yt-dlp/yt_dlp/extractor/xtube.py

215 lines
7.7 KiB
Python
Raw Normal View History

import itertools
2013-10-28 19:23:48 +01:00
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
js_to_json,
orderedSet,
parse_duration,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
sanitized_Request,
str_to_int,
url_or_none,
2013-10-28 19:23:48 +01:00
)
2013-10-28 19:23:48 +01:00
class XTubeIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
xtube:|
https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
)
(?P<id>[^/?&#]+)
'''
2016-02-16 17:05:23 +01:00
_TESTS = [{
# old URL schema
2014-02-11 08:57:49 +01:00
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
'info_dict': {
'id': 'kVTUy_G222_',
'ext': 'mp4',
'title': 'strange erotica',
2015-02-18 19:58:41 +01:00
'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers',
'duration': 450,
'view_count': int,
'comment_count': int,
'age_limit': 18,
2013-10-28 19:23:48 +01:00
}
2016-02-16 17:05:23 +01:00
}, {
# new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
'only_matching': True,
}, {
'url': 'xtube:625837',
'only_matching': True,
}, {
'url': 'xtube:kVTUy_G222_',
'only_matching': True,
}, {
'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
'only_matching': True,
2016-02-16 17:05:23 +01:00
}]
2013-10-28 19:23:48 +01:00
def _real_extract(self, url):
mobj = self._match_valid_url(url)
2016-02-16 17:05:23 +01:00
video_id = mobj.group('id')
display_id = mobj.group('display_id')
if not display_id:
display_id = video_id
if video_id.isdigit() and len(video_id) < 11:
url_pattern = 'http://www.xtube.com/video-watch/-%s'
else:
url_pattern = 'http://www.xtube.com/watch.php?v=%s'
webpage = self._download_webpage(
url_pattern % video_id, display_id, headers={
'Cookie': 'age_verified=1; cookiesAccepted=1',
})
2013-10-28 19:23:48 +01:00
title, thumbnail, duration, sources, media_definition = [None] * 5
config = self._parse_json(self._search_regex(
r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf|playerWrapper)', webpage, 'config',
default='{}'), video_id, transform_source=js_to_json, fatal=False)
if config:
config = config.get('mainRoll')
if isinstance(config, dict):
title = config.get('title')
thumbnail = config.get('poster')
duration = int_or_none(config.get('duration'))
sources = config.get('sources') or config.get('format')
media_definition = config.get('mediaDefinition')
if not isinstance(sources, dict) and not media_definition:
sources = self._parse_json(self._search_regex(
r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
webpage, 'sources', group='sources'), video_id,
transform_source=js_to_json)
formats = []
format_urls = set()
if isinstance(sources, dict):
for format_id, format_url in sources.items():
format_url = url_or_none(format_url)
if not format_url:
continue
if format_url in format_urls:
continue
format_urls.add(format_url)
formats.append({
'url': format_url,
'format_id': format_id,
'height': int_or_none(format_id),
})
if isinstance(media_definition, list):
for media in media_definition:
video_url = url_or_none(media.get('videoUrl'))
if not video_url:
continue
if video_url in format_urls:
continue
format_urls.add(video_url)
format_id = media.get('format')
if format_id == 'hls':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif format_id == 'mp4':
height = int_or_none(media.get('quality'))
formats.append({
'url': video_url,
'format_id': '%s-%d' % (format_id, height) if height else format_id,
'height': height,
})
self._remove_duplicate_formats(formats)
if not title:
title = self._search_regex(
(r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
webpage, 'title', group='title')
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'twitter:description', webpage, default=None) or self._search_regex(
2016-02-16 17:05:23 +01:00
r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
uploader = self._search_regex(
(r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
webpage, 'uploader', fatal=False)
if not duration:
duration = parse_duration(self._search_regex(
r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
webpage, 'duration', fatal=False))
2016-02-16 17:05:23 +01:00
view_count = str_to_int(self._search_regex(
(r'["\']viewsCount["\'][^>]*>(\d+)\s+views',
r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'),
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
2016-02-16 17:05:23 +01:00
r'>Comments? \(([\d,\.]+)\)<',
webpage, 'comment count', fatal=False))
2014-03-21 17:58:40 +01:00
2013-10-28 19:23:48 +01:00
return {
'id': video_id,
2016-02-16 17:05:23 +01:00
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
2016-02-16 17:05:23 +01:00
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
2013-10-28 19:23:48 +01:00
'age_limit': 18,
'formats': formats,
2014-03-22 19:16:35 +01:00
}
2014-03-22 19:16:35 +01:00
class XTubeUserIE(InfoExtractor):
IE_DESC = 'XTube user profile'
_VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
_TEST = {
'url': 'http://www.xtube.com/profile/greenshowers-4056496',
'info_dict': {
'id': 'greenshowers-4056496',
'age_limit': 18,
},
2020-02-29 17:51:56 +01:00
'playlist_mincount': 154,
}
2014-03-22 19:16:35 +01:00
def _real_extract(self, url):
user_id = self._match_id(url)
entries = []
for pagenum in itertools.count(1):
request = sanitized_Request(
'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
headers={
'Cookie': 'popunder=4',
'X-Requested-With': 'XMLHttpRequest',
'Referer': url,
})
page = self._download_json(
request, user_id, 'Downloading videos JSON page %d' % pagenum)
html = page.get('html')
if not html:
break
for video_id in orderedSet([video_id for _, video_id in re.findall(
r'data-plid=(["\'])(.+?)\1', html)]):
entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
page_count = int_or_none(page.get('pageCount'))
if not page_count or pagenum == page_count:
break
playlist = self.playlist_result(entries, user_id)
playlist['age_limit'] = 18
return playlist