import pandas as pd
import numpy as np
from Bio import SeqIO
from Bio import PDB
import requests
# 但是可能会出现 InsecureRequestWarning 警告,
# 虽然不影响代码采集但是看着不舒服,可以加上下面两行:
import urllib3
urllib3.disable_warnings()
names=pd.read_csv('C:/Users/A/Desktop/name_list.txt',header=None)
j=0
not_exist_list=[]
for i in names[0]:
j=j+1
print(j)
print(i)
url = 'https://files.rcsb.org/download/'+i+'.pdb'
#https://files.rcsb.org/download/7AR8.pdb
#print('url')
print(url)
r = requests.get(url,verify=False)
r=r.text.splitlines()
#print(r)
if r[3]==' <title>404 Not Found</title>':
print(i+'没有pdb文件。')
not_exist_list.append(i)
print(not_exist_list)
print(len(not_exist_list))