import re
import sys
import requests
import os
import subprocess
import time
import codecs


#####   dictionary definition. This lists the channels that will be scraped from the website. Format:
####	"Name of the channel as it appears on the website":, "Number the channel will be assigned on the generated XML file"
channels_to_grab = {
                    "Cultura": "3.1",
                    "Univesp TV": "3.2",
                    "TV Educação": "3.3",
                    "Record News": "6.1",
                    "RecordTV Litoral-Vale": "8.1",
                    "Rede 21": "10.1",
                    "TVB Santos": "12.1",
                    "RedeTV!": "14.1",
                    "Rede Vida": "15.1",
                    "TV Tribuna Santos": "18.1",
                    "Gazeta": "32.1",
                    "ISTV": "36.1",
                    "RBI TV": "38.1",
                    "TV Unisantos": "40.1",
                    "VTV": "46.1",
                    "Santa Cecília TV": "52.1",
                    "IDTV": "56.1",
                   }

model_file = open("config_partial.xml","r");
config_file = codecs.open("WebGrab++.config.xml","w+","utf-8")

for line in model_file:
    config_file.write(line);
model_file.close();

user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.111 Safari/537.36"
website = requests.get("http://www.lineup.tv.br/gdc.php", headers={"User-Agent": user_agent});

config_file.write("\r\n");
for f in channels_to_grab:
  #this regex works because re.search looks for the given term in the entire string. Not only that, it only finds the proper "Guia=" because it looks for DIGITS after it. if it fins anything that's not digits (when it finds the first one), it skips that one and goes to the next
  print('canal: ',f);
  stripped = re.search('Guia=(\d+)">'+f+'<\/a>', website.text);
  config_file.write("<channel site=\"lineup.net.br\" xmltv_id=\""+channels_to_grab[f]+"\" site_id=\""+stripped.group(1)+"\" update=\"i\">"+f+"</channel>\r\n");
  #print("<channel site=\"lineup.net.br\" xmltv_id=\""+channels_to_grab[f]+"\" site_id=\""+stripped.group(1)+"\" update=\"i\">"+f+"</channel>\r");
config_file.write("</settings>\n");
config_file.close();

print("WebGrab config file generated with the current channel codes for the channels requested. There's no error handling, so it must mean that the program finished sucessfully.");