urplay: Fix so we can download videos again

lib/svtplay_dl/service/urplay.py

@@ -4,8 +4,7 @@ import copy
 import json
 import logging
 import re
-from urllib.parse import urljoin
-from urllib.parse import urlparse
+from html import unescape
 
 from svtplay_dl.error import ServiceError
 from svtplay_dl.fetcher.hls import hlsparse
@@ -18,78 +17,50 @@ class Urplay(Service, OpenGraphThumbMixin):
     supported_domains = ["urplay.se", "ur.se", "betaplay.ur.se", "urskola.se"]
 
     def get(self):
-        data = self.get_urldata()
-        match = re.search(r"urPlayer.init\((.*)\);", data)
+        match = re.search(r'/Player/Player" data-react-props="([^\"]+)\"', self.get_urldata())
         if not match:
             yield ServiceError("Can't find json info")
             return
 
-        data = match.group(1)
+        data = unescape(match.group(1))
         jsondata = json.loads(data)
-        if len(jsondata["subtitles"]) > 0:
-            for sub in jsondata["subtitles"]:
-                if "label" in sub:
-                    absurl = urljoin(self.url, sub["file"].split(",")[0])
-                    if absurl.endswith("vtt"):
-                        subtype = "wrst"
-                    else:
-                        subtype = "tt"
-                    if self.config.get("get_all_subtitles"):
-                        yield subtitle(copy.copy(self.config), subtype, absurl, sub["label"], output=self.output)
-                    else:
-                        yield subtitle(copy.copy(self.config), subtype, absurl, output=self.output)
 
-        if "streamer" in jsondata["streaming_config"]:
-            basedomain = jsondata["streaming_config"]["streamer"]["redirect"]
-        else:
-            url = jsondata["streaming_config"]["loadbalancer"]
-            if url[:1] == "/":
-                url = "https:{}".format(url)
-            lbjson = self.http.request("get", url).text
-            lbjson = json.loads(lbjson)
-            basedomain = lbjson["redirect"]
-        http = "https://{}/{}".format(basedomain, jsondata["file_http"])
-        hd = None
-        if len(jsondata["file_http_hd"]) > 0:
-            http_hd = "https://{}/{}".format(basedomain, jsondata["file_http_hd"])
-            hls_hd = "{}{}".format(http_hd, jsondata["streaming_config"]["http_streaming"]["hls_file"])
-            hd = True
-        hls = "{}{}".format(http, jsondata["streaming_config"]["http_streaming"]["hls_file"])
-        streams = hlsparse(self.config, self.http.request("get", hls), hls, output=self.output)
+        res = self.http.get("https://streaming-loadbalancer.ur.se/loadbalancer.json")
+        loadbalancer = res.json()["redirect"]
+
+        for streaminfo in jsondata["currentProduct"]["streamingInfo"].keys():
+            stream = jsondata["currentProduct"]["streamingInfo"][streaminfo]
+            if stream["default"]:
+                url = "https://{}/{}playlist.m3u8".format(loadbalancer, stream["sd"]["location"])
+                streams = hlsparse(self.config, self.http.request("get", url), url, output=self.output)
                 for n in list(streams.keys()):
                     yield streams[n]
-        if hd:
-            streams = hlsparse(self.config, self.http.request("get", hls_hd), hls_hd, output=self.output)
+                url = "https://{}/{}playlist.m3u8".format(loadbalancer, stream["hd"]["location"])
+                streams = hlsparse(self.config, self.http.request("get", url), url, output=self.output)
                 for n in list(streams.keys()):
                     yield streams[n]
+                if not self.config.get("get_all_subtitles"):
+                    yield subtitle(copy.copy(self.config), "tt", stream["tt"]["location"], output=self.output)
+
+            if self.config.get("get_all_subtitles") and "tt" in stream:
+                label = stream["tt"]["language"]
+                if stream["tt"]["scope"] != "complete":
+                    label = "{}-{}".format(label, stream["tt"]["scope"])
+                yield subtitle(copy.copy(self.config), "tt", stream["tt"]["location"], label, output=self.output)
 
     def find_all_episodes(self, config):
-        parse = urlparse(self.url)
         episodes = []
 
-        if parse.netloc == "urskola.se":
-            data = self.get_urldata()
-            match = re.search('data-limit="[^"]+" href="([^"]+)"', data)
-            if match:
-                res = self.http.get(urljoin("https://urskola.se", match.group(1)))
-                data = res.text
-            tags = re.findall('<a class="puff program tv video" title="[^"]+" href="([^"]+)"', data)
-            for i in tags:
-                url = urljoin("https://urskola.se/", i)
-                if url not in episodes:
-                    episodes.append(url)
-        else:
-            match = re.search(r"/program/\d+-(\w+)-", parse.path)
+        match = re.search(r'/Player/Player" data-react-props="([^\"]+)\"', self.get_urldata())
         if not match:
-                logging.error("Can't find any videos")
-                return None
-            keyword = match.group(1)
-            all_links = re.findall('card-link" href="([^"]+)"', self.get_urldata())
-            for i in all_links:
-                match = re.search(r"/program/\d+-(\w+)-", i)
-                if match and match.group(1) == keyword:
-                    episodes.append(urljoin("https://urplay.se/", i))
+            logging.error("Can't find json info")
+            return
 
+        data = unescape(match.group(1))
+        jsondata = json.loads(data)
+
+        for episode in jsondata["accessibleEpisodes"]:
+            episodes.append("https://urplay.se/program/{}".format(episode["slug"]))
         episodes_new = []
         n = 0
         for i in episodes: