depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 01:08:10 +00:00
Code Issues Releases Wiki Activity

[tube8] Fix extraction and modernize

Browse source
This commit is contained in:
Sergey M․ 2014-04-13 03:56:32 +07:00
parent 66398056f1
commit 2fb3deeca1
1 changed files with 55 additions and 35 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

90
youtube_dl/extractor/tube8.py
View file

@ -1,63 +1,83 @@
import os from __future__ import unicode_literals
import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
compat_urllib_request, compat_urllib_request,
int_or_none,
str_to_int,
) )
from ..aes import ( from ..aes import aes_decrypt_text
aes_decrypt_text
)
class Tube8IE(InfoExtractor): class Tube8IE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/.+?/(?P<videoid>\d+)/?)$' _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
_TEST = { _TEST = {
u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/', 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
u'file': u'229795.mp4', 'file': '229795.mp4',
u'md5': u'e9e0b0c86734e5e3766e653509475db0', 'md5': 'e9e0b0c86734e5e3766e653509475db0',
u'info_dict': { 'info_dict': {
u"description": u"hot teen Kasia grinding", 'description': 'hot teen Kasia grinding',
u"uploader": u"unknown", 'uploader': 'unknown',
u"title": u"Kasia music video", 'title': 'Kasia music video',
u"age_limit": 18, 'age_limit': 18,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid') video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url) req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1') req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id) webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'videotitle ="([^"]+)', webpage, u'title') flashvars = json.loads(self._html_search_regex(
video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False) r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
if thumbnail:
thumbnail = thumbnail.replace('\\/', '/')
video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url') video_url = flashvars['video_url']
if webpage.find('"encrypted":true')!=-1: if flashvars.get('encrypted') is True:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password') video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
path = compat_urllib_parse_urlparse(video_url).path path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:] format_id = '-'.join(path.split('/')[4].split('_')[:2])
format = path.split('/')[4].split('_')[:2]
format = "-".join(format) 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)
return { return {
'id': video_id, 'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'description': video_description,
'url': video_url, 'url': video_url,
'ext': extension, 'title': title,
'format': format, 'description': description,
'format_id': format, '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, 'age_limit': 18,
} }