diff options
Diffstat (limited to 'youtube_dlc/extractor/phoenix.py')
| -rw-r--r-- | youtube_dlc/extractor/phoenix.py | 61 |
1 files changed, 34 insertions, 27 deletions
diff --git a/youtube_dlc/extractor/phoenix.py b/youtube_dlc/extractor/phoenix.py index e435c28e1..8d52ad3b4 100644 --- a/youtube_dlc/extractor/phoenix.py +++ b/youtube_dlc/extractor/phoenix.py @@ -1,45 +1,52 @@ from __future__ import unicode_literals -from .dreisat import DreiSatIE +from .common import InfoExtractor +from ..utils import ExtractorError -class PhoenixIE(DreiSatIE): +class PhoenixIE(InfoExtractor): IE_NAME = 'phoenix.de' - _VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/ - (?: - phoenix/die_sendungen/(?:[^/]+/)? - )? - (?P<id>[0-9]+)''' + _VALID_URL = r'''https?://(?:www\.)?phoenix.de/\D+(?P<id>\d+)\.html''' _TESTS = [ { - 'url': 'http://www.phoenix.de/content/884301', - 'md5': 'ed249f045256150c92e72dbb70eadec6', + 'url': 'https://www.phoenix.de/sendungen/dokumentationen/unsere-welt-in-zukunft---stadt-a-1283620.html', + 'md5': '5e765e838aa3531c745a4f5b249ee3e3', 'info_dict': { - 'id': '884301', + 'id': '0OB4HFc43Ns', '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', + 'title': 'Unsere Welt in Zukunft - Stadt', + 'description': 'md5:9bfb6fd498814538f953b2dcad7ce044', + 'upload_date': '20190912', + 'uploader': 'phoenix', + 'uploader_id': 'phoenix', } }, { - 'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815', - 'only_matching': True, - }, - { - 'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234', + 'url': 'https://www.phoenix.de/drohnenangriffe-in-saudi-arabien-a-1286995.html?ref=aktuelles', 'only_matching': True, }, + # an older page: https://www.phoenix.de/sendungen/gespraeche/phoenix-persoenlich/im-dialog-a-177727.html + # seems to not have an embedded video, even though it's uploaded on youtube: https://www.youtube.com/watch?v=4GxnoUHvOkM ] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + def extract_from_json_api(self, video_id, api_url): + doc = self._download_json( + api_url, video_id, + note="Downloading webpage metadata", + errnote="Failed to load webpage metadata") - internal_id = self._search_regex( - r'<div class="phx_vod" id="phx_vod_([0-9]+)"', - webpage, 'internal video ID') + for a in doc["absaetze"]: + if a["typ"] == "video-youtube": + return { + '_type': 'url_transparent', + 'id': a["id"], + 'title': doc["titel"], + 'url': "https://www.youtube.com/watch?v=%s" % a["id"], + 'ie_key': 'Youtube', + } + raise ExtractorError("No downloadable video found", expected=True) - 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) + def _real_extract(self, url): + page_id = self._match_id(url) + api_url = 'https://www.phoenix.de/response/id/%s' % page_id + return self.extract_from_json_api(page_id, api_url) |