Merge pull request #288 from ytdl-org/master

[pull] master from ytdl-org:master

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'<device><type>web</type></device>')
         self._device_id = xpath_text(result, 'deviceId', fatal=True)
+        email, password = self._get_login_info()
+        if email and password:
+            signature = self._signature(email, password)
+            data = '<login><token>{0}</token><device><deviceId>{1}</deviceId><type>web</type></device></login>'.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,
             })

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<id>[^/]+)'
     _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'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
 
-        flashvars = self._parse_json(self._search_regex(
+        info = self._parse_html5_media_entries(url, webpage, display_id)[0]
-            r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
+        self._sort_formats(info['formats'])
-            display_id, transform_source=js_to_json)
 
-        video_id = flashvars.get('video_id')
+        video_id = self._search_regex(
-        thumbnail = flashvars.get('preview_url')
+            (r'chs_object\s*=\s*["\'](\d+)',
-        ext = determine_ext(flashvars.get('postfix'), 'mp4')
+             r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
-
+            default=display_id)
-        formats = []
+        description = self._search_regex(
-        for video_url_key in ['video_url', 'video_alt_url']:
+            r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
-            video_url = flashvars.get(video_url_key)
+            'description', fatal=False)
-            if not video_url:
+        categories = [
-                continue
+            c.strip()
-            video_text = flashvars.get('%s_text' % video_url_key)
+            for c in self._html_search_meta(
-            fmt = {
-                'url': video_url,
-                'ext': ext,
-                'format_id': video_text,
-            }
-            m = re.search(r'^(?P<height>\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(',')
+            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))
 
-        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,
+        })
-        }