yt-dlp/youtube_dl/extractor/drtuber.py

87 lines
3.0 KiB
Python
Raw Normal View History

2014-09-01 12:12:51 -06:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
NO_DEFAULT,
str_to_int,
)
2014-09-01 12:12:51 -06:00
class DrTuberIE(InfoExtractor):
2016-11-06 07:28:51 -07:00
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
2014-09-01 12:12:51 -06:00
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
'id': '1740434',
2014-09-02 08:40:03 -06:00
'display_id': 'hot-perky-blonde-naked-golf',
2014-09-01 12:12:51 -06:00
'ext': 'mp4',
2015-02-14 05:50:13 -07:00
'title': 'hot perky blonde naked golf',
2014-09-02 07:36:26 -06:00
'like_count': int,
'comment_count': int,
2014-09-18 07:56:54 -06:00
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
2014-09-01 12:12:51 -06:00
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
2014-09-01 12:12:51 -06:00
}
2016-11-06 07:28:51 -07:00
}, {
'url': 'http://www.drtuber.com/embed/489939',
'only_matching': True,
}]
2014-09-01 12:12:51 -06:00
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
webpage)
2014-09-01 12:12:51 -06:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2016-11-06 07:28:51 -07:00
display_id = mobj.group('display_id') or video_id
2014-09-01 12:12:51 -06:00
2016-11-06 07:28:51 -07:00
webpage = self._download_webpage(
'http://www.drtuber.com/video/%s' % video_id, display_id)
2014-09-01 12:12:51 -06:00
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
2016-11-06 07:29:15 -07:00
(r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
2016-08-11 10:47:52 -06:00
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
2015-02-14 05:50:13 -07:00
webpage, 'title')
2014-09-01 12:12:51 -06:00
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
def extract_count(id_, name, default=NO_DEFAULT):
2015-07-01 09:47:56 -06:00
return str_to_int(self._html_search_regex(
r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
webpage, '%s count' % name, default=default, fatal=False))
2015-07-01 09:47:56 -06:00
like_count = extract_count('rate_likes', 'like')
dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
2015-07-01 09:47:56 -06:00
comment_count = extract_count('comments_count', 'comment')
2014-09-02 07:36:26 -06:00
2014-09-18 07:56:54 -06:00
cats_str = self._search_regex(
r'<div[^>]+class="categories_list">(.+?)</div>',
webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(
r'<a title="([^"]+)"', cats_str)
2014-09-01 12:12:51 -06:00
return {
'id': video_id,
2014-09-02 07:39:16 -06:00
'display_id': display_id,
2014-09-01 12:12:51 -06:00
'url': video_url,
'title': title,
'thumbnail': thumbnail,
2014-09-02 07:36:26 -06:00
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
2014-09-01 12:12:51 -06:00
'categories': categories,
'age_limit': self._rta_search(webpage),
2014-09-01 12:12:51 -06:00
}