From d24ace4c8fbe93a11133ddc1f4629b5626ec6bd8 Mon Sep 17 00:00:00 2001
From: luboss <lubos.katrinec@gmail.com>
Date: Fri, 2 Jun 2017 22:44:39 +0200
Subject: [PATCH 1/3] [Joj] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/joj.py        | 53 ++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)
 create mode 100755 youtube_dl/extractor/joj.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index ed603eb29..98b93d99d 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -463,6 +463,7 @@ from .jamendo import (
 )
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
+from .joj import JojIE
 from .jwplatform import JWPlatformIE
 from .jpopsukitv import JpopsukiIE
 from .kaltura import KalturaIE
diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py
new file mode 100755
index 000000000..dd04fae28
--- /dev/null
+++ b/youtube_dl/extractor/joj.py
@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class JojIE(InfoExtractor):
+    _VALID_URL = r'https?://(?P<prefix>[a-z0-9]+\.)joj\.sk/([^/]+/)*(?P<url_title>(?P<timestamp>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
+    _TESTS = [ {
+        'url': 'https://www.joj.sk/nove-byvanie/archiv/2017-05-28-nove-byvanie', # noqa
+        'md5': '731727f2caf35a3fcaf556853f92b6e1',
+        'info_dict': {
+            'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
+            'ext': 'mp4',
+            'title': '2017-05-28 - Nové Bývanie'
+        }
+    }, {
+        'url': 'http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia', # noqa
+        'md5': '13626f2d9e237a17ea72bcaaf2738311',
+        'info_dict': {
+            'id': 'f18b2c5f-9ea8-4941-a164-a814c53306ad',
+            'ext': 'mp4',
+            'title': '2016-09-06 - Starí Rodičia'
+        }
+    } ]
+        #       http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia
+        #       https://velkenoviny.joj.sk/archiv/2017-05-29-noviny-tv-joj
+    def _real_extract(self, url):
+        title_query = self._search_regex(self._VALID_URL, url, 'title_query',
+                                         group='url_title')
+        timestamp = self._search_regex(self._VALID_URL, url, 'timestamp',
+                                         group='timestamp', fatal=False)
+        # timestamp = '2017-05-28'
+        webpage = self._download_webpage(url, title_query)
+        title_simple = self._og_search_title(webpage).title()
+        title = "{timestamp} - {title_simple}".format(**locals())
+        video_id = self._html_search_regex(
+            r'<iframe src="https://media.joj.sk/embed/(?P<id>[^\?]+)', webpage,
+            'id')
+        xml_url = "https://media.joj.sk/services/Video.php?clip=" + video_id
+        xml_playlist = self._download_webpage(xml_url, title)
+        path_to_media = self._html_search_regex(
+            r'label="720p" path="(?P<path_to_media>[^"]+)"/>', xml_playlist,
+            'path_to_media', group='path_to_media')
+        media_url = 'http://n16.joj.sk/storage/' + path_to_media.replace('dat/', '', 1) # noqa
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': media_url
+            # 'display_id': ''
+            # 'description': self._og_search_description(webpage),
+        }

From 5f65d99ea21819ae4f7cc057dc131d7be07d04d7 Mon Sep 17 00:00:00 2001
From: luboss <lubos.katrinec@gmail.com>
Date: Sun, 18 Jun 2017 20:07:23 +0200
Subject: [PATCH 2/3] [Joj] Code cleanup

---
 youtube_dl/extractor/joj.py | 63 +++++++++++++++++++------------------
 1 file changed, 33 insertions(+), 30 deletions(-)

diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py
index dd04fae28..601402f39 100755
--- a/youtube_dl/extractor/joj.py
+++ b/youtube_dl/extractor/joj.py
@@ -2,52 +2,55 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+import re
 
