depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-28 13:11:49 +00:00
Code Issues Releases Wiki Activity

Extracted episode list.

Browse source
This commit is contained in:
deepspy 2024-06-24 14:22:56 +03:00
parent 833fe8c9af
commit d335e0beec
1 changed files with 25 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
youtube_dl/extractor/kankids.py
View file

@ -2,9 +2,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
import re
class KanKidsIE(InfoExtractor): class KanKidsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kankids\.org\.il/content/kids/(?P<category>[a-z]+)-main/p-(?P<id>[0-9]+)/(?P<season>\w+/)?$' _VALID_URL = r'https?://(?:www\.)?kankids\.org\.il/content/kids/(?P<category>[a-z]+)-main/p-(?P<id>[0-9]+)/(?P<season>\w+)?/?$'
_TEST = { _TEST = {
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/', 'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
@ -22,17 +23,32 @@ class KanKidsIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
a = super()._match_valid_url(url) m = super()._match_valid_url(url)
print(a.groupdict()) series_id = m.group('id')
video_id = self._match_id(url) category = m.group('category')
webpage = self._download_webpage(url, video_id) playlist_season = m.group('season')
webpage = self._download_webpage(url, series_id)
# TODO more code goes here, for example ... series_title = self._html_search_regex(r'<title>(?P<title>.+) \|', webpage, 'title')
# title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
title = 'hi' season = playlist_season if playlist_season else '(?P<season>\w+)'
playlist = set(re.findall(
r'href="/content/kids/' + # Content dir
category + r'-main/' + # Category
'p-' + series_id + '/' + # Series
season + '/' + # Season
'(?P<id>[0-9]+)/"' + # Episode
'.+title="(?P<title>.+)"' # Title
, webpage))
# , 'Episode list')
print('playlist:', playlist)
for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
pass
return { return {
'id': video_id, 'id': series_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/s1/89707/', 'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/s1/89707/',