[zdf] Rework extractors (closes #11606, closes #13473, closes #17354, closes #21185, closes #26711, closes #27068, closes #27930, closes #28198, closes #28199, closes #28274)

* Generalize unique video ids for zdf based extractors * Improve extraction * Fix 3sat and phoenix
2025-07-04 21:12:48 -05:00 · 2021-03-02 06:03:17 +07:00
parent bee6182680
commit 3fb14cd214
3 changed files with 276 additions and 285 deletions
--- a/youtube_dl/extractor/phoenix.py
+++ b/youtube_dl/extractor/phoenix.py
@ -1,45 +1,128 @@
+# coding: utf-8
 from __future__ import unicode_literals

-from .dreisat import DreiSatIE
+import re
+
+from .youtube import YoutubeIE
+from .zdf import ZDFBaseIE
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    merge_dicts,
+    unified_timestamp,
+    xpath_text,
+)


-class PhoenixIE(DreiSatIE):
+class PhoenixIE(ZDFBaseIE):
    IE_NAME = 'phoenix.de'
-    _VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/
-        (?:
-            phoenix/die_sendungen/(?:[^/]+/)?
-        )?
-        (?P<id>[0-9]+)'''
-    _TESTS = [
-        {
-            'url': 'http://www.phoenix.de/content/884301',
-            'md5': 'ed249f045256150c92e72dbb70eadec6',
-            'info_dict': {
-                'id': '884301',
-                'ext': 'mp4',
-                'title': 'Michael Krons mit Hans-Werner Sinn',
-                'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
-                'upload_date': '20141025',
-                'uploader': 'Im Dialog',
-            }
+    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
+        'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
+        'md5': '34ec321e7eb34231fd88616c65c92db0',
+        'info_dict': {
+            'id': '210222_phx_nachgehakt_corona_protest',
+            'ext': 'mp4',
+            'title': 'Wohin führt der Protest in der Pandemie?',
+            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
+            'duration': 1691,
+            'timestamp': 1613906100,
+            'upload_date': '20210221',
+            'uploader': 'Phoenix',
+            'channel': 'corona nachgehakt',
        },
-        {
-            'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815',
-            'only_matching': True,
+    }, {
+        # Youtube embed
+        'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
+        'info_dict': {
+            'id': 'hMQtqFYjomk',
+            'ext': 'mp4',
+            'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
+            'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
+            'duration': 3509,
+            'upload_date': '20201219',
+            'uploader': 'phoenix',
+            'uploader_id': 'phoenix',
        },
-        {
-            'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234',
-            'only_matching': True,
+        'params': {
+            'skip_download': True,
        },
-    ]
+    }, {
+        'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
+        'only_matching': True,
+    }, {
+        # no media
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
+        'only_matching': True,
+    }]

    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        article_id = self._match_id(url)

-        internal_id = self._search_regex(
-            r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
-            webpage, 'internal video ID')
+        article = self._download_json(
+            'https://www.phoenix.de/response/id/%s' % article_id, article_id,
+            'Downloading article JSON')

-        api_url = 'http://www.phoenix.de/php/mediaplayer/data/beitrags_details.php?ak=web&id=%s' % internal_id
-        return self.extract_from_xml_url(video_id, api_url)
+        video = article['absaetze'][0]
+        title = video.get('titel') or article.get('subtitel')
+
+        if video.get('typ') == 'video-youtube':
+            video_id = video['id']
+            return self.url_result(
+                video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
+                video_title=title)
+
+        video_id = compat_str(video.get('basename') or video.get('content'))
+
+        details = self._download_xml(
+            'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
+            video_id, 'Downloading details XML', query={
+                'ak': 'web',
+                'ptmd': 'true',
+                'id': video_id,
+                'profile': 'player2',
+            })
+
+        title = title or xpath_text(
+            details, './/information/title', 'title', fatal=True)
+        content_id = xpath_text(
+            details, './/video/details/basename', 'content id', fatal=True)
+
+        info = self._extract_ptmd(
+            'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
+            content_id, None, url)
+
+        timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
+
+        thumbnails = []
+        for node in details.findall('.//teaserimages/teaserimage'):
+            thumbnail_url = node.text
+            if not thumbnail_url:
+                continue
+            thumbnail = {
+                'url': thumbnail_url,
+            }
+            thumbnail_key = node.get('key')
+            if thumbnail_key:
+                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
+                if m:
+                    thumbnail['width'] = int(m.group(1))
+                    thumbnail['height'] = int(m.group(2))
+            thumbnails.append(thumbnail)
+
+        return merge_dicts(info, {
+            'id': content_id,
+            'title': title,
+            'description': xpath_text(details, './/information/detail'),
+            'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'uploader': xpath_text(details, './/details/channel'),
+            'uploader_id': xpath_text(details, './/details/originChannelId'),
+            'channel': xpath_text(details, './/details/originChannelTitle'),
+        })