[dcn] add show extraction and support for other types of urls
authorremitamine <remitamine@gmail.com>
Wed, 2 Sep 2015 23:29:53 +0000 (00:29 +0100)
committerremitamine <remitamine@gmail.com>
Wed, 2 Sep 2015 23:29:53 +0000 (00:29 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/dcn.py

index 39b05ce8f8d5c239ccba04530c080e0f1eaa8dcf..d4a3e8ab087a819f33653ec343cd214801e4410d 100644 (file)
@@ -118,7 +118,11 @@ from .dailymotion import (
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
-from .dcn import DCNIE
+from .dcn import (
+    DCNGeneralIE,
+    DCNVideoIE,
+    DCNShowIE,
+)
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
index 82261e25c6e5e2126b2712bee5c23702e33144ba..352d35c7acab52f5c9ffa1076aa8685f772c37b6 100644 (file)
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
@@ -12,10 +14,33 @@ from ..utils import (
 )
 
 
-class DCNIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
+class DCNGeneralIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
+
+    def _real_extract(self, url):
+        show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
+        url = ''
+        ie_key = ''
+        if video_id and int(video_id) > 0:
+            url = 'http://www.dcndigital.ae/#/media/%s' % video_id
+            ie_key = 'DCNVideo'
+        else:
+            ie_key = 'DCNShow'
+            if season_id and int(season_id) > 0:
+                url = 'http://www.dcndigital.ae/#/program/season/%s' % season_id
+            else:
+                url = 'http://www.dcndigital.ae/#/program/%s' % show_id
+        return {
+            'url': url,
+            '_type': 'url',
+            'ie_key': ie_key
+        }
+
+
+class DCNVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media)/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887',
+        'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
         'info_dict':
         {
             'id': '17375',
@@ -82,3 +107,53 @@ class DCNIE(InfoExtractor):
             'timestamp': timestamp,
             'formats': formats,
         }
+
+
+class DCNShowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
+    _TEST = {
+        'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
+        'info_dict':
+        {
+            'id': '205024',
+            'title': 'محاضرات الشيخ الشعراوي',
+            'description': '',
+        },
+        'playlist_mincount': 27,
+    }
+
+    def _real_extract(self, url):
+        show_id, season_id = re.match(self._VALID_URL, url).groups()
+        data = {}
+        if season_id:
+            request = compat_urllib_request.Request(
+                'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
+                headers={'Origin': 'http://www.dcndigital.ae'})
+            season = self._download_json(request, season_id)
+            show_id = season['id']
+            data['season'] = season_id
+        data['show_id'] = show_id
+        request = compat_urllib_request.Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/show',
+            compat_urllib_parse.urlencode(data),
+            {
+                'Origin': 'http://www.dcndigital.ae',
+                'Content-Type': 'application/x-www-form-urlencoded'
+            })
+        show = self._download_json(request, show_id)
+        title = show['cat'].get('title_en') or show['cat']['title_ar']
+        description = show['cat'].get('description_en') or show['cat'].get('description_ar')
+        entries = []
+        for video in show['videos']:
+            entries.append({
+                'url': 'http://www.dcndigital.ae/#/media/%s' % video['id'],
+                '_type': 'url',
+                'ie_key': 'DCNVideo',
+            })
+        return {
+            'id': show_id,
+            'title': title,
+            'description': description,
+            'entries': entries,
+            '_type': 'playlist',
+        }