pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 12:10:10 +09:00
Code Issues Projects Releases Wiki Activity

Support Series page

Browse Source
This commit is contained in:
dirkf 2022-04-07 23:08:42 +01:00
parent 8f6a09b921
commit 65712d99c4
1 changed files with 23 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
youtube_dl/extractor/rtve.py
View File

@ -9,7 +9,9 @@ import sys
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_b64decode, compat_b64decode,
compat_parse_qs,
compat_struct_unpack, compat_struct_unpack,
compat_urllib_parse_urlparse,
) )
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
@ -25,8 +27,8 @@ _bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(ch
class RTVEALaCartaIE(InfoExtractor): class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta' IE_NAME = 'rtve.es:play'
IE_DESC = 'RTVE a la carta' IE_DESC = 'RTVE Play'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?((alacarta|playz?)/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?((alacarta|playz?)/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
@ -90,6 +92,12 @@ class RTVEALaCartaIE(InfoExtractor):
}, { }, {
'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/', 'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.rtve.es/play/videos/modulos/capitulos/11332/?currentpage=pf_serie',
'info_dict': {
'id': '11332',
},
'playlist_mincount': 20,
}] }]
def _real_initialize(self): def _real_initialize(self):
@ -164,8 +172,21 @@ class RTVEALaCartaIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
return formats return formats
def _extract_playlist(self, url, playlist_id):
webpage = self._download_webpage(url, playlist_id)
matches = re.findall(r'''<a\b[^>]*\bhref\s*=\s*["'](%s)''' % (self._VALID_URL, ), webpage)
return self.playlist_from_matches(matches, playlist_id=playlist_id, getter=lambda x: x[0], ie=self.ie_key())
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
if 'pf_serie' == qs.get('currentpage', [None])[-1]:
return self._extract_playlist(url, video_id)
info = self._download_json( info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0] video_id)['page']['items'][0]