X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fwdr.py;h=ef096cbd248def4c67a1046c326ce7d1fd6a8796;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=feeb44b45ff32b4738957e44a6603cde93c8b9a4;hpb=b65c3e77e8fa893a41eb058102422f42276ebc11;p=youtube-dl
diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index feeb44b45..ef096cbd2 100644
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -1,13 +1,17 @@
+# -*- coding: utf-8 -*-
from __future__ import unicode_literals
+import itertools
import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_parse_qs,
compat_urlparse,
- determine_ext,
+)
+from ..utils import (
unified_strdate,
+ qualities,
)
@@ -24,10 +28,12 @@ class WDRIE(InfoExtractor):
'title': 'Servicezeit',
'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
'upload_date': '20140310',
+ 'is_live': False
},
'params': {
'skip_download': True,
},
+ 'skip': 'Page Not Found',
},
{
'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
@@ -37,10 +43,12 @@ class WDRIE(InfoExtractor):
'title': 'Marga Spiegel ist tot',
'description': 'md5:2309992a6716c347891c045be50992e4',
'upload_date': '20140311',
+ 'is_live': False
},
'params': {
'skip_download': True,
},
+ 'skip': 'Page Not Found',
},
{
'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
@@ -51,19 +59,43 @@ class WDRIE(InfoExtractor):
'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
'description': 'md5:2309992a6716c347891c045be50992e4',
'upload_date': '20091129',
+ 'is_live': False
},
},
{
- 'url': 'http://www.funkhauseuropa.de/av/audiogrenzenlosleckerbaklava101-audioplayer.html',
- 'md5': 'cfff440d4ee64114083ac44676df5d15',
+ 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
+ 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
'info_dict': {
- 'id': 'mdb-363068',
+ 'id': 'mdb-478135',
'ext': 'mp3',
- 'title': 'Grenzenlos lecker - Baklava',
+ 'title': 'Flavia Coelho: Amar é Amar',
'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
- 'upload_date': '20140311',
+ 'upload_date': '20140717',
+ 'is_live': False
},
+ 'skip': 'Page Not Found',
},
+ {
+ 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
+ 'playlist_mincount': 146,
+ 'info_dict': {
+ 'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
+ }
+ },
+ {
+ 'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
+ 'info_dict': {
+ 'id': 'mdb-103364',
+ 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
+ 'ext': 'flv',
+ 'upload_date': '20150101',
+ 'is_live': True
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }
]
def _real_extract(self, url):
@@ -78,15 +110,40 @@ class WDRIE(InfoExtractor):
self.url_result(page_url + href, 'WDR')
for href in re.findall(r'\s*]*>\s*\s*]+href="([^"]+)"', webpage, 'm3u8 url', default=None)
+ if m3u8_url:
+ m3u8_formats = self._extract_m3u8_formats(m3u8_url, page_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+ if m3u8_formats:
+ formats.extend(m3u8_formats)
+
+ direct_urls = re.findall(r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage)
+ if direct_urls:
+ for quality, video_url in direct_urls:
+ formats.append({
+ 'url': video_url,
+ 'preference': preference(quality),
+ 'http_headers': {
+ 'User-Agent': 'mobile',
+ },
+ })
+
+ self._sort_formats(formats)
description = self._html_search_meta('Description', webpage, 'description')
return {
'id': page_id,
- 'url': video_url,
- 'ext': ext,
+ 'formats': formats,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
+ 'is_live': is_live
}
@@ -127,9 +219,10 @@ class WDRMobileIE(InfoExtractor):
'info_dict': {
'title': '4283021',
'id': '421735',
+ 'ext': 'mp4',
'age_limit': 0,
},
- '_skip': 'Will be depublicized shortly'
+ 'skip': 'Problems with loading data.'
}
def _real_extract(self, url):
@@ -139,7 +232,9 @@ class WDRMobileIE(InfoExtractor):
'title': mobj.group('title'),
'age_limit': int(mobj.group('age_limit')),
'url': url,
- 'user_agent': 'mobile',
+ 'http_headers': {
+ 'User-Agent': 'mobile',
+ },
}
@@ -168,8 +263,7 @@ class WDRMausIE(InfoExtractor):
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
param_code = self._html_search_regex(
@@ -220,5 +314,3 @@ class WDRMausIE(InfoExtractor):
'thumbnail': thumbnail,
'upload_date': upload_date,
}
-
-# TODO test _1
\ No newline at end of file