Merge pull request #91 from olof/topic/refactor_oppetarkiv

Break out OppetArkiv to subclass of Svtplay

lib/svtplay_dl/service/__init__.py

@@ -99,6 +99,7 @@ from svtplay_dl.service.ruv import Ruv
 from svtplay_dl.service.radioplay import Radioplay
 from svtplay_dl.service.sr import Sr
 from svtplay_dl.service.svtplay import Svtplay
+from svtplay_dl.service.oppetarkiv import OppetArkiv
 from svtplay_dl.service.tv4play import Tv4play
 from svtplay_dl.service.urplay import Urplay
 from svtplay_dl.service.viaplay import Viaplay
@@ -122,6 +123,7 @@ sites = [
     Radioplay,
     Sr,
     Svtplay,
+    OppetArkiv,
     Tv4play,
     Urplay,
     Viaplay,

lib/svtplay_dl/service/oppetarkiv.py

@@ -0,0 +1,35 @@
+# 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 sys
+import re
+
+from svtplay_dl.service.svtplay import Svtplay
+from svtplay_dl.log import log
+
+class OppetArkiv(Svtplay):
+    supported_domains = ['oppetarkiv.se']
+
+    def find_all_episodes(self, options):
+        page = 1
+        match = re.search(r'"http://www.oppetarkiv.se/etikett/titel/([^"/]+)', self.get_urldata())
+        if match is None:
+            match = re.search(r'"http://www.oppetarkiv.se/etikett/titel/([^"/]+)', self.url)
+            if match is None:
+                log.error("Couldn't find title")
+                sys.exit(2)
+        program = match.group(1)
+        more = True
+        episodes = []
+        while more:
+            url = "http://www.oppetarkiv.se/etikett/titel/%s/?sida=%s&sort=tid_stigande&embed=true" % (program, page)
+            data = get_http_data(url)
+            visa = re.search(r'svtXColorDarkLightGrey', data)
+            if not visa:
+                more = False
+            regex = re.compile(r'(http://www.oppetarkiv.se/video/[^"]+)')
+            for match in regex.finditer(data):
+                episodes.append(match.group(1))
+            page += 1
+
+        return episodes

lib/svtplay_dl/service/svtplay.py

@@ -17,7 +17,7 @@ from svtplay_dl.fetcher.http import download_http
 from svtplay_dl.log import log
 
 class Svtplay(Service, OpenGraphThumbMixin):
-    supported_domains = ['svtplay.se', 'svt.se', 'oppetarkiv.se', 'beta.svtplay.se', 'svtflow.se']
+    supported_domains = ['svtplay.se', 'svt.se', 'beta.svtplay.se', 'svtflow.se']
 
     def __init__(self, url):
         Service.__init__(self, url)
@@ -119,38 +119,12 @@ class Svtplay(Service, OpenGraphThumbMixin):
 
 
     def find_all_episodes(self, options):
-        parse = urlparse(self.url)
+        match = re.search(r'<link rel="alternate" type="application/rss\+xml" [^>]*href="([^"]+)"',
-        if parse.netloc == "www.oppetarkiv.se":
+                          self.get_urldata())
-            page = 1
+        if match is None:
-            match = re.search(r'"http://www.oppetarkiv.se/etikett/titel/([^"/]+)', self.get_urldata())
+            log.error("Couldn't retrieve episode list")
-            if match is None:
+            sys.exit(2)
-                match = re.search(r'"http://www.oppetarkiv.se/etikett/titel/([^"/]+)', self.url)
-                if match is None:
-                    log.error("Couldn't find title")
-                    sys.exit(2)
-            program = match.group(1)
-            more = True
-            episodes = []
-            while more:
-                url = "http://www.oppetarkiv.se/etikett/titel/%s/?sida=%s&sort=tid_stigande&embed=true" % (program, page)
-                data = get_http_data(url)
-                visa = re.search(r'svtXColorDarkLightGrey', data)
-                if not visa:
-                    more = False
-                regex = re.compile(r'(http://www.oppetarkiv.se/video/[^"]+)')
-                for match in regex.finditer(data):
-                    episodes.append(match.group(1))
-                page += 1
 
-            return episodes
+        xml = ET.XML(get_http_data(match.group(1)))
 
-        else:
+        return sorted(x.text for x in xml.findall(".//item/link"))
-            match = re.search(r'<link rel="alternate" type="application/rss\+xml" [^>]*href="([^"]+)"',
-                              self.get_urldata())
-            if match is None:
-                log.error("Couldn't retrieve episode list")
-                sys.exit(2)
-
-            xml = ET.XML(get_http_data(match.group(1)))
-
-            return sorted(x.text for x in xml.findall(".//item/link"))

lib/svtplay_dl/service/tests/oppetarkiv.py

@@ -0,0 +1,20 @@
+#!/usr/bin/python
+# ex:ts=4:sw=4:sts=4:et
+# -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
+
+# The unittest framwork doesn't play nice with pylint:
+#   pylint: disable-msg=C0103
+
+from __future__ import absolute_import
+import unittest
+from svtplay_dl.service.oppetarkiv import OppetArkiv
+
+class handlesTest(unittest.TestCase):
+    def handles_oppetarkiv_se_test(self):
+        self.assertTrue(OppetArkiv.handles(
+            "http://www.oppetarkiv.se/video/1129844/jacobs-stege-avsnitt-1-av-1"))
+
+    def handles_svtplay_se_test(self):
+        self.assertFalse(OppetArkiv.handles(
+            "http://www.svtplay.se/video/1090393/del-9"))
+

lib/svtplay_dl/service/tests/svtplay.py

@@ -20,7 +20,7 @@ class handlesTest(unittest.TestCase):
             "http://www.svt.se/nyheter/sverige/det-ar-en-dodsfalla"))
 
     def handles_oppetarkiv_se_test(self):
-        self.assertTrue(Svtplay.handles(
+        self.assertFalse(Svtplay.handles(
             "http://www.oppetarkiv.se/video/1129844/jacobs-stege-avsnitt-1-av-1"))
 
     def handles_dn_se_test(self):