Import Debian changes 2020.01.24-0.1

[youtubedl] / youtube_dl / extractor / ivi.py

diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py
index 472d72b4c34fa3305b6b2808be1e45c6da25a60e..b5a740a01e1d360ca667869edef88f85e3559842 100644 (file)
--- a/youtube_dl/extractor/ivi.py
+++ b/youtube_dl/extractor/ivi.py
@@ -1,21 +1,26 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re

 import json
 import json

+import re
+import sys

 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,

-    sanitized_Request,
+    qualities,

 )
 
 
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
 )
 
 
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'

-    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['RU']
+    _LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c'
+    _LIGHT_URL = 'https://api.ivi.ru/light/'

 
     _TESTS = [
         # Single movie
 
     _TESTS = [
         # Single movie


@@ -28,7 +33,7 @@ class IviIE(InfoExtractor):
                 'title': 'Иван Васильевич меняет профессию',
                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                 'duration': 5498,
                 'title': 'Иван Васильевич меняет профессию',
                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                 'duration': 5498,

-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',

             },
             'skip': 'Only works from Russia',
         },
             },
             'skip': 'Only works from Russia',
         },


@@ -46,55 +51,128 @@ class IviIE(InfoExtractor):
                 'episode': 'Дело Гольдберга (1 часть)',
                 'episode_number': 1,
                 'duration': 2655,
                 'episode': 'Дело Гольдберга (1 часть)',
                 'episode_number': 1,
                 'duration': 2655,

-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',

             },
             'skip': 'Only works from Russia',
             },
             'skip': 'Only works from Russia',

-        }
+        },
+        {
+            # with MP4-HD720 format
+            'url': 'http://www.ivi.ru/watch/146500',
+            'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
+            'info_dict': {
+                'id': '146500',
+                'ext': 'mp4',
+                'title': 'Кукла',
+                'description': 'md5:ffca9372399976a2d260a407cc74cce6',
+                'duration': 5599,
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'skip': 'Only works from Russia',
+        },
+        {
+            'url': 'https://www.ivi.tv/watch/33560/',
+            'only_matching': True,
+        },

     ]
 
     # Sorted by quality
     ]
 
     # Sorted by quality

-    _KNOWN_FORMATS = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
+    _KNOWN_FORMATS = (
+        'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
+        'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

-        data = {
+        data = json.dumps({

             'method': 'da.content.get',
             'params': [
                 video_id, {
             'method': 'da.content.get',
             'params': [
                 video_id, {

-                    'site': 's183',
+                    'site': 's%d',

                     'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
                     'contentid': video_id
                 }
             ]
                     'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
                     'contentid': video_id
                 }
             ]

-        }
+        })

 
 

-        request = sanitized_Request(
-            'http://api.digitalaccess.ru/api/json/', json.dumps(data))
-        video_json = self._download_json(
-            request, video_id, 'Downloading video JSON')
+        bundled = hasattr(sys, 'frozen')

 
 

-        if 'error' in video_json:
-            error = video_json['error']
-            if error['origin'] == 'NoRedisValidData':
-                raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-            raise ExtractorError(
-                'Unable to download video %s: %s' % (video_id, error['message']),
-                expected=True)
+        for site in (353, 183):
+            content_data = (data % site).encode()
+            if site == 353:
+                if bundled:
+                    continue
+                try:
+                    from Cryptodome.Cipher import Blowfish
+                    from Cryptodome.Hash import CMAC
+                    pycryptodomex_found = True
+                except ImportError:
+                    pycryptodomex_found = False
+                    continue

 
 

-        result = video_json['result']
+                timestamp = (self._download_json(
+                    self._LIGHT_URL, video_id,
+                    'Downloading timestamp JSON', data=json.dumps({
+                        'method': 'da.timestamp.get',
+                        'params': []
+                    }).encode(), fatal=False) or {}).get('result')
+                if not timestamp:
+                    continue

 
 

-        formats = [{
-            'url': x['url'],
-            'format_id': x['content_format'],
-            'preference': self._KNOWN_FORMATS.index(x['content_format']),
-        } for x in result['files'] if x['content_format'] in self._KNOWN_FORMATS]
+                query = {
+                    'ts': timestamp,
+                    'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(),
+                }
+            else:
+                query = {}

 
 

-        self._sort_formats(formats)
+            video_json = self._download_json(
+                self._LIGHT_URL, video_id,
+                'Downloading video JSON', data=content_data, query=query)

 
 

+            error = video_json.get('error')
+            if error:
+                origin = error.get('origin')
+                message = error.get('message') or error.get('user_message')
+                extractor_msg = 'Unable to download video %s'
+                if origin == 'NotAllowedForLocation':
+                    self.raise_geo_restricted(message, self._GEO_COUNTRIES)
+                elif origin == 'NoRedisValidData':
+                    extractor_msg = 'Video %s does not exist'
+                elif site == 353:
+                    continue
+                elif bundled:
+                    raise ExtractorError(
+                        'This feature does not work from bundled exe. Run youtube-dl from sources.',
+                        expected=True)
+                elif not pycryptodomex_found:
+                    raise ExtractorError(
+                        'pycryptodomex not found. Please install it.',
+                        expected=True)
+                elif message:
+                    extractor_msg += ': ' + message
+                raise ExtractorError(extractor_msg % video_id, expected=True)
+            else:
+                break
+
+        result = video_json['result']

         title = result['title']
 
         title = result['title']
 

-        duration = int_or_none(result.get('duration'))
+        quality = qualities(self._KNOWN_FORMATS)
+
+        formats = []
+        for f in result.get('files', []):
+            f_url = f.get('url')
+            content_format = f.get('content_format')
+            if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format:
+                continue
+            formats.append({
+                'url': f_url,
+                'format_id': content_format,
+                'quality': quality(content_format),
+                'filesize': int_or_none(f.get('size_in_bytes')),
+            })
+        self._sort_formats(formats)
+

         compilation = result.get('compilation')
         episode = title if compilation else None
 
         compilation = result.get('compilation')
         episode = title if compilation else None
 


@@ -115,7 +193,7 @@ class IviIE(InfoExtractor):
             webpage, 'season number', default=None))
 
         episode_number = int_or_none(self._search_regex(
             webpage, 'season number', default=None))
 
         episode_number = int_or_none(self._search_regex(

-            r'<meta[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
+            r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',

             webpage, 'episode number', default=None))
 
         description = self._og_search_description(webpage, default=None) or self._html_search_meta(
             webpage, 'episode number', default=None))
 
         description = self._og_search_description(webpage, default=None) or self._html_search_meta(


@@ -131,7 +209,7 @@ class IviIE(InfoExtractor):
             'episode_number': episode_number,
             'thumbnails': thumbnails,
             'description': description,
             'episode_number': episode_number,
             'thumbnails': thumbnails,
             'description': description,

-            'duration': duration,
+            'duration': int_or_none(result.get('duration')),

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


@@ -161,7 +239,7 @@ class IviCompilationIE(InfoExtractor):
             self.url_result(
                 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
             for serie in re.findall(
             self.url_result(
                 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
             for serie in re.findall(

-                r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
+                r'<a\b[^>]+\bhref=["\']/watch/%s/(\d+)["\']' % compilation_id, html)]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)