]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ndr.py
79a13958b05e25a1c9e586168bb3a10742fbe01f
[youtubedl] / youtube_dl / extractor / ndr.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 int_or_none,
10 qualities,
11 parse_duration,
12 )
13
14
15 class NDRBaseIE(InfoExtractor):
16 def _real_extract(self, url):
17 mobj = re.match(self._VALID_URL, url)
18 video_id = mobj.group('id')
19
20 page = self._download_webpage(url, video_id, 'Downloading page')
21
22 title = self._og_search_title(page).strip()
23 description = self._og_search_description(page)
24 if description:
25 description = description.strip()
26
27 duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', default=None))
28 if not duration:
29 duration = parse_duration(self._html_search_regex(
30 r'(<span class="min">\d+</span>:<span class="sec">\d+</span>)',
31 page, 'duration', default=None))
32
33 formats = []
34
35 mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
36 if mp3_url:
37 formats.append({
38 'url': mp3_url.group('audio'),
39 'format_id': 'mp3',
40 })
41
42 thumbnail = None
43
44 video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page)
45 if video_url:
46 thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
47 if thumbnails:
48 quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
49 largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
50 thumbnail = 'http://www.ndr.de' + largest[0]
51
52 for format_id in 'lo', 'hi', 'hq':
53 formats.append({
54 'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
55 'format_id': format_id,
56 })
57
58 if not formats:
59 raise ExtractorError('No media links available for %s' % video_id)
60
61 return {
62 'id': video_id,
63 'title': title,
64 'description': description,
65 'thumbnail': thumbnail,
66 'duration': duration,
67 'formats': formats,
68 }
69
70
71 class NDRIE(NDRBaseIE):
72 IE_NAME = 'ndr'
73 IE_DESC = 'NDR.de - Mediathek'
74 _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
75
76 _TESTS = [
77 {
78 'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
79 'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
80 'note': 'Video file',
81 'info_dict': {
82 'id': '25866',
83 'ext': 'mp4',
84 'title': 'Kartoffeltage in der Lewitz',
85 'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8',
86 'duration': 166,
87 },
88 'skip': '404 Not found',
89 },
90 {
91 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
92 'md5': 'dadc003c55ae12a5d2f6bd436cd73f59',
93 'info_dict': {
94 'id': '988',
95 'ext': 'mp4',
96 'title': 'Party, Pötte und Parade',
97 'description': 'Hunderttausende feiern zwischen Speicherstadt und St. Pauli den 826. Hafengeburtstag. Die NDR Sondersendung zeigt die schönsten und spektakulärsten Bilder vom Auftakt.',
98 'duration': 3498,
99 },
100 },
101 {
102 'url': 'http://www.ndr.de/info/audio51535.html',
103 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
104 'note': 'Audio file',
105 'info_dict': {
106 'id': '51535',
107 'ext': 'mp3',
108 'title': 'La Valette entgeht der Hinrichtung',
109 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
110 'duration': 884,
111 }
112 }
113 ]
114
115
116 class NJoyIE(NDRBaseIE):
117 IE_NAME = 'N-JOY'
118 _VALID_URL = r'https?://www\.n-joy\.de/.+?(?P<id>\d+)\.html'
119
120 _TEST = {
121 'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
122 'md5': 'cb63be60cd6f9dd75218803146d8dc67',
123 'info_dict': {
124 'id': '2480',
125 'ext': 'mp4',
126 'title': 'Benaissa beim NDR Comedy Contest',
127 'description': 'Von seinem sehr "behaarten" Leben lässt sich Benaissa trotz aller Schwierigkeiten nicht unterkriegen.',
128 'duration': 654,
129 }
130 }