youtube-dl

commit abf2c79f954c065d6bf92a2129f04eb07942d022
parent 48094901086534533ca89283067f2ab732857654
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Mon,  5 Sep 2016 13:39:51 +0800

Merge branch 'mcepl-tvnoe'

Diffstat:
M
ChangeLog
 | 
6
++++++
M
youtube_dl/extractor/extractors.py
 | 
1
+
A
youtube_dl/extractor/tvnoe.py
 | 
49
+++++++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 56 insertions(+), 0 deletions(-)
diff --git a/ChangeLog b/ChangeLog
@@ -1,3 +1,9 @@
+version <unreleased>
+
+Extractors
++ [tvnoe] New extractor (#10524)
+
+
 version 2016.09.04.1
 
 Core
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -916,6 +916,7 @@ from .tvc import (
 )
 from .tvigle import TvigleIE
 from .tvland import TVLandIE
+from .tvnoe import TVNoeIE
 from .tvp import (
     TVPEmbedIE,
     TVPIE,
diff --git a/youtube_dl/extractor/tvnoe.py b/youtube_dl/extractor/tvnoe.py
@@ -0,0 +1,49 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    js_to_json,
+)
+
+
+class TVNoeIE(JWPlatformBaseIE):
+    _VALID_URL = r'https?://(www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.tvnoe.cz/video/10362',
+        'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
+        'info_dict': {
+            'id': '10362',
+            'ext': 'mp4',
+            'series': 'Noční univerzita',
+            'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
+            'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        iframe_url = self._search_regex(
+            r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
+
+        ifs_page = self._download_webpage(iframe_url, video_id)
+        jwplayer_data = self._parse_json(
+            self._find_jwplayer_data(ifs_page),
+            video_id, transform_source=js_to_json)
+        info_dict = self._parse_jwplayer_data(
+            jwplayer_data, video_id, require_title=False, base_url=iframe_url)
+
+        info_dict.update({
+            'id': video_id,
+            'title': clean_html(get_element_by_class(
+                'field-name-field-podnazev', webpage)),
+            'description': clean_html(get_element_by_class(
+                'field-name-body', webpage)),
+            'series': clean_html(get_element_by_class('title', webpage))
+        })
+
+        return info_dict