]>
Commit | Line | Data |
---|---|---|
25fadd06 | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
5dd4b346 BF |
4 | import re |
5 | ||
25fadd06 | 6 | from .common import InfoExtractor |
25fadd06 | 7 | from ..utils import ( |
8 | float_or_none, | |
9938a17f | 9 | parse_iso8601, |
896c7a23 | 10 | unescapeHTML, |
25fadd06 | 11 | ) |
12 | ||
13 | ||
14 | class RteIE(InfoExtractor): | |
896c7a23 | 15 | IE_NAME = 'rte' |
16 | IE_DESC = 'Raidió Teilifís Éireann TV' | |
6df7179e | 17 | _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)' |
25fadd06 | 18 | _TEST = { |
36eb802b | 19 | 'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/', |
25fadd06 | 20 | 'info_dict': { |
36eb802b | 21 | 'id': '10478715', |
896c7a23 | 22 | 'ext': 'flv', |
36eb802b | 23 | 'title': 'Watch iWitness online', |
25fadd06 | 24 | 'thumbnail': 're:^https?://.*\.jpg$', |
36eb802b JMF |
25 | 'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.', |
26 | 'duration': 60.046, | |
ea1d5bdc PH |
27 | }, |
28 | 'params': { | |
29 | 'skip_download': 'f4m fails with --test atm' | |
25fadd06 | 30 | } |
31 | } | |
3462af03 | 32 | |
25fadd06 | 33 | def _real_extract(self, url): |
34 | video_id = self._match_id(url) | |
25fadd06 | 35 | webpage = self._download_webpage(url, video_id) |
ea1d5bdc | 36 | |
25fadd06 | 37 | title = self._og_search_title(webpage) |
ea1d5bdc PH |
38 | description = self._html_search_meta('description', webpage, 'description') |
39 | duration = float_or_none(self._html_search_meta( | |
40 | 'duration', webpage, 'duration', fatal=False), 1000) | |
41 | ||
42 | thumbnail_id = self._search_regex( | |
43 | r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail') | |
44 | thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' | |
45 | ||
611c1dd9 | 46 | feeds_url = self._html_search_meta('feeds-prefix', webpage, 'feeds url') + video_id |
25fadd06 | 47 | json_string = self._download_json(feeds_url, video_id) |
ea1d5bdc | 48 | |
25fadd06 | 49 | # f4m_url = server + relative_url |
50 | f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url'] | |
51 | f4m_formats = self._extract_f4m_formats(f4m_url, video_id) | |
19dbaeec | 52 | self._sort_formats(f4m_formats) |
ea1d5bdc | 53 | |
25fadd06 | 54 | return { |
55 | 'id': video_id, | |
56 | 'title': title, | |
57 | 'formats': f4m_formats, | |
58 | 'description': description, | |
59 | 'thumbnail': thumbnail, | |
60 | 'duration': duration, | |
ea1d5bdc | 61 | } |
896c7a23 | 62 | |
63 | ||
896c7a23 | 64 | class RteRadioIE(InfoExtractor): |
65 | IE_NAME = 'rte:radio' | |
66 | IE_DESC = 'Raidió Teilifís Éireann radio' | |
5dd4b346 BF |
67 | # Radioplayer URLs have two distinct specifier formats, |
68 | # the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>: | |
69 | # the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_ | |
896c7a23 | 70 | # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated. |
71 | # An <id> uniquely defines an individual recording, and is the only part we require. | |
5dd4b346 | 72 | _VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)' |
896c7a23 | 73 | |
5dd4b346 BF |
74 | _TESTS = [{ |
75 | # Old-style player URL; HLS and RTMPE formats | |
896c7a23 | 76 | 'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:', |
77 | 'info_dict': { | |
78 | 'id': '10507902', | |
9938a17f | 79 | 'ext': 'mp4', |
896c7a23 | 80 | 'title': 'Gloria', |
81 | 'thumbnail': 're:^https?://.*\.jpg$', | |
9938a17f S |
82 | 'description': 'md5:9ce124a7fb41559ec68f06387cabddf0', |
83 | 'timestamp': 1451203200, | |
84 | 'upload_date': '20151227', | |
896c7a23 | 85 | 'duration': 7230.0, |
86 | }, | |
87 | 'params': { | |
88 | 'skip_download': 'f4m fails with --test atm' | |
89 | } | |
5dd4b346 BF |
90 | }, { |
91 | # New-style player URL; RTMPE formats only | |
92 | 'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_', | |
93 | 'info_dict': { | |
94 | 'id': '3250678', | |
95 | 'ext': 'flv', | |
96 | 'title': 'The Lyric Concert with Paul Herriott', | |
97 | 'thumbnail': 're:^https?://.*\.jpg$', | |
98 | 'description': '', | |
99 | 'timestamp': 1333742400, | |
100 | 'upload_date': '20120406', | |
101 | 'duration': 7199.016, | |
102 | }, | |
103 | 'params': { | |
104 | 'skip_download': 'f4m fails with --test atm' | |
105 | } | |
106 | }] | |
896c7a23 | 107 | |
108 | def _real_extract(self, url): | |
109 | item_id = self._match_id(url) | |
9938a17f S |
110 | |
111 | json_string = self._download_json( | |
112 | 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id, | |
113 | item_id) | |
896c7a23 | 114 | |
115 | # NB the string values in the JSON are stored using XML escaping(!) | |
116 | show = json_string['shows'][0] | |
117 | title = unescapeHTML(show['title']) | |
118 | description = unescapeHTML(show.get('description')) | |
119 | thumbnail = show.get('thumbnail') | |
120 | duration = float_or_none(show.get('duration'), 1000) | |
9938a17f | 121 | timestamp = parse_iso8601(show.get('published')) |
896c7a23 | 122 | |
123 | mg = show['media:group'][0] | |
124 | ||
125 | formats = [] | |
126 | ||
5dd4b346 BF |
127 | if mg.get('url'): |
128 | m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url']) | |
129 | if m: | |
130 | m = m.groupdict() | |
131 | formats.append({ | |
132 | 'url': m['url'] + '/' + m['app'], | |
133 | 'app': m['app'], | |
134 | 'play_path': m['playpath'], | |
135 | 'player_url': url, | |
136 | 'ext': 'flv', | |
137 | 'format_id': 'rtmp', | |
138 | }) | |
896c7a23 | 139 | |
140 | if mg.get('hls_server') and mg.get('hls_url'): | |
9746f431 S |
141 | formats.extend(self._extract_m3u8_formats( |
142 | mg['hls_server'] + mg['hls_url'], item_id, 'mp4', | |
143 | entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) | |
896c7a23 | 144 | |
145 | if mg.get('hds_server') and mg.get('hds_url'): | |
9746f431 S |
146 | formats.extend(self._extract_f4m_formats( |
147 | mg['hds_server'] + mg['hds_url'], item_id, | |
148 | f4m_id='hds', fatal=False)) | |
149 | ||
150 | self._sort_formats(formats) | |
896c7a23 | 151 | |
152 | return { | |
153 | 'id': item_id, | |
154 | 'title': title, | |
896c7a23 | 155 | 'description': description, |
156 | 'thumbnail': thumbnail, | |
9938a17f | 157 | 'timestamp': timestamp, |
896c7a23 | 158 | 'duration': duration, |
9938a17f | 159 | 'formats': formats, |
896c7a23 | 160 | } |