使用Python爬虫批量抓取PubChem化合物CAS

最新推荐文章于 2024-05-14 11:00:23 发布

kylin王国

最新推荐文章于 2024-05-14 11:00:23 发布

阅读量1.2k

点赞数 1

分类专栏： python技巧文章标签： python 爬虫开发语言

本文链接：https://blog.csdn.net/weixin_47634487/article/details/127774288

版权

python技巧专栏收录该内容

24 篇文章 4 订阅

订阅专栏

import pandas as pd 
import numpy as np  
import json 
import requests 
import time 
 
 #%reset -f 
cid = 5280535

 
#url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON/?heading=Chemical+and+Physical+Properties' 
url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON/?heading=Names+and+Identifiers' 
url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{a[1]}/JSON/?heading=Names+and+Identifiers' 
req = requests.get(url) 
req 
 
proper_json = json.loads(req.text) 

proper_json['Record']['Reference'][0]['SourceID']



import pandas as pd
a = pd.read_excel("G:\\非靶向代谢组数据库\\wheat\\wheat2.xlsx")
a = a['PubChem_CID']
for i in range(0, 704):
    #url0 = 'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/'+str.lower(a[i])+'/JSON/?heading=Names+and+Identifiers' 
    url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{a[i]}/JSON/?heading=Names+and+Identifiers' 
    req = requests.get(url) 
    proper_json = json.loads(req.text) 
    proper_json['Record']['Reference'][0]['SourceID']
    print(proper_json['Record']['Reference'][0]['SourceID'])