debian/control: Update list of supported sites.

[youtubedl] / youtube_dl / extractor / shahid.py

diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py
index 1178b7a2781eb8809b99c78cce9fe80a33cafdd6..62d41e88a1084c58af259176e28a8b2654ccd4ee 100644 (file)
--- a/youtube_dl/extractor/shahid.py
+++ b/youtube_dl/extractor/shahid.py
@@ -1,17 +1,24 @@
 # 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_urllib_parse
+from ..compat import compat_HTTPError

 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
 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/(?P<type>episode|movie)/(?P<id>\d+)'

     _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': {
     _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': {


@@ -27,73 +34,84 @@ class ShahidIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
             # 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',
+        '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',
         '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',
         'only_matching': True
     }]
 

-    def _handle_error(self, response):
-        if not isinstance(response, dict):
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:

             return
             return

-        error = response.get('error')
+
+        try:
+            user_data = self._download_json(
+                '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']
+        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
+
+        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:
             raise ExtractorError(
                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
                 expected=True)
 
         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
+        return data

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
+        page_type, video_id = re.match(self._VALID_URL, url).groups()

 
 

-        api_vars = {
-            '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')
+        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'))

 
         if player.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
 
         if player.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')

+        self._sort_formats(formats)

 
 

-        video = self._download_json(
-            '%s/%s/%s?%s' % (
-                api_vars['url'], api_vars['playerType'], api_vars['id'],
-                compat_urllib_parse.urlencode({
-                    'apiKey': 'sh@hid0nlin3',
-                    'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-                })),
-            video_id, 'Downloading video JSON')
-
-        video = video[api_vars['playerType']]
+        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']
 
         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]
         categories = [
             category['name']
             for category in video.get('genres', []) if 'name' in category]


@@ -101,10 +119,16 @@ class ShahidIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
         return {
             'id': video_id,
             'title': title,

-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'description': video.get('description'),
+            'thumbnail': video.get('thumbnailUrl'),
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': parse_iso8601(video.get('referenceDate')),

             'categories': categories,
             '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,
         }
             'formats': formats,
         }