New upstream version 2019.01.16

[youtubedl] / youtube_dl / extractor / radiocanada.py

diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py
index 8ec402646767a22f8a1e7cedbc89eb8576b59804..b952e59b47535efc5268322f716f0e29fc8c6296 100644 (file)
--- a/youtube_dl/extractor/radiocanada.py
+++ b/youtube_dl/extractor/radiocanada.py
@@ -13,56 +13,97 @@ from ..utils import (
     xpath_element,
     ExtractorError,
     determine_protocol,
     xpath_element,
     ExtractorError,
     determine_protocol,

+    unsmuggle_url,

 )
 
 
 class RadioCanadaIE(InfoExtractor):
     IE_NAME = 'radiocanada'
     _VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'
 )
 
 
 class RadioCanadaIE(InfoExtractor):
     IE_NAME = 'radiocanada'
     _VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'

-    _TEST = {
-        'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
-        'info_dict': {
-            'id': '7184272',
-            'ext': 'mp4',
-            'title': 'Le parcours du tireur capté sur vidéo',
-            'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
-            'upload_date': '20141023',
+    _TESTS = [
+        {
+            'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
+            'info_dict': {
+                'id': '7184272',
+                'ext': 'mp4',
+                'title': 'Le parcours du tireur capté sur vidéo',
+                'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
+                'upload_date': '20141023',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            }

         },
         },

-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
+        {
+            # empty Title
+            'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7754998/',
+            'info_dict': {
+                'id': '7754998',
+                'ext': 'mp4',
+                'title': 'letelejournal22h',
+                'description': 'INTEGRALE WEB 22H-TJ',
+                'upload_date': '20170720',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        }
+    ]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

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

         app_code, video_id = re.match(self._VALID_URL, url).groups()
 
         app_code, video_id = re.match(self._VALID_URL, url).groups()
 

-        device_types = ['ipad', 'android']
-        if app_code != 'toutv':
+        metadata = self._download_xml(
+            'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
+            video_id, note='Downloading metadata XML', query={
+                'appCode': app_code,
+                'idMedia': video_id,
+            })
+
+        def get_meta(name):
+            el = find_xpath_attr(metadata, './/Meta', 'name', name)
+            return el.text if el is not None else None
+
+        if get_meta('protectionType'):
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
+        device_types = ['ipad']
+        if not smuggled_data:

             device_types.append('flash')
             device_types.append('flash')

+            device_types.append('android')

 
         formats = []
 
         formats = []

+        error = None

         # TODO: extract f4m formats
         # f4m formats can be extracted using flashhd device_type but they produce unplayable file
         for device_type in device_types:
         # TODO: extract f4m formats
         # f4m formats can be extracted using flashhd device_type but they produce unplayable file
         for device_type in device_types:

-            v_data = self._download_xml(
-                'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx',
-                video_id, note='Downloading %s XML' % device_type, query={
-                    'appCode': app_code,
-                    'idMedia': video_id,
-                    'connectionType': 'broadband',
-                    'multibitrate': 'true',
-                    'deviceType': device_type,
+            validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx'
+            query = {
+                'appCode': app_code,
+                'idMedia': video_id,
+                'connectionType': 'broadband',
+                'multibitrate': 'true',
+                'deviceType': device_type,
+            }
+            if smuggled_data:
+                validation_url = 'https://services.radio-canada.ca/media/validation/v2/'
+                query.update(smuggled_data)
+            else:
+                query.update({

                     # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
                     'paysJ391wsHjbOJwvCs26toz': 'CA',
                     'bypasslock': 'NZt5K62gRqfc',
                     # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
                     'paysJ391wsHjbOJwvCs26toz': 'CA',
                     'bypasslock': 'NZt5K62gRqfc',

-                }, fatal=False)
+                })
+            v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False)

             v_url = xpath_text(v_data, 'url')
             if not v_url:
                 continue
             if v_url == 'null':
             v_url = xpath_text(v_data, 'url')
             if not v_url:
                 continue
             if v_url == 'null':

