From dc9d8f44d63d125ec2a5f37256bc4afa7be7c77b Mon Sep 17 00:00:00 2001 From: Unknown Date: Fri, 11 Sep 2020 03:20:44 +0200 Subject: [PATCH 1/2] [daserste-ndr] dirty workaround what a mess.. --- youtube_dlc/extractor/ndr.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/youtube_dlc/extractor/ndr.py b/youtube_dlc/extractor/ndr.py index 2447c812e..f03582118 100644 --- a/youtube_dlc/extractor/ndr.py +++ b/youtube_dlc/extractor/ndr.py @@ -19,14 +19,15 @@ class NDRBaseIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = next(group for group in mobj.groups() if group) + id = mobj.group('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): IE_NAME = 'ndr' IE_DESC = 'NDR.de - Norddeutscher Rundfunk' - _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P[^/?#]+),[\da-z]+\.html' + _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P[^/?#]+),(?P[\da-z]+)\.html' _TESTS = [{ # httpVideo, same content id 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html', @@ -86,12 +87,14 @@ class NDRIE(NDRBaseIE): 'only_matching': True, }] - def _extract_embed(self, webpage, display_id): + def _extract_embed(self, webpage, display_id, id): embed_url = self._html_search_meta( 'embedURL', webpage, 'embed URL', default=None) or self._search_regex( r'\bembedUrl["\']\s*:\s*(["\'])(?P(?:(?!\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( r']+itemprop="description">([^<]+)

', webpage, 'description', default=None) or self._og_search_description(webpage) @@ -152,7 +155,7 @@ class NJoyIE(NDRBaseIE): 'only_matching': True, }] - def _extract_embed(self, webpage, display_id): + def _extract_embed(self, webpage, display_id, id): video_id = self._search_regex( r']+id="pp_([\da-z]+)"', webpage, 'embed id') description = self._search_regex( @@ -253,7 +256,7 @@ def _real_extract(self, url): class NDREmbedIE(NDREmbedBaseIE): IE_NAME = 'ndr:embed' - _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P[\da-z]+)-(?:player|externalPlayer)\.html' + _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P[\da-z]+)-(?:player|externalPlayer)\.html' _TESTS = [{ 'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html', 'md5': '8b9306142fe65bbdefb5ce24edb6b0a9', From 921dc153f365268443c1decf6d347046c9d32ff9 Mon Sep 17 00:00:00 2001 From: Unknown Date: Sat, 12 Sep 2020 01:12:39 +0200 Subject: [PATCH 2/2] [ndr-daserste] flake8 --- youtube_dlc/extractor/ndr.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dlc/extractor/ndr.py b/youtube_dlc/extractor/ndr.py index f03582118..f3897c71b 100644 --- a/youtube_dlc/extractor/ndr.py +++ b/youtube_dlc/extractor/ndr.py @@ -93,7 +93,7 @@ def _extract_embed(self, webpage, display_id, id): default=None) or self._search_regex( r'\bembedUrl["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'embed URL', fatal=False, group='url') - if embed_url == None: + if embed_url is None: return self.url_result('ndr:%s' % id, ie=NDREmbedBaseIE.ie_key()) description = self._search_regex( r']+itemprop="description">([^<]+)

',