minhngoc25a
/
yt-dlc
mirror of https://github.com/blackjack4494/yt-dlc
1
0
Fork 1
Code Issues Releases Wiki Activity

[daserste-ndr] dirty workaround 

what a mess..
This commit is contained in:
Unknown 2020-09-11 03:20:44 +02:00
parent 389709160c
commit dc9d8f44d6
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
youtube_dlc/extractor/ndr.py
View File

@ -19,14 +19,15 @@ class NDRBaseIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = next(group for group in mobj.groups() if group) display_id = next(group for group in mobj.groups() if group)
id = mobj.group('id')
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
return self._extract_embed(webpage, display_id) return self._extract_embed(webpage, display_id, id)
class NDRIE(NDRBaseIE): class NDRIE(NDRBaseIE):
IE_NAME = 'ndr' IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Norddeutscher Rundfunk' IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
_VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html' _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<display_id>[^/?#]+),(?P<id>[\da-z]+)\.html'
_TESTS = [{ _TESTS = [{
# httpVideo, same content id # httpVideo, same content id
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html', 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@ -86,12 +87,14 @@ class NDRIE(NDRBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_embed(self, webpage, display_id): def _extract_embed(self, webpage, display_id, id):
embed_url = self._html_search_meta( embed_url = self._html_search_meta(
'embedURL', webpage, 'embed URL', 'embedURL', webpage, 'embed URL',
default=None) or self._search_regex( default=None) or self._search_regex(
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'embed URL', group='url') 'embed URL', fatal=False, group='url')
if embed_url == None:
return self.url_result('ndr:%s' % id, ie=NDREmbedBaseIE.ie_key())
description = self._search_regex( description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>', r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', default=None) or self._og_search_description(webpage) webpage, 'description', default=None) or self._og_search_description(webpage)
@ -152,7 +155,7 @@ class NJoyIE(NDRBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_embed(self, webpage, display_id): def _extract_embed(self, webpage, display_id, id):
video_id = self._search_regex( video_id = self._search_regex(
r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id') r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id')
description = self._search_regex( description = self._search_regex(
@ -253,7 +256,7 @@ class NDREmbedBaseIE(InfoExtractor):
class NDREmbedIE(NDREmbedBaseIE): class NDREmbedIE(NDREmbedBaseIE):
IE_NAME = 'ndr:embed' IE_NAME = 'ndr:embed'
_VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html' _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_TESTS = [{ _TESTS = [{
'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html', 'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
'md5': '8b9306142fe65bbdefb5ce24edb6b0a9', 'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',