youtube-dl/youtube_dl/extractor/eporner.py

120 lines
4.1 KiB
Python
Raw Normal View History

2014-08-31 05:28:53 +09:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
2014-09-01 06:51:36 +09:00
from ..utils import (
encode_base_n,
ExtractorError,
int_or_none,
2014-09-01 06:51:36 +09:00
parse_duration,
str_to_int,
)
2014-08-31 05:28:53 +09:00
class EpornerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:hd-porn|embed)/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
2014-08-31 05:28:53 +09:00
'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
'md5': '39d486f046212d8e1b911c52ab4691f8',
2014-08-31 05:28:53 +09:00
'info_dict': {
'id': 'qlDUmNsj6VS',
2014-09-02 23:39:22 +09:00
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
'ext': 'mp4',
2014-08-31 05:28:53 +09:00
'title': 'Infamous Tiffany Teen Strip Tease Video',
2014-11-16 22:55:22 +09:00
'duration': 1838,
2014-09-01 06:51:36 +09:00
'view_count': int,
2014-09-02 06:07:48 +09:00
'age_limit': 18,
},
2016-05-25 23:51:17 +09:00
}, {
# New (May 2016) URL layout
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
2016-05-25 23:51:17 +09:00
'only_matching': True,
}, {
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
'only_matching': True,
}, {
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
'only_matching': True,
}]
2014-08-31 05:28:53 +09:00
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(compat_str(urlh.geturl()))
2014-09-02 23:39:22 +09:00
hash = self._search_regex(
r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash')
2014-08-31 05:28:53 +09:00
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
r'<title>(.+?) - EPORNER', webpage, 'title')
2014-09-02 23:39:22 +09:00
# 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 23:39:22 +09:00
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
src = format_dict.get('src')
if not isinstance(src, compat_str) 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 23:39:22 +09:00
self._sort_formats(formats)
2014-08-31 05:28:53 +09:00
2014-11-16 22:55:22 +09:00
duration = parse_duration(self._html_search_meta('duration', webpage))
2014-09-01 06:51:36 +09:00
view_count = str_to_int(self._search_regex(
r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
webpage, 'view count', fatal=False))
2014-08-31 05:28:53 +09:00
return {
'id': video_id,
2014-09-02 23:39:22 +09:00
'display_id': display_id,
2014-08-31 05:28:53 +09:00
'title': title,
2014-09-01 06:51:36 +09:00
'duration': duration,
'view_count': view_count,
2014-09-02 23:39:22 +09:00
'formats': formats,
'age_limit': 18,
2014-08-31 05:28:53 +09:00
}