yt-dlp/youtube_dl/extractor/drtuber.py

102 lines
3.5 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
from ..utils import (
NO_DEFAULT,
str_to_int,
)
2014-09-01 20:12:51 +02:00
class DrTuberIE(InfoExtractor):
2016-11-06 15:28:51 +01:00
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
2014-09-01 20:12:51 +02:00
'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',
2015-02-14 13:50:13 +01:00
'title': 'hot perky blonde naked golf',
2014-09-02 15:36:26 +02:00
'like_count': int,
'comment_count': int,
2014-09-18 15:56:54 +02:00
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
'thumbnail': r're:https?://.*\.jpg$',
'age_limit': 18,
2014-09-01 20:12:51 +02:00
}
2016-11-06 15:28:51 +01:00
}, {
'url': 'http://www.drtuber.com/embed/489939',
'only_matching': True,
}]
2014-09-01 20:12:51 +02:00
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
webpage)
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')
2016-11-06 15:28:51 +01:00
display_id = mobj.group('display_id') or video_id
2014-09-01 20:12:51 +02:00
2016-11-06 15:28:51 +01:00
webpage = self._download_webpage(
'http://www.drtuber.com/video/%s' % video_id, display_id)
2014-09-01 20:12:51 +02:00
video_data = self._download_json(
'http://www.drtuber.com/player_config_json/', video_id, query={
'vid': video_id,
'embed': 0,
'aid': 0,
'domain_id': 0,
})
formats = []
for format_id, video_url in video_data['files'].items():
if video_url:
formats.append({
'format_id': format_id,
'quality': 2 if format_id == 'hq' else 1,
'url': video_url
})
self._sort_formats(formats)
2014-09-01 20:12:51 +02:00
title = self._html_search_regex(
2016-11-06 15:29:15 +01:00
(r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
2016-08-11 18:47:52 +02:00
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
2015-02-14 13:50:13 +01:00
webpage, 'title')
2014-09-01 20:12:51 +02:00
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
def extract_count(id_, name, default=NO_DEFAULT):
2015-07-01 17:47:56 +02:00
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 17:47:56 +02:00
like_count = extract_count('rate_likes', 'like')
dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
2015-07-01 17:47:56 +02:00
comment_count = extract_count('comments_count', 'comment')
2014-09-02 15:36:26 +02:00
2014-09-18 15:56:54 +02:00
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 20:12:51 +02:00
return {
'id': video_id,
2014-09-02 15:39:16 +02:00
'display_id': display_id,
'formats': formats,
2014-09-01 20:12:51 +02:00
'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
}