youtube-dl/youtube_dl/extractor/tube8.py

84 lines
3.0 KiB
Python
Raw Normal View History

2014-04-12 14:56:32 -06:00
from __future__ import unicode_literals
import json
2013-10-26 15:27:30 -06:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
2014-04-12 14:56:32 -06:00
int_or_none,
str_to_int,
2013-10-26 15:27:30 -06:00
)
2014-04-12 14:56:32 -06:00
from ..aes import aes_decrypt_text
2013-10-26 15:27:30 -06:00
class Tube8IE(InfoExtractor):
2014-04-12 14:56:32 -06:00
_VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
2013-10-26 15:27:30 -06:00
_TEST = {
2014-04-12 14:56:32 -06:00
'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
'file': '229795.mp4',
'md5': 'e9e0b0c86734e5e3766e653509475db0',
'info_dict': {
'description': 'hot teen Kasia grinding',
'uploader': 'unknown',
'title': 'Kasia music video',
'age_limit': 18,
2013-10-26 15:27:30 -06:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-04-12 14:56:32 -06:00
video_id = mobj.group('id')
2013-10-26 15:27:30 -06:00
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
2014-04-12 14:56:32 -06:00
flashvars = json.loads(self._html_search_regex(
r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
video_url = flashvars['video_url']
if flashvars.get('encrypted') is True:
video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8')
path = compat_urllib_parse_urlparse(video_url).path
2014-04-12 14:56:32 -06:00
format_id = '-'.join(path.split('/')[4].split('_')[:2])
thumbnail = flashvars.get('image_url')
title = self._html_search_regex(
r'videotitle\s*=\s*"([^"]+)', webpage, 'title')
description = self._html_search_regex(
r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
uploader = self._html_search_regex(
r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>',
webpage, 'uploader', fatal=False)
like_count = int_or_none(self._html_search_regex(
r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False))
dislike_count = int_or_none(self._html_search_regex(
r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False))
view_count = self._html_search_regex(
r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False)
if view_count:
view_count = str_to_int(view_count)
comment_count = self._html_search_regex(
r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)
if comment_count:
comment_count = str_to_int(comment_count)
2013-10-26 15:27:30 -06:00
return {
'id': video_id,
'url': video_url,
2014-04-12 14:56:32 -06:00
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'format_id': format_id,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'age_limit': 18,
2013-10-26 15:27:30 -06:00
}