PrimeWire Scraper

import os
import sys
import re
import urllib2
import webbrowser

from bs4 import BeautifulSoup

def show_search(surl):

    title = raw_input("enter show: ").replace(' ','+')
    print '[*] Working...\n'

    host = 'http://www.primewire.ag'

    soup1 = BeautifulSoup(urllib2.urlopen(host))

    for field in soup1.find_all('fieldset', {'class':'search_container'}):
        key = field.find('input', {'name':'key'})
        base = host + '/index.php?search_keywords={}&key={}&search_section=2'.format(title, key['value'])

    soup1 = BeautifulSoup(urllib2.urlopen(base))

    for div in soup1.find_all('div', {'class':'index_item index_item_ie'}):
        a = div.find('a')['href']

        if a:
            link1 = host + a.replace('watch', 'tv') + surl
            print link1

    return link1

def episode_list(search):

    soup2 = BeautifulSoup(urllib2.urlopen(search))
    links2 = {}

    for div in soup2.find_all('div', {'class':'tv_episode_item'}):
        for a in div.find_all('a'):

            match2 = re.search(r'(\d+)', a.get_text())
            title = a.find('span', {'class':'tv_episode_name'})

            if match2:
                number2 = match2.group(1)
                links2[number2] = 'http://www.primewire.ag' + a['href']

            if title:
                print '({}){}'.format(number2, title.get_text().encode('utf-8'))
            else:
                print '({}) - Untitled'.format(number2)

    return links2

def link_search(episodes, episode):
    print '[*] Searching...\n'

    soup3 = BeautifulSoup(urllib2.urlopen(episodes[episode]))
    links3 = {}

    for table in soup3.find_all('table', {'width':'100%'}):
        for a in table.find_all('a', {'target':'_blank'}):
            for li in table.find_all('li', {'class':'current-rating'}):
                 for sn in table.find_all('span', {'class':'version_host'}):

                    match3 = re.search(r'(\d+)', a.get_text())
                    img = table.find('img', {'title':'Verified Link'})

                    if match3:
                        number3 = match3.group(1)
                        links3[number3] = 'http://www.primewire.ag' + a['href']

                    if img:
                        print '({}) - {} - {} [!]'.format(number3, li.get_text(), sn.get_text())
                    else:
                        print '({}) - {} - {}'.format(number3, li.get_text(), sn.get_text())
    return links3

if __name__ == '__main__':

    if len(sys.argv) != 2:
        print 'Primewire.py season#'
        sys.exit()

    my_seasons = {
    '1': '/season-1',
    '2': '/season-2',
    '3': '/season-3',
    '4': '/season-4',
    '5': '/season-5',
    '6': '/season-6',
}
    for number in my_seasons:
        if number == sys.argv[1]:
            season = my_seasons[number]

    try:
        search = show_search(season)
        episodes = episode_list(search)

        while True:
            episode = raw_input('\n>>> #: ')
            if episode in episodes:
                 os.system('cls')
                 break

        versions = link_search(episodes, episode)

        while True:
            vid_link = raw_input('\n>>> #: ')
            if vid_link in versions:
                break

        print '[*] Opening link in browser!'
        webbrowser.open(versions[vid_link])
        sys.exit()

    except urllib2.HTTPError:
        print '- HTTP Error!'
        sys.exit()
    except urllib2.URLError:
        print '- Connection Faliure!'
        sys.exit()
    except:
        sys.exit()