import re
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+ qualities,
+)
class NDRIE(InfoExtractor):
_VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
_TESTS = [
- # video
{
- 'url': 'http://www.ndr.de/fernsehen/sendungen/hallo_niedersachsen/media/hallonds19925.html',
- 'md5': '20eba151ff165f386643dad9c1da08f7',
+ 'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
+ 'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
+ 'note': 'Video file',
'info_dict': {
- 'id': '19925',
+ 'id': '25866',
'ext': 'mp4',
- 'title': 'Hallo Niedersachsen ',
- 'description': 'Bei Hallo Niedersachsen um 19:30 Uhr erfahren Sie alles, was am Tag in Niedersachsen los war.',
- 'duration': 1722,
- },
+ 'title': 'Kartoffeltage in der Lewitz',
+ 'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8',
+ 'duration': 166,
+ }
},
- # audio
{
- 'url': 'http://www.ndr.de/903/audio191719.html',
- 'md5': '41ed601768534dd18a9ae34d84798129',
+ 'url': 'http://www.ndr.de/info/audio51535.html',
+ 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
+ 'note': 'Audio file',
'info_dict': {
- 'id': '191719',
+ 'id': '51535',
'ext': 'mp3',
- 'title': '"Es war schockierend"',
- 'description': 'md5:ed7ff8364793545021a6355b97e95f10',
- 'duration': 112,
+ 'title': 'La Valette entgeht der Hinrichtung',
+ 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
+ 'duration': 884,
}
}
]
page = self._download_webpage(url, video_id, 'Downloading page')
- title = self._og_search_title(page)
+ title = self._og_search_title(page).strip()
description = self._og_search_description(page)
+ if description:
+ description = description.strip()
- mobj = re.search(
- r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
- page)
- duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+ duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
formats = []
- mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+ mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
if mp3_url:
formats.append({
'url': mp3_url.group('audio'),
thumbnail = None
- video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+ video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page)
if video_url:
- thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
- page, 'thumbnail', fatal=False)
- if thumbnail:
- thumbnail = 'http://www.ndr.de' + thumbnail
- for format_id in ['lo', 'hi', 'hq']:
+ thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
+ if thumbnails:
+ quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
+ largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
+ thumbnail = 'http://www.ndr.de' + largest[0]
+
+ for format_id in 'lo', 'hi', 'hq':
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
'format_id': format_id,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
- }
\ No newline at end of file
+ }