[shahid] Improve and simplify

youtube_dl/extractor/shahid.py

@@ -2,17 +2,17 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
 from ..utils import (
-    js_to_json,
     ExtractorError,
-    int_or_none
+    int_or_none,
+    parse_iso8601,
 )
 
 
 class ShahidIE(InfoExtractor):
     _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
-    _TESTS = [
+    _TESTS = [{
-        {
         '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': '90574',
@@ -20,72 +20,88 @@ class ShahidIE(InfoExtractor):
             'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
             'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
             'duration': 2972,
+            'timestamp': 1422057420,
+            'upload_date': '20150123',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         }
-        },
+    }, {
-        {
         # 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
-        }
+    }]
-    ]
+
+    def _handle_error(self, response):
+        if not isinstance(response, dict):
+            return
+        error = response.get('error')
+        if error:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
+                expected=True)
+
+    def _download_json(self, url, video_id, note='Downloading JSON metadata'):
+        response = super(ShahidIE, self)._download_json(url, video_id, note)['data']
+        self._handle_error(response)
+        return response
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
 
-    _api_vars = {
+        webpage = self._download_webpage(url, video_id)
+
+        api_vars = {
+            'id': video_id,
             'type': 'player',
             'url': 'http://api.shahid.net/api/v1_1',
             'playerType': 'episode',
         }
 
-    def _real_extract(self, url):
+        flashvars = self._search_regex(
-        video_id = self._match_id(url)
+            r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
-        webpage = self._download_webpage(url, video_id)
+        if flashvars:
+            for key in api_vars.keys():
+                value = self._search_regex(
+                    r'\b%s\s*:\s*(?P<q>["\'])(?P<value>.+?)(?P=q)' % key,
+                    flashvars, 'type', default=None, group='value')
+                if value:
+                    api_vars[key] = value
+
+        player = self._download_json(
+            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
+            % (video_id, api_vars['type']), video_id, 'Downloading player JSON')
+
+        formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
 
-        player_info = ''
+        video = self._download_json(
-        flash_vars = self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars', None)
+            '%s/%s/%s?%s' % (
-        if flash_vars is not None:
+                api_vars['url'], api_vars['playerType'], api_vars['id'],
-            for line in flash_vars.splitlines():
+                compat_urllib_parse.urlencode({
-                if '+' not in line and '(' not in line and ')' not in line:
+                    'apiKey': 'sh@hid0nlin3',
-                    player_info += line
+                    'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-            player_info = self._parse_json(player_info, video_id, js_to_json, False)
+                }).encode('utf-8')),
-            if player_info is not None:
+            video_id, 'Downloading video JSON')
-                for key in self._api_vars:
-                    if key in player_info:
-                        self._api_vars[key] = player_info[key]
 
-        player_json_data = self._download_json(
+        video = video[api_vars['playerType']]
-            '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 player_json_data['error'].values():
-                raise ExtractorError(error)
-        formats = self._extract_m3u8_formats(m3u8_url, video_id)
 
-        video_info = self._download_json(
+        title = video['title']
-            self._api_vars['url'] + '/' + self._api_vars['playerType'] + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
+        description = video.get('description')
-            video_id
+        thumbnail = video.get('thumbnailUrl')
-        )['data']
+        duration = int_or_none(video.get('duration'))
-        if video_info.get('error'):
+        timestamp = parse_iso8601(video.get('referenceDate'))
-            for error in video_info['error']:
+        categories = [
-                raise ExtractorError(error)
+            category['name']
-        video_info = video_info[self._api_vars['playerType']]
+            for category in video.get('genres', []) if 'name' in category]
-        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,
+            'thumbnail': thumbnail,
             'duration': duration,
+            'timestamp': timestamp,
+            'categories': categories,
             'formats': formats,
         }