]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/rtve.py
Prepare to upload
[youtubedl] / youtube_dl / extractor / rtve.py
index 5b97d33caec2a08c79e648483ec67a1c288b6e4f..d9edf9da2f71cf6fbcf3c8bfd310c4818eced62c 100644 (file)
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import base64
@@ -6,13 +6,17 @@ import re
 import time
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_request, compat_urlparse
+from ..compat import (
+    compat_struct_unpack,
+)
 from ..utils import (
+    determine_ext,
     ExtractorError,
     float_or_none,
     remove_end,
+    remove_start,
+    sanitized_Request,
     std_headers,
-    struct_unpack,
 )
 
 
@@ -20,7 +24,7 @@ def _decrypt_url(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]
+    length = compat_struct_unpack('!I', text_chunk[:4])[0]
     # Use bytearray to get integers when iterating in both python 2.x and 3.x
     data = bytearray(text_chunk[8:8 + length])
     data = [chr(b) for b in data if b != 0]
@@ -61,7 +65,7 @@ def _decrypt_url(png):
 class RTVEALaCartaIE(InfoExtractor):
     IE_NAME = 'rtve.es:alacarta'
     IE_DESC = 'RTVE a la carta'
-    _VALID_URL = r'http://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
@@ -81,9 +85,24 @@ class RTVEALaCartaIE(InfoExtractor):
             'title': 'TODO',
         },
         'skip': 'The f4m manifest can\'t be used yet',
+    }, {
+        'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
+        'md5': 'e55e162379ad587e9640eda4f7353c0f',
+        'info_dict': {
+            'id': '4236788',
+            'ext': 'mp4',
+            'title': 'Servir y proteger - Capítulo 104 ',
+            'duration': 3222.0,
+        },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        },
     }, {
         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
         'only_matching': True,
+    }, {
+        'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
+        'only_matching': True,
     }]
 
     def _real_initialize(self):
@@ -101,21 +120,32 @@ class RTVEALaCartaIE(InfoExtractor):
             video_id)['page']['items'][0]
         if info['state'] == 'DESPU':
             raise ExtractorError('The video is no longer available', expected=True)
+        title = info['title']
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
-        png_request = compat_urllib_request.Request(png_url)
+        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(
-                '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)
+        ext = determine_ext(video_url)
+
+        formats = []
+        if not video_url.endswith('.f4m') and ext != 'm3u8':
+            if '?' not in video_url:
+                video_url = video_url.replace('resources/', 'auth/resources/')
+            video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
+
+        if ext == 'm3u8':
+            formats.extend(self._extract_m3u8_formats(
+                video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+        elif ext == 'f4m':
+            formats.extend(self._extract_f4m_formats(
+                video_url, video_id, f4m_id='hds', fatal=False))
+        else:
+            formats.append({
+                'url': video_url,
+            })
+        self._sort_formats(formats)
 
         subtitles = None
         if info.get('sbtFile') is not None:
@@ -123,8 +153,8 @@ class RTVEALaCartaIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': info['title'],
-            'url': video_url,
+            'title': title,
+            'formats': formats,
             'thumbnail': info.get('image'),
             'page_url': url,
             'subtitles': subtitles,
@@ -184,14 +214,14 @@ class RTVEInfantilIE(InfoExtractor):
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'
-    _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 
     _TESTS = [{
-        'url': 'http://www.rtve.es/noticias/directo-la-1/',
+        'url': 'http://www.rtve.es/directo/la-1/',
         'info_dict': {
-            'id': 'directo-la-1',
-            'ext': 'flv',
-            'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
+            'id': 'la-1',
+            'ext': 'mp4',
+            'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
         },
         'params': {
             'skip_download': 'live stream',
@@ -204,23 +234,55 @@ class RTVELiveIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        player_url = self._search_regex(
-            r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL')
-        title = remove_end(self._og_search_title(webpage), ' en directo')
+        title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
+        title = remove_start(title, 'Estoy viendo ')
         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         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
+            (r'playerId=player([0-9]+)',
+             r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
+             r'data-id=["\'](\d+)'),
+            webpage, 'internal video ID')
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
-        video_url = _decrypt_url(png)
+        m3u8_url = _decrypt_url(png)
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'ext': 'flv',
             'title': title,
-            'url': video_url,
-            'app': 'rtve-live-live?ovpfv=2.1.2',
-            'player_url': player_url,
-            'rtmp_live': True,
+            'formats': formats,
+            'is_live': True,
         }
+
+
+class RTVETelevisionIE(InfoExtractor):
+    IE_NAME = 'rtve.es:television'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
+
+    _TEST = {
+        'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
+        'info_dict': {
+            'id': '3069778',
+            'ext': 'mp4',
+            'title': 'Documentos TV - La revolución del móvil',
+            'duration': 3496.948,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        alacarta_url = self._search_regex(
+            r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
+            webpage, 'alacarta url', default=None)
+        if alacarta_url is None:
+            raise ExtractorError(
+                'The webpage doesn\'t contain any video', expected=True)
+
+        return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())