youtube-dl

commit 001a5fd3d75b311102264cf3920c6aa5b2322e51
parent 1e35999c1e4637174e2532c457431315b5e186d9
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Sun, 11 Sep 2016 03:02:00 +0800

[iwara] Fix extraction after relaunch

Closes #10462, closes #3215

Diffstat:
M
ChangeLog
 | 
1
+
M
youtube_dl/extractor/extractors.py
 | 
2
+-
A
youtube_dl/extractor/iwara.py
 | 
77
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
D
youtube_dl/extractor/trollvids.py
 | 
36
------------------------------------

4 files changed, 79 insertions(+), 37 deletions(-)
diff --git a/ChangeLog b/ChangeLog
@@ -1,6 +1,7 @@
 version <unreleased>
 
 Extractors
+* [iwara] Fix extraction after relaunch (#10462, #3215)
 * [newgrounds] Fix uploader extraction (#10584)
 
 
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -395,6 +395,7 @@ from .ivi import (
     IviCompilationIE
 )
 from .ivideon import IvideonIE
+from .iwara import IwaraIE
 from .izlesene import IzleseneIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
@@ -899,7 +900,6 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
-from .trollvids import TrollvidsIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
diff --git a/youtube_dl/extractor/iwara.py b/youtube_dl/extractor/iwara.py
@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import remove_end
+
+
+class IwaraIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
+    _TESTS = [{
+        'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
+        'md5': '1d53866b2c514b23ed69e4352fdc9839',
+        'info_dict': {
+            'id': 'amVwUl1EHpAD9RD',
+            'ext': 'mp4',
+            'title': '【MMD R-18】ガールフレンド carry_me_off',
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
+        'md5': '7e5f1f359cd51a027ba4a7b7710a50f0',
+        'info_dict': {
+            'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
+            'ext': 'mp4',
+            'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4',
+            'age_limit': 18,
+        },
+        'add_ie': ['GoogleDrive'],
+    }, {
+        'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
+        'md5': '1d85f1e5217d2791626cff5ec83bb189',
+        'info_dict': {
+            'id': '6liAP9s2Ojc',
+            'ext': 'mp4',
+            'age_limit': 0,
+            'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
+            'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
+            'upload_date': '20160910',
+            'uploader': 'aMMDsork',
+            'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A',
+        },
+        'add_ie': ['Youtube'],
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname
+        # ecchi is 'sexy' in Japanese
+        age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
+
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+
+        if not entries:
+            iframe_url = self._html_search_regex(
+                r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
+                webpage, 'iframe URL', group='url')
+            return {
+                '_type': 'url_transparent',
+                'url': iframe_url,
+                'age_limit': age_limit,
+            }
+
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
+
+        info_dict = entries[0]
+        info_dict.update({
+            'id': video_id,
+            'title': title,
+            'age_limit': age_limit,
+        })
+
+        return info_dict
diff --git a/youtube_dl/extractor/trollvids.py b/youtube_dl/extractor/trollvids.py
@@ -1,36 +0,0 @@
-# encoding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .nuevo import NuevoBaseIE
-
-
-class TrollvidsIE(NuevoBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?trollvids\.com/video/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
-    IE_NAME = 'trollvids'
-    _TEST = {
-        'url': 'http://trollvids.com/video/2349002/%E3%80%90MMD-R-18%E3%80%91%E3%82%AC%E3%83%BC%E3%83%AB%E3%83%95%E3%83%AC%E3%83%B3%E3%83%89-carrymeoff',
-        'md5': '1d53866b2c514b23ed69e4352fdc9839',
-        'info_dict': {
-            'id': '2349002',
-            'ext': 'mp4',
-            'title': '【MMD R-18】ガールフレンド carry_me_off',
-            'age_limit': 18,
-            'duration': 216.78,
-        },
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-
-        info = self._extract_nuevo(
-            'http://trollvids.com/nuevo/player/config.php?v=%s' % video_id,
-            video_id)
-        info.update({
-            'display_id': display_id,
-            'age_limit': 18
-        })
-        return info