爬化合物C号

最新推荐文章于 2024-05-28 08:58:34 发布

kylin王国

最新推荐文章于 2024-05-28 08:58:34 发布

阅读量60

点赞数

分类专栏：爬虫文章标签：爬虫 python

本文链接：https://blog.csdn.net/weixin_47634487/article/details/127818964

版权

爬虫专栏收录该内容

4 篇文章 0 订阅

订阅专栏

# -*- coding: utf-8 -*-
"""
Created on Tue Nov  8 13:07:40 2022

@author: Administrator
"""
#%reset -f
from pubchempy import get_compounds, Compound
import requests # 调用requests库
from bs4 import BeautifulSoup # 调用BeautifulSoup库
import json
import pandas as pd
import pandas as pd 
import numpy as np  
import json 
import requests 
import time 
for compound in get_compounds('Scopoletin', 'name'):
    b1 = compound.cid
    c1 = compound.isomeric_smiles
    d1 = compound.molecular_formula
    e1 = compound.molecular_weight
    f1 = compound.iupac_name
    

print(compound.cid)
print(compound.molecular_weight)
print(compound.molecular_formula)
print(compound.isomeric_smiles)
print(compound.iupac_name)

b1


url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{b1}/JSON/?heading=Depositor+Supplied+Synonyms' 
req = requests.get(url) 
proper_json = json.loads(req.text) 
proper_json['Record']['Section'][0]['Section'][0]['Section'][0]['Information'][0]['ReferenceNumber']

#proper_json['Record']['Section'][0]['Section'][0]['Section'][0]['Information'][0]['Value']['StringWithMarkup'][8]['String']
len1 = proper_json['Record']['Section'][0]['Section'][0]['Section'][0]['Information'][0]['Value']['StringWithMarkup']
len(len1)
for i in range(0,len(len1)):
    index = proper_json['Record']['Section'][0]['Section'][0]['Section'][0]['Information'][0]['Value']['StringWithMarkup'][i]['String']
    if len(index)==6 and index[0] =='C' :
        print('第'+str(i)+'是KEGG_ID：'+index)
    else:
        pass