diff options
Diffstat (limited to 'yt_dlp/extractor/ndr.py')
| -rw-r--r-- | yt_dlp/extractor/ndr.py | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/yt_dlp/extractor/ndr.py b/yt_dlp/extractor/ndr.py index 243221d..5181c7f 100644 --- a/yt_dlp/extractor/ndr.py +++ b/yt_dlp/extractor/ndr.py @@ -1,7 +1,7 @@ import re +import urllib.parse from .common import InfoExtractor -from ..compat import compat_urllib_parse_urlparse from ..utils import ( ExtractorError, determine_ext, @@ -125,13 +125,13 @@ class NDRIE(NDRBaseIE): # some more work needed if we only found sophoraID if re.match(r'^[a-z]+\d+$', embed_url): # get the initial part of the url path,. eg /panorama/archiv/2022/ - parsed_url = compat_urllib_parse_urlparse(url) - path = self._search_regex(r'(.+/)%s' % display_id, parsed_url.path or '', 'embed URL', default='') + parsed_url = urllib.parse.urlparse(url) + path = self._search_regex(rf'(.+/){display_id}', parsed_url.path or '', 'embed URL', default='') # find tell-tale image with the actual ID - ndr_id = self._search_regex(r'%s([a-z]+\d+)(?!\.)\b' % (path, ), webpage, 'embed URL', default=None) + ndr_id = self._search_regex(rf'{path}([a-z]+\d+)(?!\.)\b', webpage, 'embed URL', default=None) # or try to use special knowledge! NDR_INFO_URL_TPL = 'https://www.ndr.de/info/%s-player.html' - embed_url = 'ndr:%s' % (ndr_id, ) if ndr_id else NDR_INFO_URL_TPL % (embed_url, ) + embed_url = f'ndr:{ndr_id}' if ndr_id else NDR_INFO_URL_TPL % (embed_url, ) if not embed_url: raise ExtractorError('Unable to extract embedUrl') @@ -141,7 +141,7 @@ class NDRIE(NDRBaseIE): timestamp = parse_iso8601( self._search_regex( (r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="(?P<cont>[^"]+)"', - r'\bvar\s*pdt\s*=\s*(?P<q>["\'])(?P<cont>(?:(?!(?P=q)).)+)(?P=q)', ), + r'\bvar\s*pdt\s*=\s*(?P<q>["\'])(?P<cont>(?:(?!(?P=q)).)+)(?P=q)'), webpage, 'upload date', group='cont', default=None)) info = self._search_json_ld(webpage, display_id, default={}) return merge_dicts({ @@ -200,7 +200,7 @@ class NJoyIE(NDRBaseIE): # find tell-tale URL with the actual ID, or ... video_id = self._search_regex( (r'''\bsrc\s*=\s*["']?(?:/\w+)+/([a-z]+\d+)(?!\.)\b''', - r'<iframe[^>]+id="pp_([\da-z]+)"', ), + r'<iframe[^>]+id="pp_([\da-z]+)"'), webpage, 'NDR id', default=None) description = ( @@ -211,7 +211,7 @@ class NJoyIE(NDRBaseIE): return { '_type': 'url_transparent', 'ie_key': 'NDREmbedBase', - 'url': 'ndr:%s' % video_id, + 'url': f'ndr:{video_id}', 'display_id': display_id, 'description': description, 'title': display_id.replace('-', ' ').strip(), @@ -234,7 +234,7 @@ class NDREmbedBaseIE(InfoExtractor): # XXX: Conventionally, Concrete class name video_id = mobj.group('id') or mobj.group('id_s') ppjson = self._download_json( - 'http://www.ndr.de/%s-ppjson.json' % video_id, video_id) + f'http://www.ndr.de/{video_id}-ppjson.json', video_id) playlist = ppjson['playlist'] |