LCA-GPT/DataAnalysis/crawler.py

50 lines
1.8 KiB
Python

import requests
import json
import xlwings as xw
from pprint import pprint
import pandas as pd
def getMap(url,params,headers,path):
response = requests.get(url=url,headers=headers,params=params)
results = json.loads(response.content)
data = results['data']
name = []
amount = []
upstream = []
percent = []
Type = []
for item in data:
if (item['name']==None) or (item['amount'] + item['upstream'] + item['percent'] <= 0.00001):
continue
name.append(item['name'])
amount.append(item['amount']) # 当前过程的碳排放
upstream.append(item['upstream']) # 当前过程加上上游的碳排放
percent.append(item['percent']) # 影响百分比
Type.append(item['type']) # 所述的过程类型
df = pd.DataFrame({"name":name,"amount":amount,"upstream":upstream,"percent":percent,"type":Type})
path = f"/home/zhangxj/WorkFile/LCA-GPT/DataAnalysis/lciaData/{path}.csv"
df.to_csv(path,index=False)
return df
if __name__ == '__main__':
# map数据的url
url = 'https://lca.qibebt.ac.cn/lca/analysis/lcia/map?taskId=1280544753347198976&categoryId=44645932&t=1725347326992'
params = {
'taskId':'1268567356305571840',
'categoryId': '43260647',
't': '1722491855892'
}
headers = {
'accept':'application/json, text/plain, */*',
'accept-encoding':'gzip, deflate, br, zstd',
'accept-language':'zh-CN',
'authorization':'Bearer d88024bb-6434-4adf-91fb-52dff44261c3',
'priority':'u=1, i',
'referer':'https://lca.qibebt.ac.cn/',
'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36'
}
name = "风力发电机"
getMap(url,params,headers,name)