aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/mdr.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/mdr.py')
-rw-r--r--youtube_dl/extractor/mdr.py99
1 files changed, 61 insertions, 38 deletions
diff --git a/youtube_dl/extractor/mdr.py b/youtube_dl/extractor/mdr.py
index 2100583df..dc6aa9819 100644
--- a/youtube_dl/extractor/mdr.py
+++ b/youtube_dl/extractor/mdr.py
@@ -2,19 +2,25 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+ compat_str,
+ compat_urlparse,
+)
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
parse_iso8601,
+ url_or_none,
xpath_text,
)
class MDRIE(InfoExtractor):
IE_DESC = 'MDR.DE and KiKA'
- _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html'
+ _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
+
+ _GEO_COUNTRIES = ['DE']
_TESTS = [{
# MDR regularly deletes its videos
@@ -31,6 +37,7 @@ class MDRIE(InfoExtractor):
'duration': 250,
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
},
+ 'skip': '404 not found',
}, {
'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
'md5': '4930515e36b06c111213e80d1e4aad0e',
@@ -41,6 +48,7 @@ class MDRIE(InfoExtractor):
'duration': 134,
'uploader': 'KIKA',
},
+ 'skip': '404 not found',
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
@@ -49,12 +57,38 @@ class MDRIE(InfoExtractor):
'ext': 'mp4',
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
- 'timestamp': 1450950000,
- 'upload_date': '20151224',
+ 'timestamp': 1482541200,
+ 'upload_date': '20161224',
'duration': 4628,
'uploader': 'KIKA',
},
}, {
+ # audio with alternative playerURL pattern
+ 'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html',
+ 'info_dict': {
+ 'id': '100',
+ 'ext': 'mp4',
+ 'title': 'Feature: Operation Mindfuck - Robert Anton Wilson',
+ 'duration': 3239,
+ 'uploader': 'MITTELDEUTSCHER RUNDFUNK',
+ },
+ }, {
+ # empty bitrateVideo and bitrateAudio
+ 'url': 'https://www.kika.de/filme/sendung128372_zc-572e3f45_zs-1d9fb70e.html',
+ 'info_dict': {
+ 'id': '128372',
+ 'ext': 'mp4',
+ 'title': 'Der kleine Wichtel kehrt zurück',
+ 'description': 'md5:f77fafdff90f7aa1e9dca14f662c052a',
+ 'duration': 4876,
+ 'timestamp': 1607823300,
+ 'upload_date': '20201213',
+ 'uploader': 'ZDF',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
'only_matching': True,
}, {
@@ -71,18 +105,21 @@ class MDRIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
data_url = self._search_regex(
- r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
- webpage, 'data url', group='url').replace('\/', '/')
+ r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+?-avCustom\.xml)\1',
+ webpage, 'data url', group='url').replace(r'\/', '/')
doc = self._download_xml(
compat_urlparse.urljoin(url, data_url), video_id)
title = xpath_text(doc, ['./title', './broadcast/broadcastName'], 'title', fatal=True)
+ type_ = xpath_text(doc, './type', default=None)
+
formats = []
processed_urls = []
for asset in doc.findall('./assets/asset'):
for source in (
+ 'download',
'progressiveDownload',
'dynamicHttpStreamingRedirector',
'adaptiveHttpStreamingRedirector'):
@@ -90,63 +127,49 @@ class MDRIE(InfoExtractor):
if url_el is None:
continue
- video_url = url_el.text
- if video_url in processed_urls:
+ video_url = url_or_none(url_el.text)
+ if not video_url or video_url in processed_urls:
continue
processed_urls.append(video_url)
- vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
- abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
-
- ext = determine_ext(url_el.text)
+ ext = determine_ext(video_url)
if ext == 'm3u8':
- url_formats = self._extract_m3u8_formats(
+ formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
- preference=0, m3u8_id='HLS', fatal=False)
+ preference=0, m3u8_id='HLS', fatal=False))
elif ext == 'f4m':
- url_formats = self._extract_f4m_formats(
+ formats.extend(self._extract_f4m_formats(
video_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
- preference=0, f4m_id='HDS', fatal=False)
+ preference=0, f4m_id='HDS', fatal=False))
else:
media_type = xpath_text(asset, './mediaType', 'media type', default='MP4')
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
filesize = int_or_none(xpath_text(asset, './fileSize', 'file size'))
+ format_id = [media_type]
+ if vbr or abr:
+ format_id.append(compat_str(vbr or abr))
+
f = {
'url': video_url,
- 'format_id': '%s-%d' % (media_type, vbr or abr),
+ 'format_id': '-'.join(format_id),
'filesize': filesize,
'abr': abr,
- 'preference': 1,
+ 'vbr': vbr,
}
if vbr:
- width = int_or_none(xpath_text(asset, './frameWidth', 'width'))
- height = int_or_none(xpath_text(asset, './frameHeight', 'height'))
f.update({
- 'vbr': vbr,
- 'width': width,
- 'height': height,
+ 'width': int_or_none(xpath_text(asset, './frameWidth', 'width')),
+ 'height': int_or_none(xpath_text(asset, './frameHeight', 'height')),
})
- url_formats = [f]
-
- if not url_formats:
- continue
-
- if not vbr:
- for f in url_formats:
- abr = f.get('tbr') or abr
- if 'tbr' in f:
- del f['tbr']
- f.update({
- 'abr': abr,
- 'vcodec': 'none',
- })
+ if type_ == 'audio':
+ f['vcodec'] = 'none'
- formats.extend(url_formats)
+ formats.append(f)
self._sort_formats(formats)
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-02 07:48:20 +0000