Update upstream source from tag 'upstream/2019.06.08'

[youtubedl] / youtube_dl / extractor / moevideo.py

diff --git a/youtube_dl/extractor/moevideo.py b/youtube_dl/extractor/moevideo.py
index d930b96343bd081f029ad1bb7ce1ceee3c241f59..eb9b4ce7c5a3115ce9c1baf9c6b52294cfd95f61 100644 (file)
--- a/youtube_dl/extractor/moevideo.py
+++ b/youtube_dl/extractor/moevideo.py
@@ -1,15 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import json

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import compat_urllib_parse

 from ..utils import (
 from ..utils import (

-    ExtractorError,
+    clean_html,

     int_or_none,
     int_or_none,

-    sanitized_Request,

 )
 
 
 )
 
 


@@ -17,8 +14,8 @@ class MoeVideoIE(InfoExtractor):
     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?

-        (?:(?:moevideo|playreplay|videochart)\.net))/
-        (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)'''
+        (?:(?:moevideo|playreplay|videochart)\.net|thesame\.tv))/
+        (?:video|framevideo|embed)/(?P<id>[0-9a-z]+\.[0-9A-Za-z]+)'''

     _API_URL = 'http://api.letitbit.net/'
     _API_KEY = 'tVL0gjqo5'
     _TESTS = [
     _API_URL = 'http://api.letitbit.net/'
     _API_KEY = 'tVL0gjqo5'
     _TESTS = [


@@ -30,12 +27,13 @@ class MoeVideoIE(InfoExtractor):
                 'ext': 'flv',
                 'title': 'Sink cut out machine',
                 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
                 'ext': 'flv',
                 'title': 'Sink cut out machine',
                 'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',

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

                 'width': 540,
                 'height': 360,
                 'duration': 179,
                 'filesize': 17822500,
                 'width': 540,
                 'height': 360,
                 'duration': 179,
                 'filesize': 17822500,

-            }
+            },
+            'skip': 'Video has been removed',

         },
         {
             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
         },
         {
             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',


@@ -45,7 +43,7 @@ class MoeVideoIE(InfoExtractor):
                 'ext': 'flv',
                 'title': 'Operacion Condor.',
                 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
                 'ext': 'flv',
                 'title': 'Operacion Condor.',
                 'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',

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

                 'width': 480,
                 'height': 296,
                 'duration': 6027,
                 'width': 480,
                 'height': 296,
                 'duration': 6027,


@@ -56,58 +54,26 @@ class MoeVideoIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        host, video_id = re.match(self._VALID_URL, url).groups()

 
         webpage = self._download_webpage(
 
         webpage = self._download_webpage(

-            'http://%s/video/%s' % (mobj.group('host'), video_id),
+            'http://%s/video/%s' % (host, video_id),

             video_id, 'Downloading webpage')
 
         title = self._og_search_title(webpage)
             video_id, 'Downloading webpage')
 
         title = self._og_search_title(webpage)

-        thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage)
-
-        r = [
-            self._API_KEY,
-            [
-                'preview/flv_link',
-                {
-                    'uid': video_id,
-                },
-            ],
-        ]
-        r_json = json.dumps(r)
-        post = compat_urllib_parse.urlencode({'r': r_json})
-        req = sanitized_Request(self._API_URL, post)
-        req.add_header('Content-type', 'application/x-www-form-urlencoded')
-
-        response = self._download_json(req, video_id)
-        if response['status'] != 'OK':
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, response['data']),
-                expected=True
-            )
-        item = response['data'][0]
-        video_url = item['link']
-        duration = int_or_none(item['length'])
-        width = int_or_none(item['width'])
-        height = int_or_none(item['height'])
-        filesize = int_or_none(item['convert_size'])

 
 

-        formats = [{
-            'format_id': 'sd',
-            'http_headers': {'Range': 'bytes=0-'},  # Required to download
-            'url': video_url,
-            'width': width,
-            'height': height,
-            'filesize': filesize,
-        }]
+        embed_webpage = self._download_webpage(
+            'http://%s/embed/%s' % (host, video_id),
+            video_id, 'Downloading embed webpage')
+        video = self._parse_json(self._search_regex(
+            r'mvplayer\("#player"\s*,\s*({.+})',
+            embed_webpage, 'mvplayer'), video_id)['video']

 
         return {
             'id': video_id,
             'title': title,
 
         return {
             'id': video_id,
             'title': title,

-            'thumbnail': thumbnail,
-            'description': description,
-            'duration': duration,
-            'formats': formats,
+            'thumbnail': video.get('poster') or self._og_search_thumbnail(webpage),
+            'description': clean_html(self._og_search_description(webpage)),
+            'duration': int_or_none(self._og_search_property('video:duration', webpage)),
+            'url': video['ourUrl'],

         }
         }