mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-07-01 09:50:05 +02:00
Compare commits
4 Commits
9552063b73
...
674d172a31
Author | SHA1 | Date | |
---|---|---|---|
|
674d172a31 | ||
|
f3411af12e | ||
|
2f66504571 | ||
|
c0edd1c194 |
|
@ -216,6 +216,9 @@
|
||||||
BBCCoUkIPlayerGroupIE,
|
BBCCoUkIPlayerGroupIE,
|
||||||
BBCCoUkPlaylistIE,
|
BBCCoUkPlaylistIE,
|
||||||
)
|
)
|
||||||
|
from .bbcmaestro import (
|
||||||
|
BBCMaestroComIE,
|
||||||
|
)
|
||||||
from .beatbump import (
|
from .beatbump import (
|
||||||
BeatBumpPlaylistIE,
|
BeatBumpPlaylistIE,
|
||||||
BeatBumpVideoIE,
|
BeatBumpVideoIE,
|
||||||
|
|
122
yt_dlp/extractor/bbcmaestro.py
Normal file
122
yt_dlp/extractor/bbcmaestro.py
Normal file
|
@ -0,0 +1,122 @@
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import orderedSet, smuggle_url, unsmuggle_url
|
||||||
|
|
||||||
|
|
||||||
|
class BBCMaestroComIE(InfoExtractor):
|
||||||
|
_VALID_URL = (
|
||||||
|
r'https?://(?:www\.)?bbcmaestro\.com/courses/(?P<id>[^?]+)'
|
||||||
|
)
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.bbcmaestro.com/courses/julia-donaldson/writing-children-s-picture-books/trailer',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'julia-donaldson/writing-children-s-picture-books/trailer',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Course trailer',
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
'skip_download': True,
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _do_extract_video(self, url, webpage, video_id):
|
||||||
|
if '/lessons/' not in url:
|
||||||
|
title = 'Course trailer'
|
||||||
|
else:
|
||||||
|
title = self._html_search_regex(
|
||||||
|
r'<h1\b[^>]*lesson[^>]*title[^>]*>\s*(.+?)\s*</h1>',
|
||||||
|
webpage,
|
||||||
|
name='title',
|
||||||
|
flags=re.RegexFlag.S,
|
||||||
|
)
|
||||||
|
|
||||||
|
m3u8_url = self._html_search_regex(
|
||||||
|
r'<source[^>]+src="?\'?(\S+\.m3u8)',
|
||||||
|
webpage,
|
||||||
|
'video URL',
|
||||||
|
)
|
||||||
|
formats = []
|
||||||
|
if m3u8_url:
|
||||||
|
formats = self._extract_m3u8_formats(
|
||||||
|
m3u8_url=m3u8_url,
|
||||||
|
video_id=video_id,
|
||||||
|
ext='mp4',
|
||||||
|
m3u8_id='hls',
|
||||||
|
fatal=False,
|
||||||
|
)
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'title': title,
|
||||||
|
'formats': formats,
|
||||||
|
}
|
||||||
|
|
||||||
|
def _do_extract_playlist(self, url, webpage):
|
||||||
|
# Twitter Title usually: <Lesson Title> - <Author> | <Course Title>
|
||||||
|
twitter_title = self._html_search_meta(
|
||||||
|
['twitter:title'],
|
||||||
|
webpage,
|
||||||
|
fatal=True,
|
||||||
|
)
|
||||||
|
playlist_title = (
|
||||||
|
twitter_title
|
||||||
|
.split('-', maxsplit=1)[-1]
|
||||||
|
.replace('|', '-')
|
||||||
|
)
|
||||||
|
|
||||||
|
url_without_query_parameters = url.split('?', maxsplit=1)[0]
|
||||||
|
self.write_debug(f'url_without_query_parameters: {url_without_query_parameters}')
|
||||||
|
playlist_id = self._search_regex(
|
||||||
|
pattern=r'.*/courses/([^/]+/[^/]+).*',
|
||||||
|
string=url_without_query_parameters,
|
||||||
|
name='Playlist ID (from URL)',
|
||||||
|
fatal=True,
|
||||||
|
)
|
||||||
|
self.write_debug(f'playlist_id: {playlist_id}')
|
||||||
|
entries = [
|
||||||
|
self.url_result(
|
||||||
|
smuggle_url(
|
||||||
|
f'https://www.bbcmaestro.com/courses/{playlist_id}/lessons/{item_video_id}',
|
||||||
|
{'forcevideo': True},
|
||||||
|
),
|
||||||
|
ie=BBCMaestroComIE.ie_key(),
|
||||||
|
)
|
||||||
|
for item_video_id in orderedSet(re.findall(
|
||||||
|
r'href=[^>]*/courses/' + re.escape(playlist_id) + r'/lessons/([^?]+)',
|
||||||
|
webpage,
|
||||||
|
))
|
||||||
|
]
|
||||||
|
# self.write_debug('entries: %r' % entries)
|
||||||
