]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/shahid.py
Rapsys Git / youtubedl / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
New upstream version 2018.11.07
[youtubedl] / youtube_dl / extractor / shahid.py
diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py
index 62d41e88a1084c58af259176e28a8b2654ccd4ee..5c2a6206be752da16025ec714c8465e940ed8d68 100644 (file)
--- a/youtube_dl/extractor/shahid.py
+++ b/youtube_dl/extractor/shahid.py
@@ -1,45 +1,74 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import json
 import json
+import math
+import re
 
 
-from .common import InfoExtractor
+from .aws import AWSIE
 from ..compat import compat_HTTPError
 from ..utils import (
 from ..compat import compat_HTTPError
 from ..utils import (
+    clean_html,
     ExtractorError,
     ExtractorError,
+    InAdvancePagedList,
     int_or_none,
     parse_iso8601,
     str_or_none,
     urlencode_postdata,
     int_or_none,
     parse_iso8601,
     str_or_none,
     urlencode_postdata,
-    clean_html,
 )
 
 
 )
 
 
-class ShahidIE(InfoExtractor):
+class ShahidBaseIE(AWSIE):
+    _AWS_PROXY_HOST = 'api2.shahid.net'
+    _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
+
+    def _handle_error(self, e):
+        fail_data = self._parse_json(
+            e.cause.read().decode('utf-8'), None, fatal=False)
+        if fail_data:
+            faults = fail_data.get('faults', [])
+            faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
+            if faults_message:
+                raise ExtractorError(faults_message, expected=True)
+
+    def _call_api(self, path, video_id, request=None):
+        query = {}
+        if request:
+            query['request'] = json.dumps(request)
+        try:
+            return self._aws_execute_api({
+                'uri': '/proxy/v2/' + path,
+                'access_key': 'AKIAI6X4TYCIXM2B7MUQ',
+                'secret_key': '4WUUJWuFvtTkXbhaWTDv7MhO+0LqoYDWfEnUXoWn',
+            }, video_id, query)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                self._handle_error(e)
+            raise
+
+
+class ShahidIE(ShahidBaseIE):
     _NETRC_MACHINE = 'shahid'
     _NETRC_MACHINE = 'shahid'
-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?P<type>episode|movie)/(?P<id>\d+)'
+    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?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',
+        'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AC%D9%84%D8%B3-%D8%A7%D9%84%D8%B4%D8%A8%D8%A7%D8%A8-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-275286',
         'info_dict': {
         'info_dict': {
-            'id': '90574',
+            'id': '275286',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
-            'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
-            'duration': 2972,
-            'timestamp': 1422057420,
-            'upload_date': '20150123',
+            'title': 'مجلس الشباب الموسم 1 كليب 1',
+            'timestamp': 1506988800,
+            'upload_date': '20171003',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         }
     }, {
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         }
     }, {
-        'url': 'https://shahid.mbc.net/ar/movie/151746/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9.html',
+        'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
         'only_matching': True
     }, {
         # shahid plus subscriber only
         'only_matching': 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',
+        'url': 'https://shahid.mbc.net/ar/series/%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/episode-90511',
         'only_matching': True
     }]
 
         'only_matching': True
     }]
 
@@ -60,13 +89,7 @@ class ShahidIE(InfoExtractor):
                 })['user']
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
                 })['user']
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
-                fail_data = self._parse_json(
-                    e.cause.read().decode('utf-8'), None, fatal=False)
-                if fail_data:
-                    faults = fail_data.get('faults', [])
-                    faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
-                    if faults_message:
-                        raise ExtractorError(faults_message, expected=True)
+                self._handle_error(e)
             raise
 
         self._download_webpage(
             raise
 
         self._download_webpage(
@@ -80,37 +103,41 @@ class ShahidIE(InfoExtractor):
                 'sessionId': user_data['sessionId'],
             }))
 
                 'sessionId': user_data['sessionId'],
             }))
 
-    def _get_api_data(self, response):
-        data = response.get('data', {})
-
-        error = data.get('error')
-        if error:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
-                expected=True)
-
-        return data
-
     def _real_extract(self, url):
         page_type, video_id = re.match(self._VALID_URL, url).groups()
     def _real_extract(self, url):
         page_type, video_id = re.match(self._VALID_URL, url).groups()
+        if page_type == 'clip':
+            page_type = 'episode'
 
 
-        player = self._get_api_data(self._download_json(
-            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-player.html' % video_id,
-            video_id, 'Downloading player JSON'))
+        playout = self._call_api(
+            'playout/url/' + video_id, video_id)['playout']
 
 
-        if player.get('drm'):
+        if playout.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
             raise ExtractorError('This video is DRM protected.', expected=True)
 
-        formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
+        formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
         self._sort_formats(formats)
 
         self._sort_formats(formats)
 
-        video = self._get_api_data(self._download_json(
+        # video = self._call_api(
+        #     'product/id', video_id, {
+        #         'id': video_id,
+        #         'productType': 'ASSET',
+        #         'productSubType': page_type.upper()
+        #     })['productModel']
+
+        response = self._download_json(
             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
             video_id, 'Downloading video JSON', query={
                 'apiKey': 'sh@hid0nlin3',
                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
             video_id, 'Downloading video JSON', query={
                 'apiKey': 'sh@hid0nlin3',
                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-            }))[page_type]
+            })
+        data = response.get('data', {})
+        error = data.get('error')
+        if error:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
+                expected=True)
 
 
+        video = data[page_type]
         title = video['title']
         categories = [
             category['name']
         title = video['title']
         categories = [
             category['name']
@@ -132,3 +159,57 @@ class ShahidIE(InfoExtractor):
             'episode_id': video_id,
             'formats': formats,
         }
             'episode_id': video_id,
             'formats': formats,
         }
+
+
+class ShahidShowIE(ShahidBaseIE):
+    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
+        'info_dict': {
+            'id': '79187',
+            'title': 'رامز قرش البحر',
+            'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
+        },
+        'playlist_mincount': 32,
+    }, {
+        'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
+        'only_matching': True
+    }]
+    _PAGE_SIZE = 30
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+
+        product = self._call_api(
+            'playableAsset', show_id, {'showId': show_id})['productModel']
+        playlist = product['playlist']
+        playlist_id = playlist['id']
+        show = product.get('show', {})
+
+        def page_func(page_num):
+            playlist = self._call_api(
+                'product/playlist', show_id, {
+                    'playListId': playlist_id,
+                    'pageNumber': page_num,
+                    'pageSize': 30,
+                    'sorts': [{
+                        'order': 'DESC',
+                        'type': 'SORTDATE'
+                    }],
+                })
+            for product in playlist.get('productList', {}).get('products', []):
+                product_url = product.get('productUrl', []).get('url')
+                if not product_url:
+                    continue
+                yield self.url_result(
+                    product_url, 'Shahid',
+                    str_or_none(product.get('id')),
+                    product.get('title'))
+
+        entries = InAdvancePagedList(
+            page_func,
+            math.ceil(playlist['count'] / self._PAGE_SIZE),
+            self._PAGE_SIZE)
+
+        return self.playlist_result(
+            entries, show_id, show.get('title'), show.get('description'))
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...