[pornotube] Fix extraction (Closes #10322)

This commit is contained in:
Sergey M․ 2016-08-13 20:49:16 +07:00
parent 77afa008dd
commit 647a7bf5e8
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 38 additions and 45 deletions

View File

@ -3,10 +3,7 @@ from __future__ import unicode_literals
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import int_or_none
int_or_none,
sanitized_Request,
)
class PornotubeIE(InfoExtractor): class PornotubeIE(InfoExtractor):
@ -31,59 +28,55 @@ class PornotubeIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
# Fetch origin token token = self._download_json(
js_config = self._download_webpage( 'https://api.aebn.net/auth/v2/origins/authenticate',
'http://www.pornotube.com/assets/src/app/config.js', video_id, video_id, note='Downloading token',
note='Download JS config') data=json.dumps({'credentials': 'Clip Application'}).encode('utf-8'),
originAuthenticationSpaceKey = self._search_regex( headers={
r"constant\('originAuthenticationSpaceKey',\s*'([^']+)'", 'Content-Type': 'application/json',
js_config, 'originAuthenticationSpaceKey') 'Origin': 'http://www.pornotube.com',
})['tokenKey']
# Fetch actual token video_url = self._download_json(
token_req_data = { 'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id,
'authenticationSpaceKey': originAuthenticationSpaceKey, video_id, note='Downloading delivery information',
'credentials': 'Clip Application', headers={'Authorization': token})['mediaUrl']
}
token_req = sanitized_Request(
'https://api.aebn.net/auth/v1/token/primal',
data=json.dumps(token_req_data).encode('utf-8'))
token_req.add_header('Content-Type', 'application/json')
token_req.add_header('Origin', 'http://www.pornotube.com')
token_answer = self._download_json(
token_req, video_id, note='Requesting primal token')
token = token_answer['tokenKey']
# Get video URL FIELDS = (
delivery_req = sanitized_Request( 'title', 'description', 'startSecond', 'endSecond', 'publishDate',
'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id) 'studios{name}', 'categories{name}', 'movieId', 'primaryImageNumber'
delivery_req.add_header('Authorization', token) )
delivery_info = self._download_json(
delivery_req, video_id, note='Downloading delivery information')
video_url = delivery_info['mediaUrl']
# Get additional info (title etc.)
info_req = sanitized_Request(
'https://api.aebn.net/content/v1/clips/%s?expand='
'title,description,primaryImageNumber,startSecond,endSecond,'
'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,'
'movie.studios,stars.name,studios.name,categories.name,'
'clipActive,movieActive,publishDate,orientations' % video_id)
info_req.add_header('Authorization', token)
info = self._download_json( info = self._download_json(
info_req, video_id, note='Downloading metadata') 'https://api.aebn.net/content/v2/clips/%s?fields=%s'
% (video_id, ','.join(FIELDS)), video_id,
note='Downloading metadata',
headers={'Authorization': token})
if isinstance(info, list):
info = info[0]
title = info['title']
timestamp = int_or_none(info.get('publishDate'), scale=1000) timestamp = int_or_none(info.get('publishDate'), scale=1000)
uploader = info.get('studios', [{}])[0].get('name') uploader = info.get('studios', [{}])[0].get('name')
movie_id = info['movie']['movieId'] movie_id = info.get('movieId')
thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % ( primary_image_number = info.get('primaryImageNumber')
movie_id, movie_id, info['primaryImageNumber']) thumbnail = None
categories = [c['name'] for c in info.get('categories')] if movie_id and primary_image_number:
thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % (
movie_id, movie_id, primary_image_number)
start = int_or_none(info.get('startSecond'))
end = int_or_none(info.get('endSecond'))
duration = end - start if start and end else None
categories = [c['name'] for c in info.get('categories', []) if c.get('name')]
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': info['title'], 'title': title,
'description': info.get('description'), 'description': info.get('description'),
'duration': duration,
'timestamp': timestamp, 'timestamp': timestamp,
'uploader': uploader, 'uploader': uploader,
'thumbnail': thumbnail, 'thumbnail': thumbnail,