youtube-dl/youtube_dl/extractor/xtube.py

78 lines
2.9 KiB
Python
Raw Normal View History

2014-02-11 16:57:49 +09:00
from __future__ import unicode_literals
2013-10-29 03:23:48 +09:00
import re
2014-03-22 01:58:40 +09:00
import json
2013-10-29 03:23:48 +09:00
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
parse_duration,
str_to_int,
2013-10-29 03:23:48 +09:00
)
2013-10-29 03:23:48 +09:00
class XTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
2013-10-29 03:23:48 +09:00
_TEST = {
2014-02-11 16:57:49 +09:00
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
'info_dict': {
'id': 'kVTUy_G222_',
'ext': 'mp4',
'title': 'strange erotica',
'description': 'surreal gay themed erotica...almost an ET kind of thing',
'uploader': 'greenshowers',
'duration': 450,
'age_limit': 18,
2013-10-29 03:23:48 +09:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False)
video_description = self._html_search_regex(
r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False)
duration = parse_duration(self._html_search_regex(
r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False))
view_count = self._html_search_regex(
r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False)
if view_count:
view_count = str_to_int(view_count)
comment_count = self._html_search_regex(
r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False)
if comment_count:
comment_count = str_to_int(comment_count)
2014-03-22 01:58:40 +09:00
player_quality_option = json.loads(self._html_search_regex(
r'playerQualityOption = ({.+?});', webpage, 'player quality option'))
QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080']
formats = [
{
'url': furl,
2014-03-22 01:58:40 +09:00
'format_id': format_id,
'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1,
} for format_id, furl in player_quality_option.items()
2014-03-22 01:58:40 +09:00
]
self._sort_formats(formats)
2013-10-29 03:23:48 +09:00
return {
'id': video_id,
'title': video_title,
'uploader': video_uploader,
'description': video_description,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
2014-03-22 01:58:40 +09:00
'formats': formats,
2013-10-29 03:23:48 +09:00
'age_limit': 18,
2014-03-22 01:58:40 +09:00
}