d/rules: Run offline tests.

[youtubedl] / youtube_dl / extractor / eagleplatform.py

diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py
index c2f593eca201a42f7023cc64d4237b5052fbc722..36fef07b72be4db2183f2ed5fdee63981781a688 100644 (file)
--- a/youtube_dl/extractor/eagleplatform.py
+++ b/youtube_dl/extractor/eagleplatform.py
@@ -4,13 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import (
-    compat_HTTPError,
-    compat_str,
-)
+from ..compat import compat_HTTPError

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

+    unsmuggle_url,
+    url_or_none,

 )
 
 
 )
 
 


@@ -31,7 +30,7 @@ class EaglePlatformIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Навальный вышел на свободу',
             'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
             'ext': 'mp4',
             'title': 'Навальный вышел на свободу',
             'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',

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

             'duration': 87,
             'view_count': int,
             'age_limit': 0,
             'duration': 87,
             'view_count': int,
             'age_limit': 0,


@@ -45,11 +44,15 @@ class EaglePlatformIE(InfoExtractor):
             'id': '12820',
             'ext': 'mp4',
             'title': "'O Sole Mio",
             'id': '12820',
             'ext': 'mp4',
             'title': "'O Sole Mio",

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

             'duration': 216,
             'view_count': int,
         },
         'skip': 'Georestricted',
             'duration': 216,
             'view_count': int,
         },
         'skip': 'Georestricted',

+    }, {
+        # referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
+        'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
+        'only_matching': True,

     }]
 
     @staticmethod
     }]
 
     @staticmethod


@@ -60,16 +63,40 @@ class EaglePlatformIE(InfoExtractor):
             webpage)
         if mobj is not None:
             return mobj.group('url')
             webpage)
         if mobj is not None:
             return mobj.group('url')

-        # Basic usage embedding (see http://dultonmedia.github.io/eplayer/)
+        PLAYER_JS_RE = r'''
+                        <script[^>]+
+                            src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
+                        .+?
+                    '''
+        # "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)

         mobj = re.search(
             r'''(?xs)
         mobj = re.search(
             r'''(?xs)

-                    <script[^>]+
-                        src=(?P<q1>["\'])(?:https?:)?//(?P<host>.+?\.media\.eagleplatform\.com)/player/player\.js(?P=q1)
-                    .+?
+                    %s

                     <div[^>]+
                     <div[^>]+

-                        class=(?P<q2>["\'])eagleplayer(?P=q2)[^>]+
+                        class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+

                         data-id=["\'](?P<id>\d+)
                         data-id=["\'](?P<id>\d+)

-            ''', webpage)
+            ''' % PLAYER_JS_RE, webpage)
+        if mobj is not None:
+            return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
+        # Generalization of "Javascript code usage", "Combined usage" and
+        # "Usage without attaching to DOM" embeddings (see
+        # http://dultonmedia.github.io/eplayer/)
+        mobj = re.search(
+            r'''(?xs)
+                    %s
+                    <script>
+                    .+?
+                    new\s+EaglePlayer\(
+                        (?:[^,]+\s*,\s*)?
+                        {
+                            .+?
+                            \bid\s*:\s*["\']?(?P<id>\d+)
+                            .+?
+                        }
+                    \s*\)
+                    .+?
+                    </script>
+            ''' % PLAYER_JS_RE, webpage)

         if mobj is not None:
             return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
 
         if mobj is not None:
             return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
 


@@ -79,9 +106,10 @@ class EaglePlatformIE(InfoExtractor):
         if status != 200:
             raise ExtractorError(' '.join(response['errors']), expected=True)
 
         if status != 200:
             raise ExtractorError(' '.join(response['errors']), expected=True)
 

-    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
+    def _download_json(self, url_or_request, video_id, *args, **kwargs):

         try:
         try:

-            response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
+            response = super(EaglePlatformIE, self)._download_json(
+                url_or_request, video_id, *args, **kwargs)

         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError):
                 response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError):
                 response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)


@@ -93,11 +121,24 @@ class EaglePlatformIE(InfoExtractor):
         return self._download_json(url_or_request, video_id, note)['data'][0]
 
     def _real_extract(self, url):
         return self._download_json(url_or_request, video_id, note)['data'][0]
 
     def _real_extract(self, url):

+        url, smuggled_data = unsmuggle_url(url, {})
+

         mobj = re.match(self._VALID_URL, url)
         host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
 
         mobj = re.match(self._VALID_URL, url)
         host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
 

+        headers = {}
+        query = {
+            'id': video_id,
+        }
+
+        referrer = smuggled_data.get('referrer')
+        if referrer:
+            headers['Referer'] = referrer
+            query['referrer'] = referrer
+

         player_data = self._download_json(
         player_data = self._download_json(

-            'http://%s/api/player_data?id=%s' % (host, video_id), video_id)
+            'http://%s/api/player_data' % host, video_id,
+            headers=headers, query=query)

 
         media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
 
 
         media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
 


@@ -134,7 +175,7 @@ class EaglePlatformIE(InfoExtractor):
             video_id, 'Downloading mp4 JSON', fatal=False)
         if mp4_data:
             for format_id, format_url in mp4_data.get('data', {}).items():
             video_id, 'Downloading mp4 JSON', fatal=False)
         if mp4_data:
             for format_id, format_url in mp4_data.get('data', {}).items():

-                if not isinstance(format_url, compat_str):
+                if not url_or_none(format_url):

                     continue
                 height = int_or_none(format_id)
                 if height is not None and m3u8_formats_dict.get(height):
                     continue
                 height = int_or_none(format_id)
                 if height is not None and m3u8_formats_dict.get(height):