debian/README.source: Add my preference with respect to patches.

[youtubedl] / youtube_dl / extractor / shahid.py

diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py
index ca286abb1f7df74c46a62f995475fa771245f282..374f7faf9d0becc45f8dd5e49d6774fc45b8e002 100644 (file)
--- a/youtube_dl/extractor/shahid.py
+++ b/youtube_dl/extractor/shahid.py
@@ -1,44 +1,88 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import re
+import json
+

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_HTTPError

 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
     str_or_none,
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
     str_or_none,

+    urlencode_postdata,
+    clean_html,

 )
 
 
 class ShahidIE(InfoExtractor):
 )
 
 
 class ShahidIE(InfoExtractor):

-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
+    _NETRC_MACHINE = 'shahid'
+    _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/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
+        'only_matching': True

     }, {
         # shahid plus subscriber only
     }, {
         # 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
     }]
 

-    def _call_api(self, path, video_id, note):
-        data = self._download_json(
-            'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={
-                'apiKey': 'sh@hid0nlin3',
-                'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-            }).get('data', {})
+    def _api2_request(self, *args, **kwargs):
+        try:
+            return self._download_json(*args, **kwargs)
+        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)
+            raise
+
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:
+            return
+
+        user_data = self._api2_request(
+            'https://shahid.mbc.net/wd/service/users/login',
+            None, 'Logging in', data=json.dumps({
+                'email': email,
+                'password': password,
+                'basic': 'false',
+            }).encode('utf-8'), headers={
+                'Content-Type': 'application/json; charset=UTF-8',
+            })['user']
+
+        self._download_webpage(
+            'https://shahid.mbc.net/populateContext',
+            None, 'Populate Context', data=urlencode_postdata({
+                'firstName': user_data['firstName'],
+                'lastName': user_data['lastName'],
+                'userName': user_data['email'],
+                'csg_user_name': user_data['email'],
+                'subscriberId': user_data['id'],
+                'sessionId': user_data['sessionId'],
+            }))
+
+    def _get_api_data(self, response):
+        data = response.get('data', {})

 
         error = data.get('error')
         if error:
 
         error = data.get('error')
         if error:


@@ -49,21 +93,26 @@ class ShahidIE(InfoExtractor):
         return data
 
     def _real_extract(self, url):
         return data
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
+        page_type, video_id = re.match(self._VALID_URL, url).groups()
+        if page_type == 'clip':
+            page_type = 'episode'

 
 

-        player = self._call_api(
-            'Content/Episode/%s' % video_id,
-            video_id, 'Downloading player JSON')
+        playout = self._api2_request(
+            'https://api2.shahid.net/proxy/v2/playout/url/' + video_id,
+            video_id, 'Downloading player JSON')['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._call_api(
-            'episode/%s' % video_id, video_id,
-            'Downloading video JSON')['episode']
+        video = self._get_api_data(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=',
+            }))[page_type]

 
         title = video['title']
         categories = [
 
         title = video['title']
         categories = [