Switch codebase to use sanitized_Request instead of

[youtube-dl] / youtube_dl / extractor / rtve.py

diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py
index e60f85b5b4842d90b49aeec9aa87da8def92d4f9..603d7bd00620cef13cd957a54053dc7f77010e05 100644 (file)
--- a/youtube_dl/extractor/rtve.py
+++ b/youtube_dl/extractor/rtve.py
@@ -6,15 +6,18 @@ import re
 import time
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from ..utils import (
-    struct_unpack,
+    ExtractorError,
+    float_or_none,
     remove_end,
+    sanitized_Request,
+    std_headers,
+    struct_unpack,
 )
 
 
 def _decrypt_url(png):
-    encrypted_data = base64.b64decode(png)
+    encrypted_data = base64.b64decode(png.encode('utf-8'))
     text_index = encrypted_data.find(b'tEXt')
     text_chunk = encrypted_data[text_index - 4:]
     length = struct_unpack('!I', text_chunk[:4])[0]
@@ -67,6 +70,7 @@ class RTVEALaCartaIE(InfoExtractor):
             'id': '2491869',
             'ext': 'mp4',
             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
+            'duration': 5024.566,
         },
     }, {
         'note': 'Live stream',
@@ -82,25 +86,34 @@ class RTVEALaCartaIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _real_initialize(self):
+        user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
+        manager_info = self._download_json(
+            'http://www.rtve.es/odin/loki/' + user_agent_b64,
+            None, 'Fetching manager info')
+        self._manager = manager_info['manager']
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         info = self._download_json(
             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
             video_id)['page']['items'][0]
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
-        png = self._download_webpage(png_url, video_id, 'Downloading url information')
+        if info['state'] == 'DESPU':
+            raise ExtractorError('The video is no longer available', expected=True)
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
+        png_request = sanitized_Request(png_url)
+        png_request.add_header('Referer', url)
+        png = self._download_webpage(png_request, video_id, 'Downloading url information')
         video_url = _decrypt_url(png)
         if not video_url.endswith('.f4m'):
-            auth_url = video_url.replace(
+            video_url = video_url.replace(
                 'resources/', 'auth/resources/'
             ).replace('.net.rtve', '.multimedia.cdn.rtve')
-            video_path = self._download_webpage(
-                auth_url, video_id, 'Getting video url')
-            # Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get
-            # the right Content-Length header and the mp4 format
-            video_url = compat_urlparse.urljoin(
-                'http://mvod1.akcdn.rtve.es/', video_path)
+
+        subtitles = None
+        if info.get('sbtFile') is not None:
+            subtitles = self.extract_subtitles(video_id, info['sbtFile'])
 
         return {
             'id': video_id,
@@ -108,6 +121,57 @@ class RTVEALaCartaIE(InfoExtractor):
             'url': video_url,
             'thumbnail': info.get('image'),
             'page_url': url,
+            'subtitles': subtitles,
+            'duration': float_or_none(info.get('duration'), scale=1000),
+        }
+
+    def _get_subtitles(self, video_id, sub_file):
+        subs = self._download_json(
+            sub_file + '.json', video_id,
+            'Downloading subtitles info')['page']['items']
+        return dict(
+            (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
+            for s in subs)
+
+
+class RTVEInfantilIE(InfoExtractor):
+    IE_NAME = 'rtve.es:infantil'
+    IE_DESC = 'RTVE infantil'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
+
+    _TESTS = [{
+        'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
+        'md5': '915319587b33720b8e0357caaa6617e6',
+        'info_dict': {
+            'id': '3040283',
+            'ext': 'mp4',
+            'title': 'Maneras de vivir',
+            'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
+            'duration': 357.958,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._download_json(
+            'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
+            video_id)['page']['items'][0]
+
+        webpage = self._download_webpage(url, video_id)
+        vidplayer_id = self._search_regex(
+            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
+
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
+        png = self._download_webpage(png_url, video_id, 'Downloading url information')
+        video_url = _decrypt_url(png)
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'title': info['title'],
+            'url': video_url,
+            'thumbnail': info.get('image'),
+            'duration': float_or_none(info.get('duration'), scale=1000),
         }