[wdr] Add WDRBaseIE, for Sportschau (#9799)

youtube_dl/extractor/wdr.py

@@ -15,7 +15,87 @@ from ..utils import (
 )
 
 
-class WDRIE(InfoExtractor):
+class WDRBaseIE(InfoExtractor):
+    def _extract_wdr_video(self, webpage, display_id):
+        # for wdr.de the data-extension is in a tag with the class "mediaLink"
+        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
+        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
+        json_metadata = self._html_search_regex(
+            r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
+            webpage, 'media link', default=None, flags=re.MULTILINE)
+
+        if not json_metadata:
+            return
+
+        media_link_obj = self._parse_json(json_metadata, display_id,
+                                          transform_source=js_to_json)
+        jsonp_url = media_link_obj['mediaObj']['url']
+
+        metadata = self._download_json(
+            jsonp_url, 'metadata', transform_source=strip_jsonp)
+
+        metadata_tracker_data = metadata['trackerData']
+        metadata_media_resource = metadata['mediaResource']
+
+        formats = []
+
+        # check if the metadata contains a direct URL to a file
+        for kind, media_resource in metadata_media_resource.items():
+            if kind not in ('dflt', 'alt'):
+                continue
+
+            for tag_name, medium_url in media_resource.items():
+                if tag_name not in ('videoURL', 'audioURL'):
+                    continue
+
+                ext = determine_ext(medium_url)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        medium_url, display_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls'))
+                elif ext == 'f4m':
+                    manifest_url = update_url_query(
+                        medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
+                    formats.extend(self._extract_f4m_formats(
+                        manifest_url, display_id, f4m_id='hds', fatal=False))
+                elif ext == 'smil':
+                    formats.extend(self._extract_smil_formats(
+                        medium_url, 'stream', fatal=False))
+                else:
+                    a_format = {
+                        'url': medium_url
+                    }
+                    if ext == 'unknown_video':
+                        urlh = self._request_webpage(
+                            medium_url, display_id, note='Determining extension')
+                        ext = urlhandle_detect_ext(urlh)
+                        a_format['ext'] = ext
+                    formats.append(a_format)
+
+        self._sort_formats(formats)
+
+        subtitles = {}
+        caption_url = metadata_media_resource.get('captionURL')
+        if caption_url:
+            subtitles['de'] = [{
+                'url': caption_url,
+                'ext': 'ttml',
+            }]
+
+        title = metadata_tracker_data['trackerClipTitle']
+
+        return {
+            'id': metadata_tracker_data.get('trackerClipId', display_id),
+            'display_id': display_id,
+            'title': title,
+            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
+            'formats': formats,
+            'subtitles': subtitles,
+            'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')),
+        }
+
+
+class WDRIE(WDRBaseIE):
     _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
     _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
     _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
@@ -91,10 +171,10 @@ class WDRIE(InfoExtractor):
         },
         {
             'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
-            # HDS download, MD5 is unstable
+            'md5': '803138901f6368ee497b4d195bb164f2',
             'info_dict': {
                 'id': 'mdb-186083',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'upload_date': '20130919',
                 'title': 'Sachgeschichte - Achterbahn ',
                 'description': '- Die Sendung mit der Maus -',
@@ -120,14 +200,9 @@ class WDRIE(InfoExtractor):
         display_id = mobj.group('display_id')
         webpage = self._download_webpage(url, display_id)
 
-        # for wdr.de the data-extension is in a tag with the class "mediaLink"
+        info_dict = self._extract_wdr_video(webpage, display_id)
-        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
-        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
-        json_metadata = self._html_search_regex(
-            r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
-            webpage, 'media link', default=None, flags=re.MULTILINE)
 
-        if not json_metadata:
+        if not info_dict:
             entries = [
                 self.url_result(page_url + href[0], 'WDR')
                 for href in re.findall(
@@ -140,86 +215,22 @@ class WDRIE(InfoExtractor):
 
             raise ExtractorError('No downloadable streams found', expected=True)
 
-        media_link_obj = self._parse_json(json_metadata, display_id,
-                                          transform_source=js_to_json)
-        jsonp_url = media_link_obj['mediaObj']['url']
-
-        metadata = self._download_json(
-            jsonp_url, 'metadata', transform_source=strip_jsonp)
-
-        metadata_tracker_data = metadata['trackerData']
-        metadata_media_resource = metadata['mediaResource']
-
-        formats = []
-
-        # check if the metadata contains a direct URL to a file
-        for kind, media_resource in metadata_media_resource.items():
-            if kind not in ('dflt', 'alt'):
-                continue
-
-            for tag_name, medium_url in media_resource.items():
-                if tag_name not in ('videoURL', 'audioURL'):
-                    continue
-
-                ext = determine_ext(medium_url)
-                if ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        medium_url, display_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls'))
-                elif ext == 'f4m':
-                    manifest_url = update_url_query(
-                        medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
-                    formats.extend(self._extract_f4m_formats(
-                        manifest_url, display_id, f4m_id='hds', fatal=False))
-                elif ext == 'smil':
-                    formats.extend(self._extract_smil_formats(
-                        medium_url, 'stream', fatal=False))
-                else:
-                    a_format = {
-                        'url': medium_url
-                    }
-                    if ext == 'unknown_video':
-                        urlh = self._request_webpage(
-                            medium_url, display_id, note='Determining extension')
-                        ext = urlhandle_detect_ext(urlh)
-                        a_format['ext'] = ext
-                    formats.append(a_format)
-
-        self._sort_formats(formats)
-
-        subtitles = {}
-        caption_url = metadata_media_resource.get('captionURL')
-        if caption_url:
-            subtitles['de'] = [{
-                'url': caption_url,
-                'ext': 'ttml',
-            }]
-
-        title = metadata_tracker_data.get('trackerClipTitle')
         is_live = url_type == 'live'
 
         if is_live:
-            title = self._live_title(title)
+            info_dict.update({
-            upload_date = None
+                'title': self._live_title(info_dict['title']),
-        elif 'trackerClipAirTime' in metadata_tracker_data:
+                'upload_date': None,
-            upload_date = metadata_tracker_data['trackerClipAirTime']
+            })
-        else:
+        elif 'upload_date' not in info_dict:
-            upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
+            info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date'))
-
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
 
-        return {
+        info_dict.update({
-            'id': metadata_tracker_data.get('trackerClipId', display_id),
-            'display_id': display_id,
-            'title': title,
-            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
-            'formats': formats,
-            'upload_date': upload_date,
             'description': self._html_search_meta('Description', webpage),
             'is_live': is_live,
-            'subtitles': subtitles,
+        })
-        }
+
+        return info_dict
 
 
 class WDRMobileIE(InfoExtractor):