Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 15:25:49 +00:00
Code Issues Projects Releases Wiki Activity

[tube8] Modernize

Browse Source
This commit is contained in:
Sergey M․ 2016-08-17 05:46:45 +07:00
parent 6be17c0870
commit 8804f10e6b
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 10 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
youtube_dl/extractor/tube8.py
View File

@ -1,18 +1,13 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
sanitized_Request,
str_to_int,
)
from ..aes import aes_decrypt_text
from .keezmovies import KeezMoviesIE
class Tube8IE(InfoExtractor):
class Tube8IE(KeezMoviesIE):
_VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
@ -33,47 +28,17 @@ class Tube8IE(InfoExtractor):
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage, info = self._extract_info(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, display_id)
if not info['title']:
info['title'] = self._html_search_regex(
r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
flashvars = self._parse_json(
self._search_regex(
r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'),
video_id)
formats = []
for key, video_url in flashvars.items():
if not isinstance(video_url, compat_str) or not video_url.startswith('http'):
continue
height = self._search_regex(
r'quality_(\d+)[pP]', key, 'height', default=None)
if not height:
continue
if flashvars.get('encrypted') is True:
video_url = aes_decrypt_text(
video_url, flashvars['video_title'], 32).decode('utf-8')
formats.append({
'url': video_url,
'format_id': '%sp' % height,
'height': int(height),
})
self._sort_formats(formats)
thumbnail = flashvars.get('image_url')
title = self._html_search_regex(
r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
description = self._html_search_regex(
r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
uploader = self._html_search_regex(
r'<span class="username">\s*(.+?)\s*<',
webpage, 'uploader', fatal=False)
duration = int_or_none(flashvars.get('video_duration'))
like_count = int_or_none(self._search_regex(
r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
@ -86,18 +51,13 @@ def _real_extract(self, url):
r'<span id="allCommentsCount">(\d+)</span>',
webpage, 'comment count', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
info.update({
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'age_limit': 18,
'formats': formats,
}
})
return info