[pornotube] Adapt to new interface

This commit is contained in:
Philipp Hagemeister 2014-12-12 19:44:25 +01:00
parent c3f3b29b92
commit 4237ba10dc

View file

@ -1,56 +1,94 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
from ..utils import ( from ..utils import (
compat_urllib_parse, int_or_none,
unified_strdate,
) )
class PornotubeIE(InfoExtractor): class PornotubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)'
_TEST = { _TEST = {
'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing', 'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science',
'md5': '374dd6dcedd24234453b295209aa69b6', 'md5': '60fc5a4f0d93a97968fc7999d98260c9',
'info_dict': { 'info_dict': {
'id': '1689755', 'id': '4964',
'ext': 'flv', 'ext': 'mp4',
'upload_date': '20090708', 'upload_date': '20141203',
'title': 'Marilyn-Monroe-Bathing', 'title': 'Weird Hot and Wet Science',
'age_limit': 18 'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0',
'categories': ['Adult Humor', 'Blondes'],
'uploader': 'Alpha Blue Archives',
'thumbnail': 're:^https?://.*\\.jpg$',
'timestamp': 1417582800,
'age_limit': 18,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('videoid') # Fetch origin token
video_title = mobj.group('title') js_config = self._download_webpage(
'http://www.pornotube.com/assets/src/app/config.js', video_id,
note='Download JS config')
originAuthenticationSpaceKey = self._search_regex(
r"constant\('originAuthenticationSpaceKey',\s*'([^']+)'",
js_config, 'originAuthenticationSpaceKey')
# Get webpage content # Fetch actual token
webpage = self._download_webpage(url, video_id) token_req_data = {
'authenticationSpaceKey': originAuthenticationSpaceKey,
'credentials': 'Clip Application',
}
token_req = compat_urllib_request.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 the video URL # Get video URL
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' delivery_req = compat_urllib_request.Request(
video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') 'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id)
video_url = compat_urllib_parse.unquote(video_url) 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 the uploaded date # Get additional info (title etc.)
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' info_req = compat_urllib_request.Request(
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) 'https://api.aebn.net/content/v1/clips/%s?expand='
if upload_date: 'title,description,primaryImageNumber,startSecond,endSecond,'
upload_date = unified_strdate(upload_date) 'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,'
age_limit = self._rta_search(webpage) '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_req, video_id, note='Downloading metadata')
timestamp = int_or_none(info.get('publishDate'), scale=1000)
uploader = info.get('studios', [{}])[0].get('name')
movie_id = info['movie']['movieId']
thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % (
movie_id, movie_id, info['primaryImageNumber'])
categories = [c['name'] for c in info.get('categories')]
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'upload_date': upload_date, 'title': info['title'],
'title': video_title, 'description': info.get('description'),
'ext': 'flv', 'timestamp': timestamp,
'format': 'flv', 'uploader': uploader,
'age_limit': age_limit, 'thumbnail': thumbnail,
'categories': categories,
'age_limit': 18,
} }