X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fwdr.py;h=ef096cbd248def4c67a1046c326ce7d1fd6a8796;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=1238c15aa18c8eb4499c181dc108cdfd01c94d0b;hpb=b461641fb9e11ca4e5fcb2262d281e1efe12a560;p=youtube-dl
diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index 1238c15aa..ef096cbd2 100644
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -1,12 +1,17 @@
+# -*- coding: utf-8 -*-
from __future__ import unicode_literals
+import itertools
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_parse_qs,
+ compat_urlparse,
+)
from ..utils import (
unified_strdate,
- compat_urlparse,
- determine_ext,
+ qualities,
)
@@ -23,10 +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',
@@ -34,11 +41,14 @@ class WDRIE(InfoExtractor):
'id': 'mdb-363194',
'ext': 'flv',
'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',
@@ -47,19 +57,45 @@ class WDRIE(InfoExtractor):
'id': 'mdb-194332',
'ext': 'mp3',
'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',
- 'upload_date': '20140311',
+ '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):
@@ -74,15 +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,
- }
\ No newline at end of file
+ 'is_live': is_live
+ }
+
+
+class WDRMobileIE(InfoExtractor):
+ _VALID_URL = r'''(?x)
+ https?://mobile-ondemand\.wdr\.de/
+ .*?/fsk(?P[0-9]+)
+ /[0-9]+/[0-9]+/
+ (?P[0-9]+)_(?P[0-9]+)'''
+ IE_NAME = 'wdr:mobile'
+ _TEST = {
+ 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
+ 'info_dict': {
+ 'title': '4283021',
+ 'id': '421735',
+ 'ext': 'mp4',
+ 'age_limit': 0,
+ },
+ 'skip': 'Problems with loading data.'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ return {
+ 'id': mobj.group('id'),
+ 'title': mobj.group('title'),
+ 'age_limit': int(mobj.group('age_limit')),
+ 'url': url,
+ 'http_headers': {
+ 'User-Agent': 'mobile',
+ },
+ }
+
+
+class WDRMausIE(InfoExtractor):
+ _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P[^/?#]+)(?:/index\.php5|(?Sendedatum:\s*([0-9\.]+)
',
+ webpage, 'air date')
+ title_str = self._html_search_regex(
+ r'(.*?)
', webpage, 'title')
+ title = '%s - %s' % (title_date, title_str)
+ upload_date = unified_strdate(
+ self._html_search_meta('dc.date', webpage))
+
+ fields = compat_parse_qs(param_code)
+ video_url = fields['firstVideo'][0]
+ thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
+
+ formats = [{
+ 'format_id': 'rtmp',
+ 'url': video_url,
+ }]
+
+ jscode = self._download_webpage(
+ 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
+ video_id, fatal=False,
+ note='Downloading URL translation table',
+ errnote='Could not download URL translation table')
+ if jscode:
+ for m in re.finditer(
+ r"stream:\s*'dslSrc=(?P[^']+)',\s*download:\s*'(?P[^']+)'\s*\}",
+ jscode):
+ if video_url.startswith(m.group('stream')):
+ http_url = video_url.replace(
+ m.group('stream'), m.group('dl'))
+ formats.append({
+ 'format_id': 'http',
+ 'url': http_url,
+ })
+ break
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ }