Python - Any suggestions for what i have so far

Question

Alright, i put this together and it seems to work.

1channel.py -breakingbad 1

The Output (1-10):
(1) - Currently 3.80/5
(2) - Currently 3.50/5

(1 opens the link in browser)

if anyone has any suggestions or wants to improve it...

Thanks.

from bs4 import BeautifulSoup
import urllib2, sys, webbrowser

def Work(tvshow):
    print "\n[*] Working...\n"

    try:

        f = urllib2.urlopen(tvshow)
        html = f.read()
        soup = BeautifulSoup(html)

        for table in soup.findAll('table',{"width":"100%"}):
            for a in table.findAll('a',{"target":"_blank"}):
                for li in table.findAll('li',{"class":"current-rating"}):

                    if a.text=="Version 2":
                        print "(1) - %s\n" % (li.text)
                        link1 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 3":
                        print "(2) - %s\n" % (li.text)
                        link2 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 4":
                        print "(3) - %s\n" % (li.text)
                        link3 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 5":
                        print "(4) - %s\n" % (li.text)
                        link4 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 6":
                        print "(5) - %s\n" % (li.text)
                        link5 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 7":
                        print "(6) - %s\n" % (li.text)
                        link6 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 8":
                        print "(7) - %s\n" % (li.text)
                        link7 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 9":
                        print "(8) - %s\n" % (li.text)
                        link8 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 10":
                        print "(9) - %s\n" % (li.text)
                        link9 = "http://www.1channel.ch" + a['href']

                    elif a.text=="Version 11":
                        print "(10) - %s\n" % (li.text)
                        link10 = "http://www.1channel.ch" + a['href']

        user = raw_input(">>> ")

        if user == '1':
            webbrowser.open(link1)
        elif user == '2':
            webbrowser.open(link2)
        elif user == '3':
            webbrowser.open(link3)
        elif user == '4':
            webbrowser.open(link4)
        elif user == '5':
            webbrowser.open(link5)
        elif user == '6':
            webbrowser.open(link6)
        elif user == '7':
            webbrowser.open(link7)
        elif user == '8':
            webbrowser.open(link8)
        elif user == '9':
            webbrowser.open(link9)
        elif user == '10':
            webbrowser.open(link10)
        else:
            exit(0)

    except urllib2.HTTPError:
            print "- HTTP Error!"
    except urllib2.URLError:
            print "- Connection Faliure!"
    except UnboundLocalError:
            print "Episode does not exist!"

def Main():
    if len(sys.argv) !=3:
        print "1channel.py -show episode#"
        sys.exit()

    elif sys.argv[1] == '-breakingbad':
        tvshow = 'http://www.1channel.ch/tv-4128-Breaking-Bad/season-4-episode-' + sys.argv[2]

    elif sys.argv[1] == '-walkingdead':
        tvshow = 'http://www.1channel.ch/tv-2490619-The-Walking-Dead/season-3-episode-' + sys.argv[2]

    elif sys.argv[1] == '-poi':
        tvshow = 'http://www.1channel.ch/tv-2727923-Person-of-Interest/season-2-episode-' + sys.argv[2]

    else:
        sys.exit()

    Work(tvshow)

if __name__ == '__main__':
    Main()

Answer 1

Here's what I would start with:

import sys
import re
import urllib2
import webbrowser

from bs4 import BeautifulSoup

def get_episodes(url):
    print '[*] Working...'

    soup = BeautifulSoup(urllib2.urlopen(url))
    links = {}

    for table in soup.find_all('table', width='100%'):
        for a in table.find_all('a', target='_blank'):
            for li in table.find_all('li', class_='current-rating'):
                match = re.search(r'Version (\d+)', a.get_text())

                if match:
                    number = match.group(1)
                    links[number] = 'http://www.1channel.ch' + a['href']

                    print '({}) - {}\n'.format(number, li.get_text())

    return links

if __name__ == '__main__':
    if len(sys.argv) != 3:
        print '1channel.py -show episode#'
        sys.exit()
    elif sys.argv[1] == '-breakingbad':
        url = 'tv-4128-Breaking-Bad/season-4-episode-'
    elif sys.argv[1] == '-walkingdead':
        url = 'tv-2490619-The-Walking-Dead/season-3-episode-'
    elif sys.argv[1] == '-poi':
        url = 'tv-2727923-Person-of-Interest/season-2-episode-'
    else:
        sys.exit()

    try:
        episodes = get_episodes('http://www.1channel.ch/' + url + sys.argv[2])
    except urllib2.HTTPError:
        print '- HTTP Error!'
        sys.exit(0)
    except urllib2.URLError:
        print '- Connection Faliure!'
        sys.exit(0)

    number = int(raw_input('>>> '))

    if number in episodes:
        webbrowser.open(episodes[number])
    else:
        print 'Episode does not exist!'
        sys.exit(0)

• Keep functions simple and (generally) single-purpose. Have them do one simple task.
• Keep your code DRY. If you catch yourself writing the same code over and over, make a function for the general case and just fill in the variables.
• BeautifulSoup4 uses underscores instead of camel case, so findAll becomes find_all.

I haven't tested this code either, but it should work.