2022-10-02 07:11:53 +00:00
|
|
|
|
# coding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2022-10-02 09:08:43 +00:00
|
|
|
|
import base64
|
2022-10-02 07:11:53 +00:00
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
from ..utils import unified_timestamp, parse_duration
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class VXXXIE(InfoExtractor):
|
|
|
|
|
_VALID_URL = r'https?://vxxx\.com/video-(?P<id>\d+)'
|
|
|
|
|
_TESTS = [{
|
2022-10-02 09:08:43 +00:00
|
|
|
|
'url': 'https://vxxx.com/video-80747/',
|
2022-10-03 06:27:04 +00:00
|
|
|
|
'md5': '2f4bfd829b682ff9e3da1bda71b81b81',
|
2022-10-02 07:11:53 +00:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '80747',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Monica Aka Selina',
|
|
|
|
|
'display_id': 'monica-aka-selina',
|
|
|
|
|
'thumbnail': 'https://tn.vxxx.com/contents/videos_screenshots/80000/80747/420x236/1.jpg',
|
|
|
|
|
'description': '',
|
|
|
|
|
'timestamp': 1607167706,
|
|
|
|
|
'upload_date': '20201205',
|
|
|
|
|
'duration': 2373.0,
|
|
|
|
|
'categories': ['Anal', 'Asian', 'BDSM', 'Brunette', 'Toys',
|
|
|
|
|
'Fetish', 'HD', 'Interracial', 'MILF'],
|
2022-10-02 10:50:56 +00:00
|
|
|
|
'age_limit': 18,
|
|
|
|
|
}
|
|
|
|
|
}]
|
2022-10-02 07:11:53 +00:00
|
|
|
|
|
|
|
|
|
def _download_info_object(self, video_id):
|
|
|
|
|
return self._download_json(
|
|
|
|
|
'https://vxxx.com/api/json/video/86400/0/{}/{}.json'.format(
|
2022-10-02 09:08:43 +00:00
|
|
|
|
int(video_id) // 1000 * 1000,
|
2022-10-02 07:11:53 +00:00
|
|
|
|
video_id,
|
|
|
|
|
), video_id, headers={'Referer': 'https://vxxx.com'})['video']
|
|
|
|
|
|
|
|
|
|
def _download_format_object(self, video_id):
|
|
|
|
|
return self._download_json(
|
|
|
|
|
'https://vxxx.com/api/videofile.php?video_id={}'.format(video_id),
|
|
|
|
|
video_id,
|
|
|
|
|
headers={'Referer': 'https://vxxx.com'}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
def _get_video_host(self):
|
|
|
|
|
return 'vxxx.com'
|
|
|
|
|
|
2022-10-02 09:08:43 +00:00
|
|
|
|
def _decode_base164(self, e):
|
|
|
|
|
"""
|
2022-10-02 09:26:06 +00:00
|
|
|
|
Some non-standard encoding called "base164" in the JavaScript code. It's
|
|
|
|
|
similar to the regular base64 with a slightly different alphabet:
|
2022-10-02 09:08:43 +00:00
|
|
|
|
- "АВСЕМ" are Cyrillic letters instead of uppercase English letters
|
|
|
|
|
- "." is used instead of "+"; "," is used instead of "/"
|
|
|
|
|
- "~" is used for padding instead of "="
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
return base64.b64decode(e
|
|
|
|
|
.replace("А", "A")
|
|
|
|
|
.replace("В", "B")
|
|
|
|
|
.replace("С", "C")
|
|
|
|
|
.replace("Е", "E")
|
|
|
|
|
.replace("М", "M")
|
|
|
|
|
.replace(".", "+")
|
|
|
|
|
.replace(",", "/")
|
|
|
|
|
.replace("~", "=")
|
|
|
|
|
).decode()
|
2022-10-02 07:11:53 +00:00
|
|
|
|
|
|
|
|
|
def _extract_info(self, url):
|
2022-10-02 09:08:43 +00:00
|
|
|
|
matches = re.match(self._VALID_URL, url)
|
|
|
|
|
video_id = matches.group('id')
|
2022-10-02 07:11:53 +00:00
|
|
|
|
|
2022-10-02 09:08:43 +00:00
|
|
|
|
info_object = self._download_info_object(video_id)
|
2022-10-02 07:11:53 +00:00
|
|
|
|
|
|
|
|
|
info = {
|
2022-10-02 09:08:43 +00:00
|
|
|
|
'id': video_id,
|
2022-10-02 07:11:53 +00:00
|
|
|
|
'title': info_object['title'],
|
|
|
|
|
'display_id': info_object['dir'],
|
|
|
|
|
'thumbnail': info_object['thumb'],
|
|
|
|
|
'description': info_object['description'],
|
|
|
|
|
'timestamp': unified_timestamp(info_object['post_date']),
|
|
|
|
|
'duration': parse_duration(info_object['duration']),
|
|
|
|
|
'view_count': int(info_object['statistics']['viewed']),
|
|
|
|
|
'like_count': int(info_object['statistics']['likes']),
|
|
|
|
|
'dislike_count': int(info_object['statistics']['dislikes']),
|
|
|
|
|
'average_rating': float(info_object['statistics']['rating']),
|
|
|
|
|
'categories': [category['title'] for category in info_object['categories'].values()],
|
2022-10-02 10:50:56 +00:00
|
|
|
|
'age_limit': 18,
|
2022-10-02 07:11:53 +00:00
|
|
|
|
'formats': None
|
|
|
|
|
}
|
|
|
|
|
|
2022-10-02 09:08:43 +00:00
|
|
|
|
format_object = self._download_format_object(video_id)
|
2022-10-03 06:27:04 +00:00
|
|
|
|
m3u8_formats = self._extract_m3u8_formats(
|
|
|
|
|
"https://{}{}&f=video.m3u8".format(
|
2022-10-02 07:11:53 +00:00
|
|
|
|
self._get_video_host(),
|
2022-10-03 06:27:04 +00:00
|
|
|
|
self._decode_base164(format_object[0]['video_url'])
|
2022-10-02 07:11:53 +00:00
|
|
|
|
),
|
2022-10-03 06:27:04 +00:00
|
|
|
|
video_id, 'mp4')
|
|
|
|
|
self._sort_formats(m3u8_formats)
|
|
|
|
|
info['formats'] = m3u8_formats
|
2022-10-02 07:11:53 +00:00
|
|
|
|
|
|
|
|
|
return info
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
info = self._extract_info(url)
|
|
|
|
|
|
|
|
|
|
if not info['formats']:
|
|
|
|
|
return self.url_result(url, 'Generic')
|
|
|
|
|
|
|
|
|
|
return info
|