fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #8445 from bpfoley/rte-newurl 

[rte:radio] Add support for RTMP downloads, alternate URL style
This commit is contained in:
Sergey M 2016-02-07 00:28:39 +05:00
parent d4f8e83404 5dd4b3468f
commit f326b5837a
1 changed files with 37 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
youtube_dl/extractor/rte.py
View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
float_or_none, float_or_none,
@ -61,12 +63,15 @@ class RteIE(InfoExtractor):
class RteRadioIE(InfoExtractor): class RteRadioIE(InfoExtractor):
IE_NAME = 'rte:radio' IE_NAME = 'rte:radio'
IE_DESC = 'Raidió Teilifís Éireann radio' IE_DESC = 'Raidió Teilifís Éireann radio'
# Radioplayer URLs have the specifier #!rii=<channel_id>:<id>:<playable_item_id>:<date>: # Radioplayer URLs have two distinct specifier formats,
# the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>:
# the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_
# where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated. # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated.
# An <id> uniquely defines an individual recording, and is the only part we require. # An <id> uniquely defines an individual recording, and is the only part we require.
_VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:[0-9]*)(?:%3A|:)(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)'
_TEST = { _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:', 'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
'info_dict': { 'info_dict': {
'id': '10507902', 'id': '10507902',
@ -81,7 +86,23 @@ class RteRadioIE(InfoExtractor):
'params': { 'params': {
'skip_download': 'f4m fails with --test atm' '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_',
'info_dict': {
'id': '3250678',
'ext': 'flv',
'title': 'The Lyric Concert with Paul Herriott',
'thumbnail': 're:^https?://.*\.jpg$',
'description': '',
'timestamp': 1333742400,
'upload_date': '20120406',
'duration': 7199.016,
},
'params': {
'skip_download': 'f4m fails with --test atm'
} }
}]
def _real_extract(self, url): def _real_extract(self, url):
item_id = self._match_id(url) item_id = self._match_id(url)
@ -102,8 +123,18 @@ class RteRadioIE(InfoExtractor):
formats = [] formats = []
if mg.get('url') and not mg['url'].startswith('rtmpe:'): if mg.get('url'):
formats.append({'url': mg['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'): if mg.get('hls_server') and mg.get('hls_url'):
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(