diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py
index 751a3a8f2..fd5ec6033 100644
--- a/youtube_dl/extractor/cbc.py
+++ b/youtube_dl/extractor/cbc.py
@@ -1,8 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
+import hashlib
import json
import re
+from xml.sax.saxutils import escape
from .common import InfoExtractor
from ..compat import (
@@ -216,6 +218,29 @@ class CBCWatchBaseIE(InfoExtractor):
'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
}
_GEO_COUNTRIES = ['CA']
+ _LOGIN_URL = 'https://api.loginradius.com/identity/v2/auth/login'
+ _TOKEN_URL = 'https://cloud-api.loginradius.com/sso/jwt/api/token'
+ _API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37'
+ _NETRC_MACHINE = 'cbcwatch'
+
+ def _signature(self, email, password):
+ data = json.dumps({
+ 'email': email,
+ 'password': password,
+ }).encode()
+ headers = {'content-type': 'application/json'}
+ query = {'apikey': self._API_KEY}
+ resp = self._download_json(self._LOGIN_URL, None, data=data, headers=headers, query=query)
+ access_token = resp['access_token']
+
+ # token
+ query = {
+ 'access_token': access_token,
+ 'apikey': self._API_KEY,
+ 'jwtapp': 'jwt',
+ }
+ resp = self._download_json(self._TOKEN_URL, None, headers=headers, query=query)
+ return resp['signature']
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
@@ -239,7 +264,8 @@ class CBCWatchBaseIE(InfoExtractor):
def _real_initialize(self):
if self._valid_device_token():
return
- device = self._downloader.cache.load('cbcwatch', 'device') or {}
+ device = self._downloader.cache.load(
+ 'cbcwatch', self._cache_device_key()) or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if self._valid_device_token():
return
@@ -248,16 +274,30 @@ class CBCWatchBaseIE(InfoExtractor):
def _valid_device_token(self):
return self._device_id and self._device_token
+ def _cache_device_key(self):
+ email, _ = self._get_login_info()
+ return '%s_device' % hashlib.sha256(email.encode()).hexdigest() if email else 'device'
+
def _register_device(self):
- self._device_id = self._device_token = None
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, 'Acquiring device token',
data=b'web')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
- self._device_token = xpath_text(result, 'deviceToken', fatal=True)
+ email, password = self._get_login_info()
+ if email and password:
+ signature = self._signature(email, password)
+ data = '{0}{1}web'.format(
+ escape(signature), escape(self._device_id)).encode()
+ url = self._API_BASE_URL + 'device/login'
+ result = self._download_xml(
+ url, None, data=data,
+ headers={'content-type': 'application/xml'})
+ self._device_token = xpath_text(result, 'token', fatal=True)
+ else:
+ self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
- 'cbcwatch', 'device', {
+ 'cbcwatch', self._cache_device_key(), {
'id': self._device_id,
'token': self._device_token,
})
diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py
index 0ee8ea712..fae425103 100644
--- a/youtube_dl/extractor/hellporno.py
+++ b/youtube_dl/extractor/hellporno.py
@@ -1,12 +1,11 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
- js_to_json,
+ int_or_none,
+ merge_dicts,
remove_end,
- determine_ext,
+ unified_timestamp,
)
@@ -14,15 +13,21 @@ class HellPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P[^/]+)'
_TESTS = [{
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
- 'md5': '1fee339c610d2049699ef2aa699439f1',
+ 'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
'info_dict': {
'id': '149116',
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
+ 'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
+ 'categories': list,
'thumbnail': r're:https?://.*\.jpg$',
+ 'duration': 240,
+ 'timestamp': 1398762720,
+ 'upload_date': '20140429',
+ 'view_count': int,
'age_limit': 18,
- }
+ },
}, {
'url': 'http://hellporno.net/v/186271/',
'only_matching': True,
@@ -36,40 +41,36 @@ class HellPornoIE(InfoExtractor):
title = remove_end(self._html_search_regex(
r'([^<]+)', webpage, 'title'), ' - Hell Porno')
- flashvars = self._parse_json(self._search_regex(
- r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
- display_id, transform_source=js_to_json)
+ info = self._parse_html5_media_entries(url, webpage, display_id)[0]
+ self._sort_formats(info['formats'])
- video_id = flashvars.get('video_id')
- thumbnail = flashvars.get('preview_url')
- ext = determine_ext(flashvars.get('postfix'), 'mp4')
+ video_id = self._search_regex(
+ (r'chs_object\s*=\s*["\'](\d+)',
+ r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
+ default=display_id)
+ description = self._search_regex(
+ r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
+ 'description', fatal=False)
+ categories = [
+ c.strip()
+ for c in self._html_search_meta(
+ 'keywords', webpage, 'categories', default='').split(',')
+ if c.strip()]
+ duration = int_or_none(self._og_search_property(
+ 'video:duration', webpage, fatal=False))
+ timestamp = unified_timestamp(self._og_search_property(
+ 'video:release_date', webpage, fatal=False))
+ view_count = int_or_none(self._search_regex(
+ r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
- formats = []
- for video_url_key in ['video_url', 'video_alt_url']:
- video_url = flashvars.get(video_url_key)
- if not video_url:
- continue
- video_text = flashvars.get('%s_text' % video_url_key)
- fmt = {
- 'url': video_url,
- 'ext': ext,
- 'format_id': video_text,
- }
- m = re.search(r'^(?P\d+)[pP]', video_text)
- if m:
- fmt['height'] = int(m.group('height'))
- formats.append(fmt)
- self._sort_formats(formats)
-
- categories = self._html_search_meta(
- 'keywords', webpage, 'categories', default='').split(',')
-
- return {
+ return merge_dicts(info, {
'id': video_id,
'display_id': display_id,
'title': title,
- 'thumbnail': thumbnail,
+ 'description': description,
'categories': categories,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'view_count': view_count,
'age_limit': 18,
- 'formats': formats,
- }
+ })