1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/xhamster.py

136 lines
4.9 KiB
Python
Raw Normal View History

2014-01-23 02:52:59 +00:00
from __future__ import unicode_literals
2013-06-23 20:32:44 +00:00
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
2014-02-19 18:42:15 +00:00
unified_strdate,
str_to_int,
int_or_none,
parse_duration,
2013-06-23 20:32:44 +00:00
)
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
2015-01-02 11:52:48 +00:00
_VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
2014-02-19 18:42:15 +00:00
_TESTS = [
{
'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
'info_dict': {
'id': '1509445',
'ext': 'mp4',
'title': 'FemaleAgent Shy beauty takes the bait',
'upload_date': '20121014',
'uploader_id': 'Ruseful2011',
'duration': 893,
'age_limit': 18,
}
},
{
'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
'info_dict': {
'id': '2221348',
'ext': 'mp4',
'title': 'Britney Spears Sexy Booty',
'upload_date': '20130914',
'uploader_id': 'jojo747400',
'duration': 200,
'age_limit': 18,
}
2015-01-02 11:52:48 +00:00
},
{
'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
2015-01-02 15:12:25 +00:00
'only_matching': True,
2015-01-02 11:52:48 +00:00
},
2014-02-19 18:42:15 +00:00
]
2013-06-23 20:32:44 +00:00
2014-11-23 19:41:03 +00:00
def _real_extract(self, url):
2013-10-26 18:38:54 +00:00
def extract_video_url(webpage):
2014-02-19 18:42:15 +00:00
mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
if mp4 is None:
2014-02-19 18:42:15 +00:00
raise ExtractorError('Unable to extract media URL')
else:
return mp4.group(1)
2013-10-26 18:38:54 +00:00
def is_hd(webpage):
2014-01-23 03:04:35 +00:00
return '<div class=\'icon iconHD\'' in webpage
2013-10-26 18:38:54 +00:00
2013-06-23 20:32:44 +00:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
seo = mobj.group('seo')
2015-01-02 11:52:48 +00:00
proto = mobj.group('proto')
mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
2013-06-23 20:32:44 +00:00
webpage = self._download_webpage(mrss_url, video_id)
2014-02-19 18:42:15 +00:00
title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
2013-06-23 20:32:44 +00:00
2013-08-23 14:40:20 +00:00
# Only a few videos have an description
2014-01-23 03:04:35 +00:00
mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
2014-02-19 18:42:15 +00:00
description = mobj.group(1) if mobj else None
2013-06-23 20:32:44 +00:00
2014-02-19 18:42:15 +00:00
upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
2014-11-23 20:39:15 +00:00
webpage, 'upload date', fatal=False)
2014-02-19 18:42:15 +00:00
if upload_date:
upload_date = unified_strdate(upload_date)
2013-06-23 20:32:44 +00:00
2014-02-19 18:42:15 +00:00
uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
2014-11-23 20:39:15 +00:00
webpage, 'uploader id', default='anonymous')
2013-06-23 20:32:44 +00:00
2014-02-19 18:42:15 +00:00
thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
2014-11-23 20:39:15 +00:00
webpage, 'duration', fatal=False))
2014-02-19 18:42:15 +00:00
view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
if view_count:
view_count = str_to_int(view_count)
mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
(like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
comment_count = mobj.group('commentcount') if mobj else 0
2013-06-23 20:32:44 +00:00
age_limit = self._rta_search(webpage)
2013-10-26 18:38:54 +00:00
hd = is_hd(webpage)
2014-02-19 18:42:15 +00:00
video_url = extract_video_url(webpage)
2013-10-26 18:38:54 +00:00
formats = [{
'url': video_url,
'format_id': 'hd' if hd else 'sd',
2014-02-19 18:42:15 +00:00
'preference': 1,
2013-10-26 18:38:54 +00:00
}]
2013-10-26 18:38:54 +00:00
if not hd:
mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
2014-02-19 18:42:15 +00:00
webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
2013-10-26 18:38:54 +00:00
if is_hd(webpage):
video_url = extract_video_url(webpage)
formats.append({
'url': video_url,
'format_id': 'hd',
2014-01-23 03:04:35 +00:00
'preference': 2,
2013-10-26 18:38:54 +00:00
})
2014-01-23 03:04:35 +00:00
self._sort_formats(formats)
2013-10-26 18:38:54 +00:00
return {
'id': video_id,
2014-02-19 18:42:15 +00:00
'title': title,
'description': description,
'upload_date': upload_date,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'like_count': int_or_none(like_count),
'dislike_count': int_or_none(dislike_count),
'comment_count': int_or_none(comment_count),
'age_limit': age_limit,
2014-02-19 18:42:15 +00:00
'formats': formats,
2013-10-26 18:38:54 +00:00
}