diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2018-09-01 00:18:17 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2018-09-01 00:18:17 +0200 |
commit | c1a37eb24a78fe07a3ad41fc151389e444b7962b (patch) | |
tree | a1234bfad22527ceebdfc39fc10b3c029285cb06 /youtube_dl/extractor | |
parent | 4991e16c2a62ecd1a81cbb9ff6563885c1bf6210 (diff) |
[ard] Add support for Beta ARD Mediathek
Thanks to https://blog.fefe.de/?ts=a577685d for pointing out support is missing.
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/ard.py | 62 | ||||
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 |
2 files changed, 63 insertions, 0 deletions
diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 23f574d36..9c6be2dd9 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -282,3 +282,65 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } + + +class ARDBetaMediathekIE(InfoExtractor): + _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P<video_id>[a-zA-Z0-9]+)/(?P<display_id>[^/?#]+)' + _TESTS = [{ + 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', + 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', + 'info_dict': { + 'display_id': 'die-robuste-roswita', + 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', + 'title': 'Tatort: Die robuste Roswita', + 'description': r're:^Der Mord.*trĂ¼ber ist als die Ilm.', + 'duration': 5316, + 'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard', + 'upload_date': '20180826', + 'ext': 'mp4', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);', webpage, 'json') + data = self._parse_json(data_json, display_id) + + res = { + 'id': video_id, + 'display_id': display_id, + } + formats = [] + for widget in data.values(): + if widget.get('_geoblocked'): + raise ExtractorError('This video is not available due to geoblocking', expected=True) + + if '_duration' in widget: + res['duration'] = widget['_duration'] + if 'clipTitle' in widget: + res['title'] = widget['clipTitle'] + if '_previewImage' in widget: + res['thumbnail'] = widget['_previewImage'] + if 'broadcastedOn' in widget: + res['upload_date'] = unified_strdate(widget['broadcastedOn']) + if 'synopsis' in widget: + res['description'] = widget['synopsis'] + if '_subtitleUrl' in widget: + res['subtitles'] = {'de': [{ + 'ext': 'ttml', + 'url': widget['_subtitleUrl'], + }]} + if '_quality' in widget: + formats.append({ + 'format_id': widget['_quality'], + 'url': widget['_stream']['json'][0], + }) + + self._sort_formats(formats) + res['formats'] = formats + + return res diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6012d0f5f..995af9988 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -54,6 +54,7 @@ from .appletrailers import ( from .archiveorg import ArchiveOrgIE from .arkena import ArkenaIE from .ard import ( + ARDBetaMediathekIE, ARDIE, ARDMediathekIE, ) |