X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fwdr.py;h=a851578e075589e6b36d828135f9919a9f1d0c38;hb=090eb8e25f08f36827772ced4c7420b59c616b8b;hp=d1c46ccb347125fd048be7b3b8a2b5860db35e32;hpb=7b6faddfc808ba798ab654312e98d01005cda9ee;p=youtube-dl
diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index d1c46ccb3..a851578e0 100644
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -1,6 +1,7 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
+import itertools
import re
from .common import InfoExtractor
@@ -9,8 +10,8 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
- determine_ext,
unified_strdate,
+ qualities,
)
@@ -27,10 +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',
@@ -40,10 +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',
@@ -54,6 +59,7 @@ class WDRIE(InfoExtractor):
'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
'description': 'md5:2309992a6716c347891c045be50992e4',
'upload_date': '20091129',
+ 'is_live': False
},
},
{
@@ -65,8 +71,31 @@ class WDRIE(InfoExtractor):
'title': 'Flavia Coelho: Amar é Amar',
'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
'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):
@@ -79,42 +108,107 @@ class WDRIE(InfoExtractor):
if mobj.group('player') is None:
entries = [
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:
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, page_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
+
+ 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
}
@@ -143,7 +237,9 @@ class WDRMobileIE(InfoExtractor):
'title': mobj.group('title'),
'age_limit': int(mobj.group('age_limit')),
'url': url,
- 'user_agent': 'mobile',
+ 'http_headers': {
+ 'User-Agent': 'mobile',
+ },
}