 
 class JojIE(InfoExtractor):
-    _VALID_URL = r'https?://(?P<prefix>[a-z0-9]+\.)joj\.sk/([^/]+/)*(?P<url_title>(?P<timestamp>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
-    _TESTS = [ {
+    _VALID_URL = r'https?://([a-z0-9]+\.)joj\.sk/([^/]+/)*(?P<title_query>(?P<release_date>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
+    _TESTS = [{
         'url': 'https://www.joj.sk/nove-byvanie/archiv/2017-05-28-nove-byvanie', # noqa
-        'md5': '731727f2caf35a3fcaf556853f92b6e1',
         'info_dict': {
             'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
             'ext': 'mp4',
-            'title': '2017-05-28 - Nové Bývanie'
+            'title': 'Nové Bývanie',
+            'release_date': '20170528'
         }
     }, {
-        'url': 'http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia', # noqa
-        'md5': '13626f2d9e237a17ea72bcaaf2738311',
+        'url': 'http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia',
         'info_dict': {
             'id': 'f18b2c5f-9ea8-4941-a164-a814c53306ad',
             'ext': 'mp4',
-            'title': '2016-09-06 - Starí Rodičia'
+            'title': 'Starí Rodičia',
+            'release_date': '20160906'
         }
-    } ]
-        #       http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia
-        #       https://velkenoviny.joj.sk/archiv/2017-05-29-noviny-tv-joj
+    }]
+
+    media_src_url = 'http://n16.joj.sk/storage/'
+    xml_source_url = 'https://media.joj.sk/services/Video.php?clip='
+
     def _real_extract(self, url):
-        title_query = self._search_regex(self._VALID_URL, url, 'title_query',
-                                         group='url_title')
-        timestamp = self._search_regex(self._VALID_URL, url, 'timestamp',
-                                         group='timestamp', fatal=False)
-        # timestamp = '2017-05-28'
-        webpage = self._download_webpage(url, title_query)
-        title_simple = self._og_search_title(webpage).title()
-        title = "{timestamp} - {title_simple}".format(**locals())
+        mobj = re.match(self._VALID_URL, url)
+        title_query = mobj.group('title_query')
+        release_date = mobj.group('release_date').replace('-', '')
+        webpage = self._download_webpage(url, 'video_id')
         video_id = self._html_search_regex(
-            r'<iframe src="https://media.joj.sk/embed/(?P<id>[^\?]+)', webpage,
-            'id')
-        xml_url = "https://media.joj.sk/services/Video.php?clip=" + video_id
-        xml_playlist = self._download_webpage(xml_url, title)
-        path_to_media = self._html_search_regex(
-            r'label="720p" path="(?P<path_to_media>[^"]+)"/>', xml_playlist,
-            'path_to_media', group='path_to_media')
-        media_url = 'http://n16.joj.sk/storage/' + path_to_media.replace('dat/', '', 1) # noqa
+            r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P<video_id>[a-f0-9\-]+)', webpage,
+            'id', group='video_id', default=None)
+        print(video_id)
+        xml_playlist_url = self.xml_source_url + video_id
+        xml_playlist_et = self._download_xml(xml_playlist_url, title_query)
+        formats = []
+        for file_el in xml_playlist_et.iter('file'):
+            formats.append({'height': file_el.attrib['id'].replace('p', ''),
+                            'url': self.media_src_url + file_el.attrib['path'].replace(  # noqa
+                                'dat/', '', 1)})
+
+        def get_height(d):
+            return d.get('height')
 
         return {
             'id': video_id,
-            'title': title,
-            'url': media_url
-            # 'display_id': ''
-            # 'description': self._og_search_description(webpage),
+            'title': self._og_search_title(webpage).title(),
+            'formats': sorted(formats, key=get_height),
+            'release_date': release_date
         }

From f6cff4b6f02520daeed24a4fcff583ac2ff6168b Mon Sep 17 00:00:00 2001
From: luboss <lubos.katrinec@gmail.com>
Date: Mon, 3 Jul 2017 20:58:35 +0200
Subject: [PATCH 3/3] [Joj] * fixed broken compatibility with Python 2.6 [Joj]
 * removed debug output [Joj] * removed parsing unimportant title_query [Joj]
 * fixed sorting formats

---
 youtube_dl/extractor/joj.py | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py
index 601402f39..2ebfec902 100755
--- a/youtube_dl/extractor/joj.py
+++ b/youtube_dl/extractor/joj.py
@@ -6,7 +6,7 @@ import re
 
 
 class JojIE(InfoExtractor):
-    _VALID_URL = r'https?://([a-z0-9]+\.)joj\.sk/([^/]+/)*(?P<title_query>(?P<release_date>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
+    _VALID_URL = r'https?://[a-z0-9]+\.joj\.sk/([^/]+/)*(?P<title_query>(?P<release_date>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
     _TESTS = [{
         'url': 'https://www.joj.sk/nove-byvanie/archiv/2017-05-28-nove-byvanie', # noqa
         'info_dict': {
@@ -30,27 +30,27 @@ class JojIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        title_query = mobj.group('title_query')
         release_date = mobj.group('release_date').replace('-', '')
-        webpage = self._download_webpage(url, 'video_id')
+        webpage = self._download_webpage(url, 'id')
         video_id = self._html_search_regex(
-            r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P<video_id>[a-f0-9\-]+)', webpage,
-            'id', group='video_id', default=None)
-        print(video_id)
+            r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P<video_id>[a-f0-9\-]+)',
+            webpage, 'id', group='video_id')
         xml_playlist_url = self.xml_source_url + video_id
-        xml_playlist_et = self._download_xml(xml_playlist_url, title_query)
+        xml_playlist_et = self._download_xml(xml_playlist_url, 'XML playlist')
         formats = []
-        for file_el in xml_playlist_et.iter('file'):
-            formats.append({'height': file_el.attrib['id'].replace('p', ''),
+        for file_el in xml_playlist_et.findall('files/file'):
+            try:
+                height = int(file_el.attrib['id'].replace('p', ''))
+            except ValueError:
+                height = 0
+            formats.append({'height': height,
                             'url': self.media_src_url + file_el.attrib['path'].replace(  # noqa
                                 'dat/', '', 1)})
-
-        def get_height(d):
-            return d.get('height')
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': self._og_search_title(webpage).title(),
-            'formats': sorted(formats, key=get_height),
+            'formats': formats,
             'release_date': release_date
         }