]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ccma.py
Annotate changelog with bug being closed.
[youtubedl] / youtube_dl / extractor / ccma.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 (
8 int_or_none,
9 parse_duration,
10 parse_iso8601,
11 clean_html,
12 )
13
14
15 class CCMAIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
17 _TESTS = [{
18 'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
19 'md5': '7296ca43977c8ea4469e719c609b0871',
20 'info_dict': {
21 'id': '5630208',
22 'ext': 'mp4',
23 'title': 'L\'espot de La Marató de TV3',
24 'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
25 'timestamp': 1470918540,
26 'upload_date': '20160811',
27 }
28 }, {
29 'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
30 'md5': 'fa3e38f269329a278271276330261425',
31 'info_dict': {
32 'id': '943685',
33 'ext': 'mp3',
34 'title': 'El Consell de Savis analitza el derbi',
35 'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
36 'upload_date': '20171205',
37 'timestamp': 1512507300,
38 }
39 }]
40
41 def _real_extract(self, url):
42 media_type, media_id = re.match(self._VALID_URL, url).groups()
43 media_data = {}
44 formats = []
45 profiles = ['pc'] if media_type == 'audio' else ['mobil', 'pc']
46 for i, profile in enumerate(profiles):
47 md = self._download_json('http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
48 'media': media_type,
49 'idint': media_id,
50 'profile': profile,
51 }, fatal=False)
52 if md:
53 media_data = md
54 media_url = media_data.get('media', {}).get('url')
55 if media_url:
56 formats.append({
57 'format_id': profile,
58 'url': media_url,
59 'quality': i,
60 })
61 self._sort_formats(formats)
62
63 informacio = media_data['informacio']
64 title = informacio['titol']
65 durada = informacio.get('durada', {})
66 duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
67 timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
68
69 subtitles = {}
70 subtitols = media_data.get('subtitols', {})
71 if subtitols:
72 sub_url = subtitols.get('url')
73 if sub_url:
74 subtitles.setdefault(
75 subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
76 'url': sub_url,
77 })
78
79 thumbnails = []
80 imatges = media_data.get('imatges', {})
81 if imatges:
82 thumbnail_url = imatges.get('url')
83 if thumbnail_url:
84 thumbnails = [{
85 'url': thumbnail_url,
86 'width': int_or_none(imatges.get('amplada')),
87 'height': int_or_none(imatges.get('alcada')),
88 }]
89
90 return {
91 'id': media_id,
92 'title': title,
93 'description': clean_html(informacio.get('descripcio')),
94 'duration': duration,
95 'timestamp': timestamp,
96 'thumnails': thumbnails,
97 'subtitles': subtitles,
98 'formats': formats,
99 }