#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 19 14:33:51 2020

@author: tanu
"""
#%% load packages
import os,sys
import subprocess
import argparse
import requests
import re
import time
from bs4 import BeautifulSoup
import pandas as pd
from pandas.api.types import is_string_dtype
from pandas.api.types import is_numeric_dtype
#%%============================================================================
homedir = os.path.expanduser('~')
#print(homedir)
host = 'http://biosig.unimelb.edu.au'
# Needed if things try to block the 'requests' user agent
#headers = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"}
#%%
def get_results(url_file):
    # initilialise empty df
    dynamut_results_out_df = pd.DataFrame()
    with open(url_file, 'r') as f:
        for count, line in enumerate(f):
            line = line.strip()
            print('URL no.', count+1, '\n', line)
            #batch_response = requests.get(line, headers=headers)
            batch_response = requests.get(line)
            batch_soup = BeautifulSoup(batch_response.text, features = 'html.parser')
                                   
            # initilialise empty df
            #dynamut_results_df = pd.DataFrame()
            for a in batch_soup.find_all('a', href=True, attrs = {'class':'btn btn-default btn-sm'}):
                print ("Found the URL:", a['href']) 
                single_result_url = host + a['href']
                snp = re.search(r'([A-Z]+[0-9]+[A-Z]+$)', single_result_url).group(0)
                print(snp)
                print('\nGetting results from:',  single_result_url)
                
                result_response = requests.get(single_result_url)
                if result_response.status_code == 200:
                        print('\nFetching results for SNP:', snp)
                        # extract results using the html parser          
                        soup = BeautifulSoup(result_response.text, features = 'html.parser')
                        #web_result_raw = soup.find(id = 'predictions').get_text()
                        ddg_dynamut = soup.find(id = 'ddg_dynamut').get_text()
                        ddg_encom = soup.find(id = 'ddg_encom').get_text()
                        ddg_mcsm = soup.find(id = 'ddg_mcsm').get_text()
                        ddg_sdm = soup.find(id = 'ddg_sdm').get_text()
                        ddg_duet = soup.find(id = 'ddg_duet').get_text()
                        dds_encom = soup.find(id = 'dds_encom').get_text()
                        
                        param_dict = {"mutationinformation" : snp
                            , "ddg_dynamut" : ddg_dynamut
                            , "ddg_encom"   : ddg_encom
                            , "ddg_mcsm"    : ddg_mcsm
                            , "ddg_sdm"     : ddg_sdm
                            , "ddg_duet"    : ddg_duet
                            , "dds_encom"   : dds_encom 
                            }
                        results_df = pd.DataFrame.from_dict(param_dict, orient = "index").T
                        print('Result DF:', results_df, 'for URL:', line)
                        #dynamut_results_df = dynamut_results_df.append(results_df)#!1 too many!:-)
                        dynamut_results_out_df = dynamut_results_out_df.append(results_df)
                        
    #print(dynamut_results_out_df)
    print('\nWriting dynamut results df')
    print('\nResults File:'
          , '\nNo. of rows:', dynamut_results_out_df.shape[0]
          , '\nNo. of cols:', dynamut_results_out_df.shape[1])
    print(dynamut_results_out_df)
    dynamut_results_out_df.to_csv('/tmp/test_dynamut.csv', index = False)

#%%
# example 1: multiple urls in a single file
my_url_file_multiple = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_multiple.txt'
print(my_url_file_multiple)
get_results(my_url_file_multiple)

# example 2: single url in a file
my_url_file_single = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_single.txt'
print(my_url_file_multiple)
get_results(my_url_file_single)
#%%