SolarFM/plugins/youtube_download/yt_dlp/extractor/daftsex.py

151 lines
5.8 KiB
Python
Raw Normal View History

from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
2023-08-14 01:13:21 +00:00
ExtractorError,
int_or_none,
js_to_json,
parse_count,
parse_duration,
2023-02-21 01:18:45 +00:00
traverse_obj,
try_get,
2023-02-21 01:18:45 +00:00
unified_timestamp,
)
class DaftsexIE(InfoExtractor):
2023-08-14 01:13:21 +00:00
_VALID_URL = r'https?://(?:www\.)?daft\.sex/watch/(?P<id>-?\d+_\d+)'
_TESTS = [{
2023-08-14 01:13:21 +00:00
'url': 'https://daft.sex/watch/-35370899_456246186',
'md5': '64c04ef7b4c7b04b308f3b0c78efe7cd',
2023-02-21 01:18:45 +00:00
'info_dict': {
'id': '-35370899_456246186',
'ext': 'mp4',
'title': 'just relaxing',
2023-08-14 01:13:21 +00:00
'description': 'just relaxing Watch video Watch video in high quality',
2023-02-21 01:18:45 +00:00
'upload_date': '20201113',
'timestamp': 1605261911,
2023-08-14 01:13:21 +00:00
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
'duration': 15.0,
'view_count': int
2023-02-21 01:18:45 +00:00
},
}, {
2023-08-14 01:13:21 +00:00
'url': 'https://daft.sex/watch/-156601359_456242791',
'info_dict': {
'id': '-156601359_456242791',
'ext': 'mp4',
'title': 'Skye Blue - Dinner And A Show',
2023-02-21 01:18:45 +00:00
'description': 'Skye Blue - Dinner And A Show - Watch video Watch video in high quality',
'upload_date': '20200916',
'timestamp': 1600250735,
'thumbnail': 'https://psv153-1.crazycloud.ru/videos/-156601359/456242791/thumb.jpg?extra=i3D32KaBbBFf9TqDRMAVmQ',
},
2023-08-14 01:13:21 +00:00
'skip': 'deleted / private'
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2023-02-21 01:18:45 +00:00
title = self._html_search_meta('name', webpage, 'title')
timestamp = unified_timestamp(self._html_search_meta('uploadDate', webpage, 'Upload Date', default=None))
description = self._html_search_meta('description', webpage, 'Description', default=None)
duration = parse_duration(self._search_regex(
r'Duration: ((?:[0-9]{2}:){0,2}[0-9]{2})',
webpage, 'duration', fatal=False))
views = parse_count(self._search_regex(
r'Views: ([0-9 ]+)',
webpage, 'views', fatal=False))
player_hash = self._search_regex(
r'DaxabPlayer\.Init\({[\s\S]*hash:\s*"([0-9a-zA-Z_\-]+)"[\s\S]*}',
webpage, 'player hash')
player_color = self._search_regex(
r'DaxabPlayer\.Init\({[\s\S]*color:\s*"([0-9a-z]+)"[\s\S]*}',
webpage, 'player color', fatal=False) or ''
embed_page = self._download_webpage(
2023-08-14 01:13:21 +00:00
'https://dxb.to/player/%s?color=%s' % (player_hash, player_color),
video_id, headers={'Referer': url})
video_params = self._parse_json(
self._search_regex(
r'window\.globParams\s*=\s*({[\S\s]+})\s*;\s*<\/script>',
embed_page, 'video parameters'),
video_id, transform_source=js_to_json)
server_domain = 'https://%s' % compat_b64decode(video_params['server'][::-1]).decode('utf-8')
2023-02-21 01:18:45 +00:00
cdn_files = traverse_obj(video_params, ('video', 'cdn_files')) or {}
if cdn_files:
formats = []
for format_id, format_data in cdn_files.items():
ext, height = format_id.split('_')
formats.append({
'format_id': format_id,
'url': f'{server_domain}/videos/{video_id.replace("_", "/")}/{height}.mp4?extra={format_data.split(".")[-1]}',
'height': int_or_none(height),
'ext': ext,
})
return {
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'duration': duration,
'thumbnail': try_get(video_params, lambda vi: 'https:' + compat_b64decode(vi['video']['thumb']).decode('utf-8')),
'timestamp': timestamp,
'view_count': views,
'age_limit': 18,
}
2023-08-14 01:13:21 +00:00
items = self._download_json(
2023-02-21 01:18:45 +00:00
f'{server_domain}/method/video.get/{video_id}', video_id,
headers={'Referer': url}, query={
'token': video_params['video']['access_token'],
'videos': video_id,
'ckey': video_params['c_key'],
'credentials': video_params['video']['credentials'],
2023-08-14 01:13:21 +00:00
})['response']['items']
2023-02-21 01:18:45 +00:00
2023-08-14 01:13:21 +00:00
if not items:
raise ExtractorError('Video is not available', video_id=video_id, expected=True)
item = items[0]
formats = []
2023-02-21 01:18:45 +00:00
for f_id, f_url in item.get('files', {}).items():
if f_id == 'external':
return self.url_result(f_url)
ext, height = f_id.split('_')
height_extra_key = traverse_obj(video_params, ('video', 'partial', 'quality', height))
if height_extra_key:
formats.append({
'format_id': f'{height}p',
'url': f'{server_domain}/{f_url[8:]}&videos={video_id}&extra_key={height_extra_key}',
'height': int_or_none(height),
'ext': ext,
})
2023-02-21 01:18:45 +00:00
thumbnails = []
for k, v in item.items():
if k.startswith('photo_') and v:
width = k.replace('photo_', '')
thumbnails.append({
'id': width,
'url': v,
'width': int_or_none(width),
})
return {
'id': video_id,
'title': title,
'formats': formats,
2023-02-21 01:18:45 +00:00
'comment_count': int_or_none(item.get('comments')),
'description': description,
'duration': duration,
2023-02-21 01:18:45 +00:00
'thumbnails': thumbnails,
'timestamp': timestamp,
'view_count': views,
'age_limit': 18,
}