debian/copyright: use spaces rather than tabs to start continuation lines.

[youtubedl] / youtube_dl / extractor / pladform.py

diff --git a/youtube_dl/extractor/pladform.py b/youtube_dl/extractor/pladform.py
index 551c8c9f0fef4566afd5691628b2c216c157fd0c..e86c65396bc0326c80268b4a3130b6bb786dfa9f 100644 (file)
--- a/youtube_dl/extractor/pladform.py
+++ b/youtube_dl/extractor/pladform.py
@@ -1,8 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_urlparse

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

+    determine_ext,

     ExtractorError,
     int_or_none,
     xpath_text,
     ExtractorError,
     int_or_none,
     xpath_text,


@@ -24,17 +28,15 @@ class PladformIE(InfoExtractor):
                         (?P<id>\d+)
                     '''
     _TESTS = [{
                         (?P<id>\d+)
                     '''
     _TESTS = [{

-        # http://muz-tv.ru/kinozal/view/7400/
-        'url': 'http://out.pladform.ru/player?pl=24822&videoid=100183293',
-        'md5': '61f37b575dd27f1bb2e1854777fe31f4',
+        'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
+        'md5': '53362fac3a27352da20fa2803cc5cd6f',

         'info_dict': {
         'info_dict': {

-            'id': '100183293',
+            'id': '3777899',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
-            'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'duration': 694,
-            'age_limit': 0,
+            'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
+            'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 3190,

         },
     }, {
         'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
         },
     }, {
         'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',


@@ -44,25 +46,58 @@ class PladformIE(InfoExtractor):
         'only_matching': True,
     }]
 
         'only_matching': True,
     }]
 

+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+

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

+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        pl = qs.get('pl', ['1'])[0]
+

         video = self._download_xml(
         video = self._download_xml(

-            'http://out.pladform.ru/getVideo?pl=1&videoid=%s' % video_id,
-            video_id)
+            'http://out.pladform.ru/getVideo', video_id, query={
+                'pl': pl,
+                'videoid': video_id,
+            })

 
 

-        if video.tag == 'error':
+        def fail(text):

             raise ExtractorError(
             raise ExtractorError(

-                '%s returned error: %s' % (self.IE_NAME, video.text),
+                '%s returned error: %s' % (self.IE_NAME, text),

                 expected=True)
 
                 expected=True)
 

+        if video.tag == 'error':
+            fail(video.text)
+

         quality = qualities(('ld', 'sd', 'hd'))
 
         quality = qualities(('ld', 'sd', 'hd'))
 

-        formats = [{
-            'url': src.text,
-            'format_id': src.get('quality'),
-            'quality': quality(src.get('quality')),
-        } for src in video.findall('./src')]
+        formats = []
+        for src in video.findall('./src'):
+            if src is None:
+                continue
+            format_url = src.text
+            if not format_url:
+                continue
+            if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': src.text,
+                    'format_id': src.get('quality'),
+                    'quality': quality(src.get('quality')),
+                })
+
+        if not formats:
+            error = xpath_text(video, './cap', 'error', default=None)
+            if error:
+                fail(error)
+

         self._sort_formats(formats)
 
         webpage = self._download_webpage(
         self._sort_formats(formats)
 
         webpage = self._download_webpage(