[ie/youtube] Extract upload timestamp if available (#9856)

[yt-dlp.git] / yt_dlp / extractor / shahid.py

diff --git a/yt_dlp/extractor/shahid.py b/yt_dlp/extractor/shahid.py
index 8cbb620ed944895d8cb3096e1922c176cdd7dbb5..89aee27280005f56c08db1ae198833ad3f1e246a 100644 (file)
--- a/yt_dlp/extractor/shahid.py
+++ b/yt_dlp/extractor/shahid.py
@@ -1,16 +1,13 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import json
 import math
 import re
 
 from .aws import AWSIE
-from ..compat import compat_HTTPError
+from ..networking.exceptions import HTTPError
 from ..utils import (
-    clean_html,
     ExtractorError,
     InAdvancePagedList,
+    clean_html,
     int_or_none,
     parse_iso8601,
     str_or_none,
@@ -21,10 +18,11 @@
 class ShahidBaseIE(AWSIE):
     _AWS_PROXY_HOST = 'api2.shahid.net'
     _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
+    _VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'
 
     def _handle_error(self, e):
         fail_data = self._parse_json(
-            e.cause.read().decode('utf-8'), None, fatal=False)
+            e.cause.response.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')])
@@ -42,14 +40,14 @@ def _call_api(self, path, video_id, request=None):
                 'secret_key': '4WUUJWuFvtTkXbhaWTDv7MhO+0LqoYDWfEnUXoWn',
             }, video_id, query)
         except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError):
+            if isinstance(e.cause, HTTPError):
                 self._handle_error(e)
             raise
 
 
 class ShahidIE(ShahidBaseIE):
     _NETRC_MACHINE = 'shahid'
-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
+    _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
         'info_dict': {
@@ -73,25 +71,24 @@ class ShahidIE(ShahidBaseIE):
         # shahid plus subscriber only
         '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
+    }, {
+        'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
+        'only_matching': True
     }]
 
-    def _real_initialize(self):
-        email, password = self._get_login_info()
-        if email is None:
-            return
-
+    def _perform_login(self, username, password):
         try:
             user_data = self._download_json(
                 'https://shahid.mbc.net/wd/service/users/login',
                 None, 'Logging in', data=json.dumps({
-                    'email': email,
+                    'email': username,
                     '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):
+            if isinstance(e.cause, HTTPError):
                 self._handle_error(e)
             raise
 
@@ -107,7 +104,7 @@ def _real_initialize(self):
             }))
 
     def _real_extract(self, url):
-        page_type, video_id = re.match(self._VALID_URL, url).groups()
+        page_type, video_id = self._match_valid_url(url).groups()
         if page_type == 'clip':
             page_type = 'episode'
 
@@ -115,13 +112,12 @@ def _real_extract(self, url):
             'playout/new/url/' + video_id, video_id)['playout']
 
         if not self.get_param('allow_unplayable_formats') and playout.get('drm'):
-            raise ExtractorError('This video is DRM protected.', expected=True)
+            self.report_drm(video_id)
 
         formats = self._extract_m3u8_formats(re.sub(
             # https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
             r'aws\.manifestfilter=[\w:;,-]+&?',
             '', playout['url']), video_id, 'mp4')
-        self._sort_formats(formats)
 
         # video = self._call_api(
         #     'product/id', video_id, {
@@ -168,7 +164,7 @@ def _real_extract(self, url):
 
 
 class ShahidShowIE(ShahidBaseIE):
-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
+    _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?: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': {