)
      
      # 将响应内容转换为Json对象
      jsonobj = json.loads(text)
      
      # 从Json对象获取想要的内容
      toCntPercent = jsonobj[&#39;data&#39;][&#39;interCrowdInfo&#39;][1][&#39;toCntPercent&#39;]
      
      # 生成行数据
      row.append(str(toCntPercent)+"%")
      
  # 保存行数据    
  rows.append(row)
  
# 生成Excel表头
header = [&#39;AI流转率&#39;, &#39;21&#39;, &#39;22&#39;, &#39;23&#39;, &#39;24&#39;, &#39;25&#39;, &#39;26&#39;, &#39;27&#39;, &#39;28&#39;, &#39;29&#39;, &#39;30&#39;, &#39;31&#39;]
 
# 将表头数据和爬虫数据导出到Excel文件
with open(&#39;D:\\res\\pachong\\tmall.csv&#39;, &#39;w&#39;, encoding=&#39;gb18030&#39;) as f :
  f_csv = csv.writer(f)
  f_csv.writerow(header)
  f_csv.writerows(rows)

Salin selepas log masuk

import csv
import json
import ssl
import urllib.request
 
# 爬虫地址
url = &#39;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&#39;
 
# 不校验证书
ssl._create_default_https_context = ssl._create_unverified_context
 
# 携带cookie进行访问
headers = {
&#39;Host&#39;:&#39;databank.yushanfang.com&#39;,
&#39;Referer&#39;:&#39;https://databank.yushanfang.com/&#39;,
&#39;Connection&#39;:&#39;keep-alive&#39;,
&#39;User-Agent&#39;:&#39;Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36&#39;,
&#39;Cookie&#39;:&#39;_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&#39;,
}
 
rows = []
n = 20
while n <31:
  row = []
  row.append(n)
  
  m =21
  while m <32:
    
    if m < n + 1:
      row.append("")
    else:
      
      # 格式化请求地址，更换请求参数
      reqUrl = url.format(n, m)
      
      # 打印本次请求地址
      print(reqUrl)
      
      # 发送请求，获取响应结果
      request = urllib.request.Request(url=reqUrl, headers=headers)
      response = urllib.request.urlopen(request)
      text = response.read().decode(&#39;utf8&#39;)
      
      # 打印本次请求响应内容
      print(text)
      
      # 将响应内容转换为Json对象
      jsonobj = json.loads(text)
      
      # 从Json对象获取想要的内容
      toCntPercent = jsonobj[&#39;data&#39;][&#39;interCrowdInfo&#39;][1][&#39;toCntPercent&#39;]
      
      # 生成行数据
      row.append(str(toCntPercent) + "%")
      
    m = m+1
    
  rows.append(row)    
  n = n+1
  
# 生成Excel表头
header = [&#39;AI流转率&#39;, &#39;21&#39;, &#39;22&#39;, &#39;23&#39;, &#39;24&#39;, &#39;25&#39;, &#39;26&#39;, &#39;27&#39;, &#39;28&#39;, &#39;29&#39;, &#39;30&#39;, &#39;31&#39;]
 
# 将表头数据和爬虫数据导出到Excel文件
with open(&#39;D:\\res\\pachong\\tmall.csv&#39;, &#39;w&#39;, encoding=&#39;gb18030&#39;) as f :
  f_csv = csv.writer(f)
  f_csv.writerow(header)
  f_csv.writerows(rows)

Salin selepas log masuk

导出内容如下：