ytdl/youtube_dl/extractor/extremetube.py

93 lines
3.1 KiB
Python
Raw Normal View History

2014-04-19 19:42:51 +02:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
int_or_none,
2014-09-27 17:36:53 +02:00
str_to_int,
)
2014-04-19 19:42:51 +02:00
class ExtremeTubeIE(InfoExtractor):
2015-11-08 14:14:39 +01:00
_VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
_TESTS = [{
2014-04-19 19:42:51 +02:00
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
2014-04-19 19:42:51 +02:00
'info_dict': {
2015-11-08 14:14:39 +01:00
'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
2014-04-19 19:42:51 +02:00
'ext': 'mp4',
'title': 'Music Video 14 british euro brit european cumshots swallow',
'uploader': 'unknown',
2014-09-27 17:36:53 +02:00
'view_count': int,
2014-04-19 19:42:51 +02:00
'age_limit': 18,
}
}, {
'url': 'http://www.extremetube.com/gay/video/abcde-1234',
'only_matching': True,
2015-11-08 14:14:39 +01:00
}, {
'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
'only_matching': True,
}, {
'url': 'http://www.extremetube.com/video/652431',
'only_matching': True,
}]
def _real_extract(self, url):
2015-11-08 14:14:39 +01:00
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
2014-04-19 19:42:51 +02:00
video_title = self._html_search_regex(
r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
2014-04-19 19:42:51 +02:00
uploader = self._html_search_regex(
2014-09-27 17:36:53 +02:00
r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
webpage, 'uploader', fatal=False)
view_count = str_to_int(self._html_search_regex(
r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
webpage, 'view count', fatal=False))
flash_vars = self._parse_json(
self._search_regex(
r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
video_id)
formats = []
for quality_key, video_url in flash_vars.items():
height = int_or_none(self._search_regex(
r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
if not height:
continue
f = {
'url': video_url,
}
mobj = re.search(
r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
else:
f.update({
'format_id': '%dp' % height,
'height': height,
})
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': video_title,
'formats': formats,
'uploader': uploader,
2014-09-27 17:36:53 +02:00
'view_count': view_count,
'age_limit': 18,
}