0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-05 04:17:27 +00:00
yt-dlp/yt_dlp/extractor/teachertube.py
sepro add96eb9f8
[cleanup] Add more ruff rules (#10149)
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

126 lines
4.2 KiB
Python

import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
qualities,
)
class TeacherTubeIE(InfoExtractor):
_WORKING = False
IE_NAME = 'teachertube'
IE_DESC = 'teachertube.com videos'
_VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)'
_TESTS = [{
# flowplayer
'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
'md5': 'f9434ef992fd65936d72999951ee254c',
'info_dict': {
'id': '339997',
'ext': 'mp4',
'title': 'Measures of dispersion from a frequency table',
'description': 'Measures of dispersion from a frequency table',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
}, {
# jwplayer
'url': 'http://www.teachertube.com/music.php?music_id=8805',
'md5': '01e8352006c65757caf7b961f6050e21',
'info_dict': {
'id': '8805',
'ext': 'mp3',
'title': 'PER ASPERA AD ASTRA',
'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
},
}, {
# unavailable video
'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
error = self._search_regex(
r'<div\b[^>]+\bclass=["\']msgBox error[^>]+>([^<]+)', webpage,
'error', default=None)
if error:
raise ExtractorError(f'{self.IE_NAME} said: {error}', expected=True)
title = self._html_search_meta('title', webpage, 'title', fatal=True)
TITLE_SUFFIX = ' - TeacherTube'
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)].strip()
description = self._html_search_meta('description', webpage, 'description')
if description:
description = description.strip()
quality = qualities(['mp3', 'flv', 'mp4'])
media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
formats = [
{
'url': media_url,
'quality': quality(determine_ext(media_url)),
} for media_url in set(media_urls)
]
thumbnail = self._og_search_thumbnail(
webpage, default=None) or self._html_search_meta(
'thumbnail', webpage)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}
class TeacherTubeUserIE(InfoExtractor):
_WORKING = False
IE_NAME = 'teachertube:user:collection'
IE_DESC = 'teachertube.com user and collection videos'
_VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
_MEDIA_RE = r'''(?sx)
class="?sidebar_thumb_time"?>[0-9:]+</div>
\s*
<a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
'''
_TEST = {
'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
'info_dict': {
'id': 'rbhagwati2',
},
'playlist_mincount': 179,
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
user_id = mobj.group('user')
urls = []
webpage = self._download_webpage(url, user_id)
urls.extend(re.findall(self._MEDIA_RE, webpage))
pages = re.findall(rf'/ajax-user/user-videos/{user_id}\?page=([0-9]+)', webpage)[:-1]
for p in pages:
more = f'http://www.teachertube.com/ajax-user/user-videos/{user_id}?page={p}'
webpage = self._download_webpage(more, user_id, f'Downloading page {p}/{len(pages)}')
video_urls = re.findall(self._MEDIA_RE, webpage)
urls.extend(video_urls)
entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
return self.playlist_result(entries, user_id)