import re
from .common import InfoExtractor
+from ..compat import compat_HTTPError
from ..utils import (
float_or_none,
parse_iso8601,
unescapeHTML,
+ ExtractorError,
)
-class RteIE(InfoExtractor):
- IE_NAME = 'rte'
- IE_DESC = 'Raidió Teilifís Éireann TV'
- _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
- _TEST = {
- 'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
- 'info_dict': {
- 'id': '10478715',
- 'ext': 'flv',
- 'title': 'Watch iWitness online',
- 'thumbnail': 're:^https?://.*\.jpg$',
- 'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
- 'duration': 60.046,
- },
- 'params': {
- 'skip_download': 'f4m fails with --test atm'
- }
- }
-
+class RteBaseIE(InfoExtractor):
def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ item_id = self._match_id(url)
- title = self._og_search_title(webpage)
- description = self._html_search_meta('description', webpage, 'description')
- duration = float_or_none(self._html_search_meta(
- 'duration', webpage, 'duration', fatal=False), 1000)
+ try:
+ json_string = self._download_json(
+ 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
+ item_id)
+ except ExtractorError as ee:
+ if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+ error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False)
+ if error_info:
+ raise ExtractorError(
+ '%s said: %s' % (self.IE_NAME, error_info['message']),
+ expected=True)
+ raise
- thumbnail_id = self._search_regex(
- r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
- thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
+ # NB the string values in the JSON are stored using XML escaping(!)
+ show = json_string['shows'][0]
+ title = unescapeHTML(show['title'])
+ description = unescapeHTML(show.get('description'))
+ thumbnail = show.get('thumbnail')
+ duration = float_or_none(show.get('duration'), 1000)
+ timestamp = parse_iso8601(show.get('published'))
- feeds_url = self._html_search_meta('feeds-prefix', webpage, 'feeds url') + video_id
- json_string = self._download_json(feeds_url, video_id)
+ mg = show['media:group'][0]
- # f4m_url = server + relative_url
- f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
- f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
+ formats = []
+
+ if mg.get('url'):
+ m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url'])
+ if m:
+ m = m.groupdict()
+ formats.append({
+ 'url': m['url'] + '/' + m['app'],
+ 'app': m['app'],
+ 'play_path': m['playpath'],
+ 'player_url': url,
+ 'ext': 'flv',
+ 'format_id': 'rtmp',
+ })
+
+ if mg.get('hls_server') and mg.get('hls_url'):
+ formats.extend(self._extract_m3u8_formats(
+ mg['hls_server'] + mg['hls_url'], item_id, 'mp4',
+ entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+ if mg.get('hds_server') and mg.get('hds_url'):
+ formats.extend(self._extract_f4m_formats(
+ mg['hds_server'] + mg['hds_url'], item_id,
+ f4m_id='hds', fatal=False))
+
+ self._sort_formats(formats)
return {
- 'id': video_id,
+ 'id': item_id,
'title': title,
- 'formats': f4m_formats,
'description': description,
'thumbnail': thumbnail,
+ 'timestamp': timestamp,
'duration': duration,
+ 'formats': formats,
}
-class RteRadioIE(InfoExtractor):
+class RteIE(RteBaseIE):
+ IE_NAME = 'rte'
+ IE_DESC = 'Raidió Teilifís Éireann TV'
+ _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
+ 'md5': '4a76eb3396d98f697e6e8110563d2604',
+ 'info_dict': {
+ 'id': '10478715',
+ 'ext': 'mp4',
+ 'title': 'iWitness',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'description': 'The spirit of Ireland, one voice and one minute at a time.',
+ 'duration': 60.046,
+ 'upload_date': '20151012',
+ 'timestamp': 1444694160,
+ },
+ }
+
+
+class RteRadioIE(RteBaseIE):
IE_NAME = 'rte:radio'
IE_DESC = 'Raidió Teilifís Éireann radio'
# Radioplayer URLs have two distinct specifier formats,
_TESTS = [{
# Old-style player URL; HLS and RTMPE formats
'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
+ 'md5': 'c79ccb2c195998440065456b69760411',
'info_dict': {
'id': '10507902',
'ext': 'mp4',
'upload_date': '20151227',
'duration': 7230.0,
},
- 'params': {
- 'skip_download': 'f4m fails with --test atm'
- }
}, {
# New-style player URL; RTMPE formats only
'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_',
'duration': 7199.016,
},
'params': {
- 'skip_download': 'f4m fails with --test atm'
- }
+ # rtmp download
+ 'skip_download': True,
+ },
}]
-
- def _real_extract(self, url):
- item_id = self._match_id(url)
-
- json_string = self._download_json(
- 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
- item_id)
-
- # NB the string values in the JSON are stored using XML escaping(!)
- show = json_string['shows'][0]
- title = unescapeHTML(show['title'])
- description = unescapeHTML(show.get('description'))
- thumbnail = show.get('thumbnail')
- duration = float_or_none(show.get('duration'), 1000)
- timestamp = parse_iso8601(show.get('published'))
-
- mg = show['media:group'][0]
-
- formats = []
-
- if mg.get('url'):
- m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url'])
- if m:
- m = m.groupdict()
- formats.append({
- 'url': m['url'] + '/' + m['app'],
- 'app': m['app'],
- 'play_path': m['playpath'],
- 'player_url': url,
- 'ext': 'flv',
- 'format_id': 'rtmp',
- })
-
- if mg.get('hls_server') and mg.get('hls_url'):
- formats.extend(self._extract_m3u8_formats(
- mg['hls_server'] + mg['hls_url'], item_id, 'mp4',
- entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
-
- if mg.get('hds_server') and mg.get('hds_url'):
- formats.extend(self._extract_f4m_formats(
- mg['hds_server'] + mg['hds_url'], item_id,
- f4m_id='hds', fatal=False))
-
- self._sort_formats(formats)
-
- return {
- 'id': item_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'timestamp': timestamp,
- 'duration': duration,
- 'formats': formats,
- }