yt-dlp/youtube_dl/extractor/drtuber.py

72 lines
2.6 KiB
Python
Raw Normal View History

2014-09-01 14:12:51 -04:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-09-02 09:36:26 -04:00
from ..utils import str_to_int
2014-09-01 14:12:51 -04:00
class DrTuberIE(InfoExtractor):
2014-09-02 09:39:16 -04:00
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
2014-09-01 14:12:51 -04:00
_TEST = {
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
'id': '1740434',
2014-09-02 10:40:03 -04:00
'display_id': 'hot-perky-blonde-naked-golf',
2014-09-01 14:12:51 -04:00
'ext': 'mp4',
2015-02-14 07:50:13 -05:00
'title': 'hot perky blonde naked golf',
2014-09-02 09:36:26 -04:00
'like_count': int,
'dislike_count': int,
'comment_count': int,
2014-09-18 09:56:54 -04:00
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
2014-09-01 14:12:51 -04:00
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
2014-09-01 14:12:51 -04:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-02 09:39:16 -04:00
display_id = mobj.group('display_id')
2014-09-01 14:12:51 -04:00
2014-09-02 09:39:16 -04:00
webpage = self._download_webpage(url, display_id)
2014-09-01 14:12:51 -04:00
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
2015-02-14 07:50:13 -05:00
[r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
webpage, 'title')
2014-09-01 14:12:51 -04:00
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
2014-09-02 09:36:26 -04:00
like_count = str_to_int(self._html_search_regex(
r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._html_search_regex(
r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
webpage, 'like count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'<span class="comments_count">([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
2014-09-18 09:56:54 -04:00
cats_str = self._search_regex(
r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
2014-09-01 14:12:51 -04:00
return {
'id': video_id,
2014-09-02 09:39:16 -04:00
'display_id': display_id,
2014-09-01 14:12:51 -04:00
'url': video_url,
'title': title,
'thumbnail': thumbnail,
2014-09-02 09:36:26 -04:00
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
2014-09-01 14:12:51 -04:00
'categories': categories,
'age_limit': self._rta_search(webpage),
2014-09-01 14:12:51 -04:00
}