爬取集思录数据(1)--强赎表

集思录强赎表爬取:

网页样式

 

 实现代码

import requests
import pandas as pd

url = 'https://www.jisilu.cn/data/cbnew/redeem_list/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'
}
response = requests.post(url = url,headers=headers)
jsl_qiangsu_json = response.json()['rows']
df_jsl = []
for i in range(0,len(jsl_qiangsu_json)):
    df_jsl.append(jsl_qiangsu_json[i]['cell'])
df = pd.DataFrame(df_jsl)
df['redeem_count']=df['redeem_count'].str.replace('<span style="color:red;">','')
df['redeem_count']=df['redeem_count'].str.replace('</span>','')
df['redeem_count']=df['redeem_count'].str.replace('<span title=','')
df['redeem_count']=df['redeem_count'].str.replace('style="color:gray;">','')
df.to_csv('jslqs.csv',encoding = 'gbk')