mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-27 07:06:52 +01:00
add96eb9f8
Authored by: seproDev Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com> Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
105 lines
3.7 KiB
Python
105 lines
3.7 KiB
Python
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
NO_DEFAULT,
|
|
int_or_none,
|
|
parse_duration,
|
|
str_to_int,
|
|
)
|
|
|
|
|
|
class DrTuberIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
|
|
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)']
|
|
_TESTS = [{
|
|
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
|
|
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
|
|
'info_dict': {
|
|
'id': '1740434',
|
|
'display_id': 'hot-perky-blonde-naked-golf',
|
|
'ext': 'mp4',
|
|
'title': 'hot perky blonde naked golf',
|
|
'like_count': int,
|
|
'comment_count': int,
|
|
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
|
|
'thumbnail': r're:https?://.*\.jpg$',
|
|
'age_limit': 18,
|
|
},
|
|
}, {
|
|
'url': 'http://www.drtuber.com/embed/489939',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
mobj = self._match_valid_url(url)
|
|
video_id = mobj.group('id')
|
|
display_id = mobj.group('display_id') or video_id
|
|
|
|
webpage = self._download_webpage(
|
|
f'http://www.drtuber.com/video/{video_id}', display_id)
|
|
|
|
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,
|
|
})
|
|
|
|
duration = int_or_none(video_data.get('duration')) or parse_duration(
|
|
video_data.get('duration_format'))
|
|
|
|
title = self._html_search_regex(
|
|
(r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
|
|
r'<title>([^<]+)\s*@\s+DrTuber',
|
|
r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
|
|
r'<p[^>]+class="title_substrate">([^<]+)</p>',
|
|
r'<title>([^<]+) - \d+'),
|
|
webpage, 'title')
|
|
|
|
thumbnail = self._html_search_regex(
|
|
r'poster="([^"]+)"',
|
|
webpage, 'thumbnail', fatal=False)
|
|
|
|
def extract_count(id_, name, default=NO_DEFAULT):
|
|
return str_to_int(self._html_search_regex(
|
|
rf'<span[^>]+(?:class|id)="{id_}"[^>]*>([\d,\.]+)</span>',
|
|
webpage, f'{name} count', default=default, fatal=False))
|
|
|
|
like_count = extract_count('rate_likes', 'like')
|
|
dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
|
|
comment_count = extract_count('comments_count', 'comment')
|
|
|
|
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)
|
|
|
|
return {
|
|
'id': video_id,
|
|
'display_id': display_id,
|
|
'formats': formats,
|
|
'title': title,
|
|
'thumbnail': thumbnail,
|
|
'like_count': like_count,
|
|
'dislike_count': dislike_count,
|
|
'comment_count': comment_count,
|
|
'categories': categories,
|
|
'age_limit': self._rta_search(webpage),
|
|
'duration': duration,
|
|
}
|