歌ネットから歌詞取得するプログラム

getlyrics.py

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import re


def createurl(url, ep=""):
    url += ep; url = url.replace("m//", "m/") if "//" in url else url; return url

songtitle = raw_input(">>>")
p = re.compile(r"<[^>]*?>")
p2 = re.compile(r'[\\|/|:|?|.|"|<|>|\|*|]')
baseurl = 'http://www.uta-net.com'

try:
    tag_tbody = BeautifulSoup(requests.get(createurl(baseurl, "/search/"), params={"Keyword": songtitle, "Aselect": 2}).text, "lxml").find_all("tbody")
    tag_tr = tag_tbody[0].find_all("tr")
    data = []
    for i in tag_tr:
        aaa = []
        td = i.find_all("td")
        aaa.append(p.sub("", unicode(td[0])))
        aaa.append(p.sub("", unicode(td[1])))
        aaa.append(td[0].find("a")["href"])
        data.append(aaa)
except:
    print "Not Found"
    exit()

if len(data) != 1:
    for i, x in enumerate(data):
        print "%s: %s - %s" % (i, x[0], x[1])
    num = raw_input(">>>")
    try:
        num = int(num)
        song = data[num]
    except:
        print "error"
        exit()
else:
    song = data[0]

text = ""
for i in BeautifulSoup(requests.get(createurl(baseurl, "/user/phplib/svg/showkasi.php"), params={"ID": song[2][6:-1]}).text, "lxml").find("g").find_all("text"):
    text += p.sub("", str(i)) + "\n"
if "&amp;" in text:
    text = text.replace("&amp;", "&")
if not os.path.isdir("lyrics"):
    os.mkdir("lyrics")
with open("./lyrics/%s.txt" % p2.sub("-", song[0]), "w") as f:
    f.write(text[:-1])