-                raise ExtractorError('%s said: %s' % (
-                    self.IE_NAME, xpath_text(v_data, 'message')), expected=True)
+                error = xpath_text(v_data, 'message')
+                continue

             ext = determine_ext(v_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
             ext = determine_ext(v_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(


@@ -79,7 +120,7 @@ class RadioCanadaIE(InfoExtractor):
                         continue
                     f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
                     protocol = determine_protocol({'url': f_url})
                         continue
                     f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
                     protocol = determine_protocol({'url': f_url})

-                    formats.append({
+                    f = {

                         'format_id': '%s-%d' % (protocol, tbr),
                         'url': f_url,
                         'ext': 'flv' if protocol == 'rtmp' else ext,
                         'format_id': '%s-%d' % (protocol, tbr),
                         'url': f_url,
                         'ext': 'flv' if protocol == 'rtmp' else ext,


@@ -87,7 +128,14 @@ class RadioCanadaIE(InfoExtractor):
                         'width': int_or_none(url_e.get('width')),
                         'height': int_or_none(url_e.get('height')),
                         'tbr': tbr,
                         'width': int_or_none(url_e.get('width')),
                         'height': int_or_none(url_e.get('height')),
                         'tbr': tbr,

-                    })
+                    }
+                    mobj = re.match(r'(?P<url>rtmp://[^/]+/[^/]+)/(?P<playpath>[^?]+)(?P<auth>\?.+)', f_url)
+                    if mobj:
+                        f.update({
+                            'url': mobj.group('url') + mobj.group('auth'),
+                            'play_path': mobj.group('playpath'),
+                        })
+                    formats.append(f)

                     if protocol == 'rtsp':
                         base_url = self._search_regex(
                             r'rtsp://([^?]+)', f_url, 'base url', default=None)
                     if protocol == 'rtsp':
                         base_url = self._search_regex(
                             r'rtsp://([^?]+)', f_url, 'base url', default=None)


@@ -99,22 +147,22 @@ class RadioCanadaIE(InfoExtractor):
                             formats.extend(self._extract_f4m_formats(
                                 base_url + '/manifest.f4m', video_id,
                                 f4m_id='hds', fatal=False))
                             formats.extend(self._extract_f4m_formats(
                                 base_url + '/manifest.f4m', video_id,
                                 f4m_id='hds', fatal=False))

+        if not formats and error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error), expected=True)

         self._sort_formats(formats)
 
         self._sort_formats(formats)
 

-        metadata = self._download_xml(
-            'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
-            video_id, note='Downloading metadata XML', query={
-                'appCode': app_code,
-                'idMedia': video_id,
-            })
-
-        def get_meta(name):
-            el = find_xpath_attr(metadata, './/Meta', 'name', name)
-            return el.text if el is not None else None
+        subtitles = {}
+        closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5')
+        if closed_caption_url:
+            subtitles['fr'] = [{
+                'url': closed_caption_url,
+                'ext': determine_ext(closed_caption_url, 'vtt'),
+            }]

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

-            'title': get_meta('Title'),
+            'title': get_meta('Title') or get_meta('AV-nomEmission'),

             'description': get_meta('Description') or get_meta('ShortDescription'),
             'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
             'duration': int_or_none(get_meta('length')),
             'description': get_meta('Description') or get_meta('ShortDescription'),
             'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
             'duration': int_or_none(get_meta('length')),


@@ -122,6 +170,7 @@ class RadioCanadaIE(InfoExtractor):
             'season_number': int_or_none('SrcSaison'),
             'episode_number': int_or_none('SrcEpisode'),
             'upload_date': unified_strdate(get_meta('Date')),
             'season_number': int_or_none('SrcSaison'),
             'episode_number': int_or_none('SrcEpisode'),
             'upload_date': unified_strdate(get_meta('Date')),

+            'subtitles': subtitles,

             'formats': formats,
         }
 
             'formats': formats,
         }