chemdumper.py

#http://chemspipy.readthedocs.io/en/latest/guide/install.html
import chemspipy as chpy

token = "<your token from http://chemspipy.readthedocs.io/en/latest/guide/intro.html#securitytoken>"
cs = chpy.ChemSpider(token)

n_samples = 10**5 #amount of molecules to save

import numpy as np

#seed random compound ids (~90% valid)
compound_ids = np.random.choice(58191596,size=n_samples,replace=False)

#you may need to avoid duplicates when downloading additional data
#the compound ids are avaliable through data['csid']

data = []
for i,csid in enumerate(compound_ids):
    try:
        info = cs.get_extended_compound_info(csid)
        info['csid']=csid
        data.append(info)
    except chpy.errors.ChemSpiPyError: pass
    if i%100==0:
        print i,'/',len(compound_ids)
    

import pandas as pd
df = pd.DataFrame(data)
df.to_csv("./data.tsv",sep='\t')