[shahid] try to bypass geo restriction and extract more metadata(closes #10062)

youtube_dl/extractor/shahid.py

@@ -2,11 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
+    str_or_none,
 )
 
 
@@ -33,45 +33,27 @@ class ShahidIE(InfoExtractor):
         'only_matching': True
     }]
 
-    def _handle_error(self, response):
+    def _call_api(self, path, video_id, note):
-        if not isinstance(response, dict):
+        data = self._download_json(
-            return
+            'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={
-        error = response.get('error')
+                'apiKey': 'sh@hid0nlin3',
+                'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
+            }).get('data', {})
+
+        error = data.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'):
+        return data
-        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)
 
-        webpage = self._download_webpage(url, video_id)
+        player = self._call_api(
-
+            'Content/Episode/%s' % video_id,
-        api_vars = {
+            video_id, 'Downloading player JSON')
-            'id': video_id,
-            'type': 'player',
-            'url': 'http://api.shahid.net/api/v1_1',
-            'playerType': 'episode',
-        }
-
-        flashvars = self._search_regex(
-            r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
-        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')
 
         if player.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
@@ -79,22 +61,11 @@ def _real_extract(self, url):
         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
         self._sort_formats(formats)
 
-        video = self._download_json(
+        video = self._call_api(
-            '%s/%s/%s?%s' % (
+            'episode/%s' % video_id, video_id,
-                api_vars['url'], api_vars['playerType'], api_vars['id'],
+            'Downloading video JSON')['episode']
-                compat_urllib_parse_urlencode({
-                    'apiKey': 'sh@hid0nlin3',
-                    'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-                })),
-            video_id, 'Downloading video JSON')
-
-        video = video[api_vars['playerType']]
 
         title = video['title']
-        description = video.get('description')
-        thumbnail = video.get('thumbnailUrl')
-        duration = int_or_none(video.get('duration'))
-        timestamp = parse_iso8601(video.get('referenceDate'))
         categories = [
             category['name']
             for category in video.get('genres', []) if 'name' in category]
@@ -102,10 +73,16 @@ def _real_extract(self, url):
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': video.get('description'),
-            'thumbnail': thumbnail,
+            'thumbnail': video.get('thumbnailUrl'),
-            'duration': duration,
+            'duration': int_or_none(video.get('duration')),
-            'timestamp': timestamp,
+            'timestamp': parse_iso8601(video.get('referenceDate')),
             'categories': categories,
+            'series': video.get('showTitle') or video.get('showName'),
+            'season': video.get('seasonTitle'),
+            'season_number': int_or_none(video.get('seasonNumber')),
+            'season_id': str_or_none(video.get('seasonId')),
+            'episode_number': int_or_none(video.get('number')),
+            'episode_id': video_id,
             'formats': formats,
         }