gistfile1.py

def urlinformation():
    titlelist = []
    genrelist = []
    valuelist = []

    lists = (
        titlelist,
        genrelist,
        valuelist,
    )


    idlist = ['0091209', '0111161']
    for i in idlist:
        headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}
        req = urllib2.Request("http://www.imdb.com/title/tt"+i+"/", headers=headers)
        html = urllib2.urlopen("http://www.imdb.com/title/tt"+i+"/", timeout = 30).read()
        soup = BeautifulSoup(html)

        nameTag = soup.findAll("title")
        genreTag = soup.findAll("span",{"itemprop":"genre"})
        ratingTag = soup.findAll("span",{"itemprop":"ratingValue"})

        tags = (
            nameTag,
            genreTag,
            ratingTag,
        )

        def TEXT(tag):
            return tag.find(text=True)

        for tag_list, result in zip( tags, lists ):
            tag_str = ",".join(map( TEXT, tag_list))
            result.append(tag_str)

    return zip( * lists )