From 10cab648ca999b8a82b5f95579d90131a823dbe5 Mon Sep 17 00:00:00 2001
From: BrutuZ <BrutuZ@users.noreply.github.com>
Date: Thu, 12 Mar 2020 01:15:29 -0300
Subject: [PATCH] [hanime] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/hanime.py     | 71 ++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)
 create mode 100644 youtube_dl/extractor/hanime.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 64d1fa251..3fd5ae986 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -420,6 +420,7 @@ from .goshgay import GoshgayIE
 from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hbo import HBOIE
+from .hanime import HanimeIE
 from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
 from .hellporno import HellPornoIE
diff --git a/youtube_dl/extractor/hanime.py b/youtube_dl/extractor/hanime.py
new file mode 100644
index 000000000..f06066e21
--- /dev/null
+++ b/youtube_dl/extractor/hanime.py
@@ -0,0 +1,71 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import clean_html
+
+
+class HanimeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hanime\.tv/videos/hentai/(?P<id>.+)(?:\?playlist_id=\w+)?'
+    _TEST = {
+        'url': 'https://hanime.tv/videos/hentai/kuroinu-1',
+        'info_dict': {
+            'id': '33964',
+            'display_id': 'kuroinu-1',
+            'title': 'Kuroinu 1',
+            'description': 'md5:37d5bb20d4a0834bd147bc1bac588a0b',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'release_date': '20120127',
+            'upload_date': '20140509',
+            'creator': 'Magin Label',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'tags': list,
+            'censored': True,
+            'ext': 'mp4',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_slug = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_slug)
+        page_json = self._html_search_regex(r'window.__NUXT__=(.+?);<\/script>', webpage, 'Inline JSON')
+        page_json = self._parse_json(page_json, video_slug).get('state').get('data').get('video').get('hentai_video')
+        api_json = self._download_json(
+            'https://members.hanime.tv/api/v3/videos_manifests/%s' % video_slug,
+            video_slug,
+            'API Call', headers={'X-Directive': 'api'}
+        )
+        api_json = api_json.get('videos_manifest').get('servers')[0].get('streams')
+
+        title = page_json.get('name') or api_json.get[0].get('video_stream_group_id')
+        tags = [t.get('text') for t in page_json.get('hentai_tags')]
+
+        video_id = str(api_json[0].get('id'))
+        playlist_url = api_json[0].get('url') or api_json[1].get('url')
+        formats = self._extract_m3u8_formats(playlist_url, video_slug, 'mp4')
+        return {
+            'id': video_id,
+            'display_id': video_slug,
+            'title': title,
+            'description': clean_html(page_json.get('description')).strip(),
+            'thumbnails': [
+                {'id': 'Cover', 'url': page_json.get('cover_url')},
+                {'id': 'Poster', 'url': page_json.get('poster_url')}
+            ],
+            'release_date': page_json.get('released_at').replace('-', '')[:8],
+            'upload_date': page_json.get('created_at').replace('-', '')[:8],
+            'creator': page_json.get('brand'),
+            'view_count': page_json.get('views'),
+            'like_count': page_json.get('likes'),
+            'dislike_count': page_json.get('dislikes'),
+            'tags': tags,
+            'censored': page_json.get('is_censored'),
+            'formats': formats,
+        }