[shahid] add default fallbacks for extracting api vars

[youtube-dl] / youtube_dl / extractor / shahid.py

diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py
index d492070da43bbe8f39df2d56dbf527c73aa65915..39914018999a89bc9b56a1a8ac59d025b2d38559 100644 (file)
--- a/youtube_dl/extractor/shahid.py
+++ b/youtube_dl/extractor/shahid.py
@@ -1,16 +1,25 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
 from .common import InfoExtractor
-from ..utils import get_element_by_id
+from ..utils import (
+    js_to_json,
+    ExtractorError,
+    int_or_none
+)
+
 
 class ShahidIE(InfoExtractor):
     _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
     _TESTS = [
         {
-            'url': 'https://shahid.mbc.net/ar/episode/108084/%D8%AE%D9%88%D8%A7%D8%B7%D8%B1-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-11-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
+            'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
             'info_dict': {
-                'id': '108084',
+                'id': '90574',
                 'ext': 'm3u8',
-                'title': 'بسم الله',
-                'description': 'بسم الله'
+                'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
+                'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
+                'duration': 2972,
             },
             'params': {
                 # m3u8 download
@@ -18,39 +27,65 @@ class ShahidIE(InfoExtractor):
             }
         },
         {
-            #shahid plus subscriber only
-            'url': 'https://shahid.mbc.net/ar/series/90497/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011.html',
+            # shahid plus subscriber only
+            'url': 'https://shahid.mbc.net/ar/episode/90511/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
             'only_matching': True
         }
     ]
 
+    _api_vars = {
+        'type': 'player',
+        'url': 'http://api.shahid.net/api/v1_1',
+        'playerType': 'episode',
+    }
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        json_data = self._parse_json(
-            get_element_by_id('jsonld', webpage),
-            video_id
-        )
-        title = json_data['name']
-        thumbnail = json_data['image']
-        categories = json_data['genre']
-        description = json_data['description']
+
+        player_info = ''
+        flash_vars = self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars', None)
+        if flash_vars is not None:
+            for line in flash_vars.splitlines():
+                if '+' not in line and '(' not in line and ')' not in line:
+                    player_info += line
+            player_info = self._parse_json(player_info, video_id, js_to_json, False)
+            if player_info is not None:
+                for key in self._api_vars:
+                    if key in player_info:
+                        self._api_vars[key] = player_info[key]
+
         player_json_data = self._download_json(
-            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-'+video_id+'.type-player.html',
+            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + self._api_vars['type'] + '.html',
             video_id
         )['data']
         if 'url' in player_json_data:
             m3u8_url = player_json_data['url']
         else:
-            for error in json_data['error'].values():
-                self.report_warning(error)
-            return
+            for error in player_json_data['error'].values():
+                raise ExtractorError(error)
         formats = self._extract_m3u8_formats(m3u8_url, video_id)
+
+        video_info = self._download_json(
+            self._api_vars['url'] + '/' + self._api_vars['playerType'] + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
+            video_id
+        )['data']
+        if video_info.get('error'):
+            for error in video_info['error']:
+                raise ExtractorError(error)
+        video_info = video_info[self._api_vars['playerType']]
+        title = video_info['title']
+        thumbnail = video_info.get('thumbnailUrl')
+        categories = [category['name'] for category in video_info.get('genres')]
+        description = video_info.get('description')
+        duration = int_or_none(video_info.get('duration'))
+
         return {
             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
             'categories': categories,
             'description': description,
+            'duration': duration,
             'formats': formats,
         }