使用Python的XMLTV EPG指南数据

Question

我有一个python脚本，它可以端到端地运行，并为Kodi EPG生成看起来有效的XMLTV指南数据(尽管这是我第一次尝试创建这样的数据)：

Tv_guide类：

def __init__(self, start, end, args, kwargs):

    self.start = 1
    self.end = 3000


global i, channel_list, url_list, date_check, image_list, super_list, epg_list

channel_list = []
url_list = []
date_check = []
image_list = []
super_list = []
epg_list = []

for i in range(66, 67):

    global div_list
    div_list = []

    time.sleep(1)


    def session_setup():


        global r, html


        SelectProxy.select_proxy()
        local_proxy = SelectProxy.global_proxy

        session = requests.Session()
        session.proxies = {local_proxy}

        url = ['http://www.tvguide.co.uk/mobile/channellisting.asp?ch=', str(i)]
        url = ''.join(url)

        if url not in url_list:

            url_list.append(url)

        headers ={
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
        'Accept-Encoding': 'gzip, deflate',
        'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.',
        'Connection': 'keep-alive',
        'Host': 'www.tvguide.co.uk',
        'Referer': 'http://www.tvguide.co.uk/mobile/',
        'Upgrade-Insecure-Requests': '1',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
        }

        r = session.get(url, headers=headers)

        html = r.content

    session_setup()


    def soup_scanner():


        global soup
        global channel, image4, div_list2

        time.sleep(1)

        soup = BeautifulSoup(r.text, "html.parser")


        try:

            channel = soup.find('h1').text

            for div in soup.select('div'):

                if not div.script:

                    for image in div.find_all('img'):

                        image2 = re.search(r' src="\S+?"', str(image))
                        image2 = image2.group(0)
                        image3 = image2.split('src="')[1]
                        image4a = image3.split('"')[0]

                        div_list.append(image4a)

            div_list2 = ''
            div_list2 = div_list[3]


        except Exception as exc:

            pass


    soup_scanner()


    def soup_parser():


        global joined_list, joined_list2, date, time_list, desc_list, rating_list, date_list


        rolling_date = soup.find_all('h2')

        joined_list2 = []


        for x in soup.select('table'):

            time_list = []
            desc_list = []
            rating_list = []
            date_list = []
            joined_list = []

            xdate = rolling_date[0].text
            rolling_date.pop(0)


            for tr in x.select('tr'):

                if not tr.script:


                    for td in tr.find_all('td'):

                        date_list.append(xdate)

                        a = ''.join(re.sub(r'\s+', ' ', td.text))
                        b = a.strip()


                        if b[:1] in '0123456789':


                            time_list.append(b)


                        else:

                            if ' Rating' in b:

                                c = b.split(' Rating')

                            else:

                                c = b.split(' Rating')
                                c.append(0.0)

                            desc = c[0]
                            desc_list.append(desc)


                            rating = ''.join(['Rating: ', str(c[1])])
                            rating_list.append(rating)



            try:

                time_list_lag = time_list[:]
                del time_list_lag[0]
                joined_list = zip(time_list, time_list_lag, desc_list, rating_list, date_list)
                joined_list2.append(joined_list)


            except Exception as exc:

                print traceback.format_exc() 
                pass


    soup_parser()


    def soup_to_text():


        global cat_list, super_list2


        for sub in joined_list2:

            for e in sub:

                super_list2 = []

                now = datetime.now()

                if channel not in channel_list:

                    channel_list.append(channel)

                if date not in date_check:

                    date_check.append(date)

                if div_list2 not in image_list:

                    image_list.append(div_list2)

                super_list2.append(channel)
                super_list2.append(div_list2)
                super_list2.append('http://www.tv.sky.com')
                super_list2.append(date)


                try:

                    starttime = datetime.strptime(' '.join([str(now.year), e[4], e[0]]), '%Y %a %d %b %H:%M%p').strftime('%Y%m%d%H%M%S')
                    endtime = datetime.strptime(' '.join([str(now.year), e[4], e[1]]), '%Y %a %d %b %H:%M%p').strftime('%Y%m%d%H%M%S')

                    global epg_data

                    clean_channel = str(channel).replace('&', '&')
                    clean_e2 = str(e[2]).replace('&', '&')
                    clean_e3 = str(e[3]).replace('&', '&')



                    epg_data = ''.join(['<program start="',starttime,' +0200" stop="',endtime,' +0200" channel="',clean_channel,'">','<desc lang="eng">',clean_e2,' ',clean_e3,'</desc>','<icon src="',div_list2,'" />', \
                           '<country>UK</country>','</program>'])

                    epg_list.append(epg_data)


                except Exception as exc:

                    pass
                    #print e
                    #print traceback.format_exc()


            super_list.append(super_list2)
            cat_list = zip(channel_list, date_check, url_list, image_list)


    soup_to_text()

print '**********************************************************************************************************************************************************************'


print '<?xml version="1.0" encoding="UTF-8"?>'
print'<tv generator-info-name="TV Guide Scraper - by Aaron Aardvark" generator-info-url="http://www.aaardvark.com">'

for superx in super_list:

    print ''.join(['<channel id="',str(superx[0]),'">'])
    print ''.join(['<display-name lang="en">',str(superx[0]),'</display-name>'])
    print ''.join(['<icon src="',str(superx[1]),'" />'])
    print ''.join(['<url>',str(superx[2]),'</url>'])
    print ''.join(['</channel>'])

for epg in epg_list:

    print epg

print '</tv>'

为了测试它，我现在只抓取了一个通道。我在NextPVR后端和一个在线解析工具中都进行了尝试，并获得了相同的结果。我的输出正确地生成了一个频道列表，但没有节目数据。

我已经将我精简后的输出包括在下面。有没有人看到我做错了什么？

谢谢

<?xml version="1.0" encoding="UTF-8"?>
<tv generator-info-name="TV Guide Scraper - by Aaron Aardvark" generator-info-url="http://www.aaardvark.com">
<channel id="BBC News">
<display-name lang="en">BBC News</display-name>
<icon src="http://my.tvguide.co.uk/channel_logos/60x35/66.png" />
<url>http://www.tv.sky.com</url>
</channel>
<program start="20180506060000 +0200" stop="20180506070000 +0200" channel="BBC News"><desc lang="eng">Breakfast A round-up of national and international news, plus sports reports, weather forecasts and arts and entertainment features (Subtitles) Rating: : 1.5</desc><icon src="http://my.tvguide.co.uk/channel_logos/60x35/66.png" /><country>UK</country></program>
</tv>

Answer 1

如果有人遇到同样的问题，最终解决了这个问题。标记应为<programme>，而不是<program>。