Mi media center - Foro

Código: Seleccionar todo

import re
import requests
import PyV8

def grab_cloudflare(url, *args, **kwargs):
    sess = requests.session()
    sess.headers["User-Agent"] = "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0"
    resp = sess.get(url, *args, **kwargs)
    url = resp.url
    page = resp.content

    if "a = document.getElementById('jschl-answer');" not in page:
      # Return page as it is; no Cloudflare protection detected
      return page

    # Otherwise, Cloudflare anti-bots is on
    domain = url.split("/")[2]

    challenge = re.search(r'name="jschl_vc" value="(\w+)"', page).group(1)

    builder = re.search(r"setTimeout.+?\r?\n([\s\S]+?a\.value =.+?)\r?\n", page).group(1)
    builder = re.sub(r"a\.value =(.+?) \+ .+?;", r"\1", builder)
    builder = re.sub(r"\s{3,}[a-z](?: = |\.).+", "", builder)

    with PyV8.JSContext() as ctxt:
      # Safely evaluate Javascript expression
      answer = str(int(ctxt.eval(builder)) + len(domain))

    params = {"jschl_vc": challenge, "jschl_answer": answer}
    submit_url = url + "/cdn-cgi/l/chk_jschl"
    return sess.get(submit_url, params=params, headers={"Referer": url}, *args, **kwargs).content, sess

Código: Seleccionar todo

def anti_cloudflare(url):
    # global headers

    try:
        resp_headers = scrapertools.get_headers_from_response(url, headers=headers)
        resp_headers = dict(resp_headers)
    except urllib2.HTTPError, e:
        resp_headers = e.headers

    if 'refresh' in resp_headers:
        time.sleep(int(resp_headers['refresh'][:1]))

        scrapertools.get_headers_from_response(host + '/' + resp_headers['refresh'][7:], headers=headers)

    return scrapertools.cache_page(url, headers=headers)

Código: Seleccionar todo

if "pelispedia" in scrapedurl and "/player/" in scrapedurl:

            data = scrapertools.cachePage(scrapedurl, headers=headers, device=item.device)

            try:
                matches = re.findall( 'sources: (\[\{.+\}\]),' , data)
                jsoncontent = matches[0]
            except:
                jsoncontent = None

            if jsoncontent:
                try:
                    array = json.loads(jsoncontent)
                except:
                    array = []


            try:
                matches = re.findall( 'tracks: \[\{file: "(.+)",label:' , data)
                subtitle = matches[0]
            except:
                subtitle = None

            for video in array:
                url = video['file']
                label = video['label']
                title = "Ver video en ["+label+"]"
                itemlist.append(Item(channel=__channel__, title=title, subtitle=subtitle, url=url, player="vlc" if subtitle else "native", server="directo", action="play", folder=False))

Código: Seleccionar todo

def play(item):
    logger.info("pelisalacarta.channels.pelispedia play url={0}".format(item.url))

    itemlist = []
    # Para videos flash y html5
    if "pelispedia.biz" in item.url:
        logger.info("estoy en el otro html5")
        key = scrapertools.find_single_match(item.url, 'v=([^&]+).+?imagen=([^&]+)')

        thumbnail = ""
        if len(key) > 1:
            thumbnail = key[1]
        headers.append(['Referer',item.extra])
        data = scrapertools.cache_page(item.url, headers=headers)

        media_url = scrapertools.find_single_match(data, '"file":"([^"]+)"').replace("\\","")
        sub = scrapertools.find_single_match(data, 'file:\s"([^"]+)".+?label:\s"Spanish"')
        itemlist.append(Item(channel=__channel__, title=item.title, url=media_url, server="directo", action="play",
                                 subtitle=sub, thumbnail=thumbnail))
    elif "pelispedia" in item.url:
        key = scrapertools.find_single_match(item.url, 'index.php\?id=([^&]+)&sub=([^&]+)&.+?imagen=([^&]+)')

        subtitle = ""
        thumbnail = ""

        if key[2] != "":
            thumbnail = key[2]
        if key[1] != "":
            url_sub = "http://www.pelispedia.tv/sub/%s.srt" % key[1]
            data_sub = anti_cloudflare(url_sub
            #Función que guarda los subs en un archivo y devuelve la ruta
            subtitle = save_sub(data_sub)
        if "Player_Html5" in item.url:
            url = "http://www.pelispedia.tv/Pe_Player_Html5/pk/pk1/plugins/protected.php"
            post = "fv=21&url="+urllib.quote(key[0])+"&sou=pic"
        else:
            url = "http://www.pelispedia.tv/Pe_flsh/plugins/gkpluginsphp.php"
            post = "link="+urllib.quote(key[0])
        data = scrapertools.cache_page(url, post=post, headers=headers)
        media_urls = scrapertools.find_multiple_matches(data, '(?:link|url)":"([^"]+)"')
        # Si hay varias urls se añade la última que es la de mayor calidad
        if len(media_urls) > 0:
            url = media_urls[len(media_urls)-1].replace("\\", "")
            itemlist.append(Item(channel=__channel__, title=item.title, url=url, server="directo", action="play",
                                 subtitle=subtitle, thumbnail=thumbnail))
    else:
        itemlist = servertools.find_video_items(data=item.url)
        for videoitem in itemlist:
            videoitem.title = item.title
            videoitem.channel = __channel__

    return itemlist