# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
- qualities,
)
-class NDRIE(InfoExtractor):
+preferences = {'xl': 4, 'l': 3, 'm': 2, 's': 1, 'xs': 0,}
+
+
+class NDRBaseIE(InfoExtractor):
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ json_data = self._download_json('http://www.ndr.de/%s-ppjson.json' % video_id, video_id, 'Downloading page')
+
+ formats = []
+ objetType = json_data.get('config').get('objectType')
+ if objetType == 'video':
+ for key, f in json_data.get('playlist').items():
+ if key != 'config':
+ src = f['src']
+ if '.f4m' in src:
+ formats.extend(self._extract_f4m_formats(src, video_id))
+ elif '.m3u8' in src:
+ formats.extend(self._extract_m3u8_formats(src, video_id))
+ else:
+ quality = f.get('quality')
+ formats.append({
+ 'url': src,
+ 'format_id': quality,
+ 'preference': preferences.get(quality),
+ })
+ elif objetType == 'audio':
+ for key, f in json_data.get('playlist').items():
+ if key != 'config':
+ formats.append({
+ 'url': f['src'],
+ 'format_id': 'mp3',
+
+ })
+ else:
+ raise ExtractorError('No media links available for %s' % video_id)
+
+ self._sort_formats(formats)
+
+ config = json_data.get('playlist').get('config')
+
+ title = config['title']
+ duration = int_or_none(config.get('duration'))
+ thumbnails = [{
+ 'id': thumbnail.get('quality'),
+ 'url': thumbnail.get('src'),
+ 'preference': preferences.get(thumbnail.get('quality'))
+ } for thumbnail in config.get('poster').values()]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnails': thumbnails,
+ 'duration': duration,
+ 'formats': formats,
+ }
+
+
+class NDRIE(NDRBaseIE):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Mediathek'
- _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+ _VALID_URL = r'https?://www\.ndr\.de/.+?,(?P<id>\w+)\.html'
_TESTS = [
{
- 'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
- 'md5': 'e7a6079ca39d3568f4996cb858dd6708',
+ 'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
+ 'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
'note': 'Video file',
'info_dict': {
- 'id': '7959',
+ 'id': 'nordmagazin25866',
+ 'ext': 'mp4',
+ 'title': 'Kartoffeltage in der Lewitz',
+ 'duration': 166,
+ },
+ 'skip': '404 Not found',
+ },
+ {
+ 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
+ 'md5': 'dadc003c55ae12a5d2f6bd436cd73f59',
+ 'info_dict': {
+ 'id': 'hafengeburtstag988',
'ext': 'mp4',
- 'title': 'Markt - die ganze Sendung',
- 'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
- 'duration': 2655,
+ 'title': 'Party, Pötte und Parade',
+ 'duration': 3498,
},
},
{
- 'url': 'http://www.ndr.de/info/audio51535.html',
+ 'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
'note': 'Audio file',
'info_dict': {
- 'id': '51535',
+ 'id': 'audio51535',
'ext': 'mp3',
'title': 'La Valette entgeht der Hinrichtung',
- 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
'duration': 884,
}
}
]
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- page = self._download_webpage(url, video_id, 'Downloading page')
- title = self._og_search_title(page).strip()
- description = self._og_search_description(page)
- if description:
- description = description.strip()
+class NJoyIE(NDRBaseIE):
+ IE_NAME = 'N-JOY'
+ _VALID_URL = r'https?://www\.n-joy\.de/.+?,(?P<id>\w+)\.html'
- 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)
- if mp3_url:
- formats.append({
- 'url': mp3_url.group('audio'),
- 'format_id': 'mp3',
- })
-
- thumbnail = None
-
- video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
- if video_url:
- 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,
- })
-
- if not formats:
- raise ExtractorError('No media links available for %s' % video_id)
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'formats': formats,
- }
\ No newline at end of file
+ _TEST = {
+ 'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
+ 'md5': 'cb63be60cd6f9dd75218803146d8dc67',
+ 'info_dict': {
+ 'id': '2480',
+ 'ext': 'mp4',
+ 'title': 'Benaissa beim NDR Comedy Contest',
+ 'duration': 654,
+ }
+ }
projects / youtube-dl.git / blobdiff