youtube-dl/youtube_dl/extractor/drtuber.py

71 lines
2.5 KiB
Python
Raw Normal View History

2014-09-01 18:12:51 +00:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-09-02 13:36:26 +00:00
from ..utils import str_to_int
2014-09-01 18:12:51 +00:00
class DrTuberIE(InfoExtractor):
2014-09-02 13:39:16 +00:00
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
2014-09-01 18:12:51 +00:00
_TEST = {
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
'id': '1740434',
2014-09-02 14:40:03 +00:00
'display_id': 'hot-perky-blonde-naked-golf',
2014-09-01 18:12:51 +00:00
'ext': 'mp4',
2015-02-14 12:50:13 +00:00
'title': 'hot perky blonde naked golf',
2014-09-02 13:36:26 +00:00
'like_count': int,
'dislike_count': int,
'comment_count': int,
2014-09-18 13:56:54 +00:00
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
2014-09-01 18:12:51 +00:00
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
2014-09-01 18:12:51 +00:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-02 13:39:16 +00:00
display_id = mobj.group('display_id')
2014-09-01 18:12:51 +00:00
2014-09-02 13:39:16 +00:00
webpage = self._download_webpage(url, display_id)
2014-09-01 18:12:51 +00:00
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
2015-07-01 15:47:56 +00:00
[r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
2015-02-14 12:50:13 +00:00
webpage, 'title')
2014-09-01 18:12:51 +00:00
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
2015-07-01 15:47:56 +00:00
def extract_count(id_, name):
return str_to_int(self._html_search_regex(
r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
webpage, '%s count' % name, fatal=False))
like_count = extract_count('rate_likes', 'like')
dislike_count = extract_count('rate_dislikes', 'dislike')
comment_count = extract_count('comments_count', 'comment')
2014-09-02 13:36:26 +00:00
2014-09-18 13:56:54 +00:00
cats_str = self._search_regex(
2015-07-01 15:47:56 +00:00
r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
2014-09-18 13:56:54 +00:00
categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
2014-09-01 18:12:51 +00:00
return {
'id': video_id,
2014-09-02 13:39:16 +00:00
'display_id': display_id,
2014-09-01 18:12:51 +00:00
'url': video_url,
'title': title,
'thumbnail': thumbnail,
2014-09-02 13:36:26 +00:00
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
2014-09-01 18:12:51 +00:00
'categories': categories,
'age_limit': self._rta_search(webpage),
2014-09-01 18:12:51 +00:00
}