]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/swrmediathek.py
[generic] Use default opener for HEAD request (Fixes #3528)
[youtube-dl.git] / youtube_dl / extractor / swrmediathek.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import parse_duration
8
9
10 class SWRMediathekIE(InfoExtractor):
11     _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/(?:content/)?player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
12
13     _TESTS = [{
14         'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6',
15         'md5': '8c5f6f0172753368547ca8413a7768ac',
16         'info_dict': {
17             'id': '849790d0-dab8-11e3-a953-0026b975f2e6',
18             'ext': 'mp4',
19             'title': 'SWR odysso',
20             'description': 'md5:2012e31baad36162e97ce9eb3f157b8a',
21             'thumbnail': 're:^http:.*\.jpg$',
22             'duration': 2602,
23             'upload_date': '20140515',
24             'uploader': 'SWR Fernsehen',
25             'uploader_id': '990030',
26         },
27     }, {
28         'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
29         'md5': 'b10ab854f912eecc5a6b55cd6fc1f545',
30         'info_dict': {
31             'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
32             'ext': 'mp4',
33             'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen',
34             'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2',
35             'thumbnail': 're:http://.*\.jpg',
36             'duration': 5305,
37             'upload_date': '20140516',
38             'uploader': 'SWR Fernsehen',
39             'uploader_id': '990030',
40         },
41     }, {
42         'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6',
43         'md5': '4382e4ef2c9d7ce6852535fa867a0dd3',
44         'info_dict': {
45             'id': 'bba23e10-cb93-11e3-bf7f-0026b975f2e6',
46             'ext': 'mp3',
47             'title': 'Saša Stanišic: Vor dem Fest',
48             'description': 'md5:5b792387dc3fbb171eb709060654e8c9',
49             'thumbnail': 're:http://.*\.jpg',
50             'duration': 3366,
51             'upload_date': '20140520',
52             'uploader': 'SWR 2',
53             'uploader_id': '284670',
54         }
55     }, {
56         'url': 'http://swrmediathek.de/content/player.htm?show=52dc7e00-15c5-11e4-84bc-0026b975f2e6',
57         'md5': '881531487d0633080a8cc88d31ef896f',
58         'info_dict': {
59             'id': '52dc7e00-15c5-11e4-84bc-0026b975f2e6',
60             'ext': 'mp4',
61             'title': 'Familienspaß am Bodensee',
62             'description': 'md5:0b591225a32cfde7be1629ed49fe4315',
63             'thumbnail': 're:http://.*\.jpg',
64             'duration': 1784,
65             'upload_date': '20140727',
66             'uploader': 'SWR Fernsehen BW',
67             'uploader_id': '281130',
68         }
69     }]
70
71     def _real_extract(self, url):
72         mobj = re.match(self._VALID_URL, url)
73         video_id = mobj.group('id')
74
75         video = self._download_json(
76             'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id, video_id, 'Downloading video JSON')
77
78         attr = video['attr']
79         media_type = attr['entry_etype']
80
81         formats = []
82         for entry in video['sub']:
83             if entry['name'] != 'entry_media':
84                 continue
85
86             entry_attr = entry['attr']
87             codec = entry_attr['val0']
88             quality = int(entry_attr['val1'])
89
90             fmt = {
91                 'url': entry_attr['val2'],
92                 'quality': quality,
93             }
94
95             if media_type == 'Video':
96                 fmt.update({
97                     'format_note': ['144p', '288p', '544p'][quality-1],
98                     'vcodec': codec,
99                 })
100             elif media_type == 'Audio':
101                 fmt.update({
102                     'acodec': codec,
103                 })
104             formats.append(fmt)
105
106         self._sort_formats(formats)
107
108         return {
109             'id': video_id,
110             'title': attr['entry_title'],
111             'description': attr['entry_descl'],
112             'thumbnail': attr['entry_image_16_9'],
113             'duration': parse_duration(attr['entry_durat']),
114             'upload_date': attr['entry_pdatet'][:-4],
115             'uploader': attr['channel_title'],
116             'uploader_id': attr['channel_idkey'],
117             'formats': formats,
118         }