youtube-dl

commit: 845333acf6280761d19f91b3e018c418d922a0de
parent 252abb1e8b881aa9d3942c436711ac33235b37cd
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 27 Jan 2019 04:14:54 +0700

[wakanim] Add extractor (closes #14374)

Diffstat:
M
youtube_dl/extractor/extractors.py
1
+
A
youtube_dl/extractor/wakanim.py
55
+++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 56 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -1373,6 +1373,7 @@ from .vuclip import VuClipIE
 from .vvvvid import VVVVIDIE
 from .vyborymos import VyboryMosIE
 from .vzaar import VzaarIE
+from .wakanim import WakanimIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,
diff --git a/youtube_dl/extractor/wakanim.py b/youtube_dl/extractor/wakanim.py
@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    merge_dicts,
+    urljoin,
+)
+
+
+class WakanimIE(InfoExtractor):
+    _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu',
+        'info_dict': {
+            'id': '2997',
+            'ext': 'mp4',
+            'title': 'Episode 02',
+            'description': 'md5:2927701ea2f7e901de8bfa8d39b2852d',
+            'series': 'The Asterisk War  (OmU.)',
+            'season_number': 1,
+            'episode': 'Episode 02',
+            'episode_number': 2,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        m3u8_url = urljoin(url, self._search_regex(
+            r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url',
+            group='url'))
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+
+        info = self._search_json_ld(webpage, video_id, default={})
+
+        title = self._search_regex(
+            (r'<h1[^>]+\bclass=["\']episode_h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'<span[^>]+\bclass=["\']episode_title["\'][^>]*>(?P<title>[^<]+)'),
+            webpage, 'title', default=None, group='title')
+
+        return merge_dicts(info, {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        })