Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 14:37:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

[mdr] Add support for modern URLs (Fixes #2775)

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-04-21 06:25:21 +02:00
parent a4eb9578af
commit e8f2025edf
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/mdr.py
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -7,9 +9,13 @@
class MDRIE(InfoExtractor): class MDRIE(InfoExtractor):
_VALID_URL = r'^(?P<domain>(?:https?://)?(?:www\.)?mdr\.de)/mediathek/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)_.*' _VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)'
# No tests, MDR regularily deletes its videos # No tests, MDR regularily deletes its videos
_TEST = {
'url': 'http://www.mdr.de/fakt/video189002.html',
'only_matching': True,
}
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
@ -19,9 +25,9 @@ def _real_extract(self, url):
# determine title and media streams from webpage # determine title and media streams from webpage
html = self._download_webpage(url, video_id) html = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h2>(.*?)</h2>', html, u'title') title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title')
xmlurl = self._search_regex( xmlurl = self._search_regex(
r'(/mediathek/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, u'XML URL') r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL')
doc = self._download_xml(domain + xmlurl, video_id) doc = self._download_xml(domain + xmlurl, video_id)
formats = [] formats = []
@ -41,7 +47,7 @@ def _real_extract(self, url):
if vbr_el is None: if vbr_el is None:
format.update({ format.update({
'vcodec': 'none', 'vcodec': 'none',
'format_id': u'%s-%d' % (media_type, abr), 'format_id': '%s-%d' % (media_type, abr),
}) })
else: else:
vbr = int(vbr_el.text) // 1000 vbr = int(vbr_el.text) // 1000
@ -49,12 +55,9 @@ def _real_extract(self, url):
'vbr': vbr, 'vbr': vbr,
'width': int(a.find('frameWidth').text), 'width': int(a.find('frameWidth').text),
'height': int(a.find('frameHeight').text), 'height': int(a.find('frameHeight').text),
'format_id': u'%s-%d' % (media_type, vbr), 'format_id': '%s-%d' % (media_type, vbr),
}) })
formats.append(format) formats.append(format)
if not formats:
raise ExtractorError(u'Could not find any valid formats')
self._sort_formats(formats) self._sort_formats(formats)
return { return {