|
return self.playlist_result(
|
||||||
|
entries=entries,
|
||||||
|
playlist_id=playlist_id,
|
||||||
|
playlist_title=playlist_title,
|
||||||
|
)
|
||||||
|
|
||||||
|
def _check_login_provided(self):
|
||||||
|
if not self._cookies_passed:
|
||||||
|
self.raise_login_required('Login details are needed to download this content', method='cookies')
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
url, smuggled_data = unsmuggle_url(url, {})
|
||||||
|
self.write_debug(f'Extracting from: {url}')
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
self.write_debug(f'Video ID: {video_id}')
|
||||||
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
|
is_private_course_content = ('/lessons/' in url)
|
||||||
|
is_login_required = is_private_course_content
|
||||||
|
if is_login_required:
|
||||||
|
# Note: We can only download the course trailer without login
|
||||||
|
self._check_login_provided()
|
||||||
|
|
||||||
|
is_playlist = (
|
||||||
|
is_private_course_content
|
||||||
|
and not smuggled_data.get('forcevideo')
|
||||||
|
and not self.get_param('noplaylist')
|
||||||
|
)
|
||||||
|
|
||||||
|
if is_playlist:
|
||||||
|
return self._do_extract_playlist(url, webpage=webpage)
|
||||||
|
return self._do_extract_video(url, webpage=webpage, video_id=video_id)
|
|
@ -1,51 +1,35 @@
|
||||||
import random
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import xpath_text
|
|
||||||
|
|
||||||
|
|
||||||
class MatchTVIE(InfoExtractor):
|
class MatchTVIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
|
_VALID_URL = [
|
||||||
|
r'https?://matchtv\.ru/on-air/?(?:$|[?#])',
|
||||||
|
r'https?://video\.matchtv\.ru/iframe/channel/106/?(?:$|[?#])',
|
||||||
|
]
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://matchtv.ru/#live-player',
|
'url': 'http://matchtv.ru/on-air/',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'matchtv-live',
|
'id': 'matchtv-live',
|
||||||
'ext': 'flv',
|
'ext': 'mp4',
|
||||||
'title': r're:^Матч ТВ - Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
|
'title': r're:^Матч ТВ - Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
|
||||||
'is_live': True,
|
'live_status': 'is_live',
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://matchtv.ru/on-air/',
|
'url': 'https://video.matchtv.ru/iframe/channel/106',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = 'matchtv-live'
|
video_id = 'matchtv-live'
|
||||||
video_url = self._download_json(
|
webpage = self._download_webpage('https://video.matchtv.ru/iframe/channel/106', video_id)
|
||||||
'http://player.matchtv.ntvplus.tv/player/smil', video_id,
|
video_url = self._html_search_regex(
|
||||||
query={
|
r'data-config="config=(https?://[^?"]+)[?"]', webpage, 'video URL').replace('/feed/', '/media/') + '.m3u8'
|
||||||
'ts': '',
|
|
||||||
'quality': 'SD',
|
|
||||||
'contentId': '561d2c0df7159b37178b4567',
|
|
||||||
'sign': '',
|
|
||||||
'includeHighlights': '0',
|
|
||||||
'userId': '',
|
|
||||||
'sessionId': random.randint(1, 1000000000),
|
|
||||||
'contentType': 'channel',
|
|
||||||
'timeShift': '0',
|
|
||||||
'platform': 'portal',
|
|
||||||
},
|
|
||||||
headers={
|
|
||||||
'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
|
|
||||||
})['data']['videoUrl']
|
|
||||||
f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
|
|
||||||
formats = self._extract_f4m_formats(f4m_url, video_id)
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': 'Матч ТВ - Прямой эфир',
|
'title': 'Матч ТВ - Прямой эфир',
|
||||||
'is_live': True,
|
'is_live': True,
|
||||||
'formats': formats,
|
'formats': self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True),
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue
Block a user