yt-dlc/yt_dlp/extractor/eporner.py

133 lines
4.6 KiB
Python
Raw Normal View History

2014-08-30 20:28:53 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-08-31 21:51:36 +00:00
from ..utils import (
encode_base_n,
ExtractorError,
int_or_none,
merge_dicts,
2014-08-31 21:51:36 +00:00
parse_duration,
str_to_int,
2018-07-21 12:08:28 +00:00
url_or_none,
2014-08-31 21:51:36 +00:00
)
2014-08-30 20:28:53 +00:00
class EpornerIE(InfoExtractor):
2021-01-01 12:26:37 +00:00
_VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:(?:hd-porn|embed)/|video-)(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
2014-08-30 20:28:53 +00:00
'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
'md5': '39d486f046212d8e1b911c52ab4691f8',
2014-08-30 20:28:53 +00:00
'info_dict': {
'id': 'qlDUmNsj6VS',
2014-09-02 14:39:22 +00:00
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
'ext': 'mp4',
2014-08-30 20:28:53 +00:00
'title': 'Infamous Tiffany Teen Strip Tease Video',
'description': 'md5:764f39abf932daafa37485eb46efa152',
'timestamp': 1232520922,
'upload_date': '20090121',
2014-11-16 13:55:22 +00:00
'duration': 1838,
2014-08-31 21:51:36 +00:00
'view_count': int,
2014-09-01 21:07:48 +00:00
'age_limit': 18,
},
'params': {
'proxy': '127.0.0.1:8118'
}
2016-05-25 14:51:17 +00:00
}, {
# New (May 2016) URL layout
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
2016-05-25 14:51:17 +00:00
'only_matching': True,
}, {
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
'only_matching': True,
}, {
2021-01-01 12:26:37 +00:00
'url': 'http://www.eporner.com/embed/3YRUtzMcWn0',
'only_matching': True,
}, {
'url': 'https://www.eporner.com/video-FJsA19J3Y3H/one-of-the-greats/',
'only_matching': True,
}]
2014-08-30 20:28:53 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage, urlh = self._download_webpage_handle(url, display_id)
video_id = self._match_id(urlh.geturl())
2014-09-02 14:39:22 +00:00
hash = self._search_regex(
2021-01-01 12:26:37 +00:00
r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash')
2014-08-30 20:28:53 +00:00
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
r'<title>(.+?) - EPORNER', webpage, 'title')
2014-09-02 14:39:22 +00:00
# Reverse engineered from vjs.js
def calc_hash(s):
return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8)))
video = self._download_json(
'http://www.eporner.com/xhr/video/%s' % video_id,
display_id, note='Downloading video JSON',
query={
'hash': calc_hash(hash),
'device': 'generic',
'domain': 'www.eporner.com',
'fallback': 'false',
})
if video.get('available') is False:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, video['message']), expected=True)
sources = video['sources']
2014-09-02 14:39:22 +00:00
formats = []
for kind, formats_dict in sources.items():
if not isinstance(formats_dict, dict):
continue
for format_id, format_dict in formats_dict.items():
if not isinstance(format_dict, dict):
continue
2018-07-21 12:08:28 +00:00
src = url_or_none(format_dict.get('src'))
if not src or not src.startswith('http'):
continue
if kind == 'hls':
formats.extend(self._extract_m3u8_formats(
src, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=kind, fatal=False))
else:
height = int_or_none(self._search_regex(
r'(\d+)[pP]', format_id, 'height', default=None))
fps = int_or_none(self._search_regex(
r'(\d+)fps', format_id, 'fps', default=None))
formats.append({
'url': src,
'format_id': format_id,
'height': height,
'fps': fps,
})
2014-09-02 14:39:22 +00:00
self._sort_formats(formats)
2014-08-30 20:28:53 +00:00
json_ld = self._search_json_ld(webpage, display_id, default={})
duration = parse_duration(self._html_search_meta(
'duration', webpage, default=None))
2014-08-31 21:51:36 +00:00
view_count = str_to_int(self._search_regex(
2021-01-01 12:26:37 +00:00
r'id=["\']cinemaviews1["\'][^>]*>\s*([0-9,]+)',
webpage, 'view count', default=None))
2014-08-30 20:28:53 +00:00
return merge_dicts(json_ld, {
2014-08-30 20:28:53 +00:00
'id': video_id,
2014-09-02 14:39:22 +00:00
'display_id': display_id,
2014-08-30 20:28:53 +00:00
'title': title,
2014-08-31 21:51:36 +00:00
'duration': duration,
'view_count': view_count,
2014-09-02 14:39:22 +00:00
'formats': formats,
'age_limit': 18,
})