svtplay-dl/lib/svtplay_dl/service/svtplay.py

# ex:ts=4:sw=4:sts=4:et
# -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
from __future__ import absolute_import
import re
import json
import os
import xml.etree.ElementTree as ET
import copy
from svtplay_dl.service import Service, OpenGraphThumbMixin
from svtplay_dl.utils import get_http_data, filenamify
from svtplay_dl.utils.urllib import urlparse
from svtplay_dl.fetcher.hds import hdsparse
from svtplay_dl.fetcher.hls import HLS, hlsparse
from svtplay_dl.fetcher.rtmp import RTMP
from svtplay_dl.fetcher.http import HTTP
from svtplay_dl.subtitle import subtitle
from svtplay_dl.log import log

class Svtplay(Service, OpenGraphThumbMixin):
    supported_domains = ['svtplay.se', 'svt.se', 'beta.svtplay.se', 'svtflow.se']

    def __init__(self, url):
        Service.__init__(self, url)
        self.subtitle = None

    def get(self, options):
        if re.findall("svt.se", self.url):
            error, data = self.get_urldata()
            if error:
                log.error("Can't get the page")
                return
            match = re.search(r"data-json-href=\"(.*)\"", data)
            if match:
                filename = match.group(1).replace("&", "&").replace("&format=json", "")
                url = "http://www.svt.se%s" % filename
            else:
                log.error("Can't find video file for: %s", self.url)
                return
        else:
            url = self.url

        pos = url.find("?")
        if pos < 0:
            dataurl = "%s?&output=json&format=json" % url
        else:
            dataurl = "%s&output=json&format=json" % url
        error, data = get_http_data(dataurl)
        if error:
            log.error("Can't get api page. this is a bug.")
            return
        data = json.loads(data)
        if "live" in data["video"]:
            options.live = data["video"]["live"]
        else:
            options.live = False

        if options.output_auto:
            directory = os.path.dirname(options.output)
            options.service = "svtplay"

            name = data["statistics"]["folderStructure"]
            if name.find(".") > 0:
                title = "%s-%s-%s-%s" % (name[:name.find(".")], data["statistics"]["title"], data["videoId"], options.service)
            else:
                title = "%s-%s-%s-%s" % (name, data["statistics"]["title"], data["videoId"], options.service)
            title = filenamify(title)
            if len(directory):
                options.output = "%s/%s" % (directory, title)
            else:
                options.output = title

        if self.exclude(options):
            return

        if data["video"]["subtitleReferences"]:
            try:
                suburl = data["video"]["subtitleReferences"][0]["url"]
            except KeyError:
                pass
            if suburl and len(suburl) > 0:
                yield subtitle(copy.copy(options), "wrst", suburl)

        if options.force_subtitle:
            return

        for i in data["video"]["videoReferences"]:
            parse = urlparse(i["url"])

            if parse.path.find("m3u8") > 0:
                streams = hlsparse(i["url"])
                for n in list(streams.keys()):
                    yield HLS(copy.copy(options), streams[n], n)
            elif parse.path.find("f4m") > 0:
                match = re.search(r"\/se\/secure\/", i["url"])
                if not match:
                    parse = urlparse(i["url"])
                    manifest = "%s://%s%s?%s&hdcore=3.3.0" % (parse.scheme, parse.netloc, parse.path, parse.query)
                    streams = hdsparse(copy.copy(options), manifest)
                    if streams:
                        for n in list(streams.keys()):
                            yield streams[n]
            elif parse.scheme == "rtmp":
                embedurl = "%s?type=embed" % url
                error, data = get_http_data(embedurl)
                match = re.search(r"value=\"(/(public)?(statiskt)?/swf(/video)?/svtplayer-[0-9\.a-f]+swf)\"", data)
                swf = "http://www.svtplay.se%s" % match.group(1)
                options.other = "-W %s" % swf
                yield RTMP(copy.copy(options), i["url"], i["bitrate"])
            else:
                yield HTTP(copy.copy(options), i["url"], "0")

    def find_all_episodes(self, options):
        match = re.search(r'<link rel="alternate" type="application/rss\+xml" [^>]*href="([^"]+)"',
                          self.get_urldata()[1])
        if match is None:
            log.error("Couldn't retrieve episode list")
            return
        error, data = get_http_data(match.group(1))
        if error:
            log.error("Cant get rss page")
            return
        xml = ET.XML(data)

        episodes = [x.text for x in xml.findall(".//item/link")]
        episodes_new = []
        n = 1
        for i in episodes:
            episodes_new.append(i)
            if n == options.all_last:
                break
            n += 1
        return sorted(episodes_new)