youtube-dl

commit 3bf8c316a663741ab806f48cf9121209aba88b72
parent e37c92ec6d137cd2d09c5f13e9a261c4fae552dd
Author: Sergey M․ <dstftw@gmail.com>
Date:   Mon, 20 Jul 2015 00:01:22 +0600

[sportschau] Reimplement in terms of ard extractor

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
7
+++++--
M
youtube_dl/extractor/ard.py
 | 
39
+++++++++++++++++++++++++++++++++++++++
D
youtube_dl/extractor/sportschau.py
 | 
47
-----------------------------------------------

3 files changed, 44 insertions(+), 49 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -22,7 +22,11 @@ from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE, ARDMediathekIE
+from .ard import (
+    ARDIE,
+    ARDMediathekIE,
+    SportschauIE,
+)
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -553,7 +557,6 @@ from .sportbox import (
     SportBoxEmbedIE,
 )
 from .sportdeutschland import SportDeutschlandIE
-from .sportschau import SportschauIE
 from .srf import SrfIE
 from .srmediathek import SRMediathekIE
 from .ssa import SSAIE
diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py
@@ -8,6 +8,7 @@ from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
+    get_element_by_attribute,
     qualities,
     int_or_none,
     parse_duration,
@@ -246,3 +247,41 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
+
+
+class SportschauIE(ARDMediathekIE):
+    IE_NAME = 'Sportschau'
+    _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html'
+    _TEST = {
+        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
+        'info_dict': {
+            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
+            'ext': 'mp4',
+            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        base_url = mobj.group('baseurl')
+
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_attribute('class', 'headline', webpage)
+        description = self._html_search_meta('description', webpage, 'description')
+
+        info = self._extract_media_info(
+            base_url + '-mc_defaultQuality-h.json', webpage, video_id)
+
+        info.update({
+            'title': title,
+            'description': description,
+        })
+
+        return info
diff --git a/youtube_dl/extractor/sportschau.py b/youtube_dl/extractor/sportschau.py
@@ -1,47 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import get_element_by_attribute
-
-
-class SportschauIE(InfoExtractor):
-    IE_NAME = 'Sportschau'
-    _VALID_URL = r'https?://(?:www\.)?sportschau\.de/\w+(?:/\w+)?/video(?P<id>\w+)\.html'
-    _TEST = {
-        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
-        'info_dict': {
-            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
-            'ext': 'mp4',
-            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        ext = '-mc_defaultQuality-h.json'
-        json_url = url[:-5] + ext
-
-        json = self._download_json(json_url, video_id)
-        thumb_url = json['_previewImage']
-
-        m3u8_url = json['_mediaArray'][1]['_mediaStreamArray'][0]['_stream'][0]
-        m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, ext="mp4")
-
-        webpage = self._download_webpage(url, video_id)
-        title = get_element_by_attribute('class', 'headline', webpage)
-        desc = self._html_search_meta('description', webpage)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': m3u8_formats,
-            'description': desc,
-            'thumbnail': thumb_url,
-        }