ytdl/youtube_dl/extractor/drtuber.py

71 lines
2.5 KiB
Python
Raw Normal View History

2014-09-01 20:12:51 +02:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-09-02 15:36:26 +02:00
from ..utils import str_to_int
2014-09-01 20:12:51 +02:00
class DrTuberIE(InfoExtractor):
2014-09-02 15:39:16 +02:00
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
2014-09-01 20:12:51 +02:00
_TEST = {
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
'id': '1740434',
2014-09-02 16:40:03 +02:00
'display_id': 'hot-perky-blonde-naked-golf',
2014-09-01 20:12:51 +02:00
'ext': 'mp4',
'title': 'Hot Perky Blonde Naked Golf',
2014-09-02 15:36:26 +02:00
'like_count': int,
'dislike_count': int,
'comment_count': int,
2014-09-01 20:12:51 +02:00
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
2014-09-01 20:12:51 +02:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-02 15:39:16 +02:00
display_id = mobj.group('display_id')
2014-09-01 20:12:51 +02:00
2014-09-02 15:39:16 +02:00
webpage = self._download_webpage(url, display_id)
2014-09-01 20:12:51 +02:00
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
2014-09-02 15:36:26 +02:00
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))
cats_str = self._html_search_regex(
2014-09-01 20:12:51 +02:00
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
categories = None if cats_str is None else cats_str.split(' ')
2014-09-01 20:12:51 +02:00
return {
'id': video_id,
2014-09-02 15:39:16 +02:00
'display_id': display_id,
2014-09-01 20:12:51 +02:00
'url': video_url,
'title': title,
'thumbnail': thumbnail,
2014-09-02 15:36:26 +02:00
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
2014-09-01 20:12:51 +02:00
'categories': categories,
'age_limit': self._rta_search(webpage),
2014-09-01 20:12:51 +02:00
}