Python: スカパーのチャンネル一覧取得

gistfile1.py

# -*- coding: utf-8 -*-
import requests
import re
from BeautifulSoup import BeautifulSoup

MASTER_URL = "http://www.skyperfectv.co.jp/search/sky/S5_1/InfoInput.html"
PROGRAM_URL = "http://www.skyperfectv.co.jp/search/sky/S9_1/Program.html"

NAME_EXTRACTOR = re.compile(r'name\s*:\s*"([^"]+)"')
CHANNEL_EXTRACTOR = re.compile(r'chAr\[(\d+)\]\s*=\s*"([^"]+)"')

def get_channels():
    r = requests.post(MASTER_URL, {"getmaster": 1, "master_mode": "A"})
    bs = BeautifulSoup(unicode(r.content, "Shift_JIS"))
    scripts = bs.head.findAll("script")
    master = filter(lambda x: not x.has_key("src"), scripts)[0]

    lines = master.text.splitlines()

    genres = {}
    channels = []
    cur_genre = None
    for line in lines:
        line = line.strip()
        if line.startswith("genAr.push"):
            m = NAME_EXTRACTOR.search(line)
            if (cur_genre is not None) and len(channels) > 0:
                genres[cur_genre] = channels
            cur_genre = m.group(1)
            channels = []
        elif line.startswith("chAr"):
            m = CHANNEL_EXTRACTOR.search(line)
            chid = m.group(1)
            chname = m.group(2)
            chname = chname[chname.index(" ")+1:]
            channels.append((chid, chname))

    if (cur_genre is not None) and len(channels) > 0:
        genres[cur_genre] = channels

    return genres


if __name__ == '__main__':
    genres = get_channels()
    for g,cs in genres.items():
        print g
        for c in cs:
            print (c[0] + ": " + c[1])