利用蛋白的chembl ID爬取其synonyms

师姐的小要求,安排一下:

import requests
from multiprocessing import Pool
import json
import pandas as pd


def get_synonyms(ID):   
    url =  'https://www.ebi.ac.uk/chembl/api/data/target/{}.json'.format(ID)
    s = requests.session()
    page = s.get(url).text
    text = json.loads(page)
    
    a = text['target_components'][0]['target_component_synonyms']
    synonyms = [i['component_synonym'] for i in a]
    dic = {ID:synonyms}
    return dic

def get_ids(path):
    df = pd.read_csv(path)
    ids = df['CHEMBL_ID']
    return ids

if __name__ == '__main__':
    path ='input by yourself'
    ids = get_ids(path)
    pool = Pool(processes = 28)
    for ID in ids:
        try:
            pool.apply_async(func = get_synonyms,args = (ID,))
        except:
            pass
    pool.close()
    pool.join()