aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/rtp.py42
1 files changed, 33 insertions, 9 deletions
diff --git a/youtube_dl/extractor/rtp.py b/youtube_dl/extractor/rtp.py
index 4511cba49..ecf4939cd 100644
--- a/youtube_dl/extractor/rtp.py
+++ b/youtube_dl/extractor/rtp.py
@@ -1,16 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
-import json
+import re
from .common import InfoExtractor
-from ..utils import js_to_json
class RTPIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
_TESTS = [{
'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
+ 'md5': 'e736ce0c665e459ddb818546220b4ef8',
'info_dict': {
'id': 'e174042',
'ext': 'mp3',
@@ -18,9 +18,6 @@ class RTPIE(InfoExtractor):
'description': 'As paixões musicais de António Cartaxo e António Macedo',
'thumbnail': 're:^https?://.*\.jpg',
},
- 'params': {
- 'skip_download': True, # RTMP download
- },
}, {
'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
'only_matching': True,
@@ -37,21 +34,48 @@ class RTPIE(InfoExtractor):
player_config = self._search_regex(
r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config')
- config = json.loads(js_to_json(player_config))
+ config = self._parse_json(player_config, video_id)
path, ext = config.get('file').rsplit('.', 1)
formats = [{
+ 'format_id': 'rtmp',
+ 'ext': ext,
+ 'vcodec': config.get('type') == 'audio' and 'none' or None,
+ 'preference': -2,
+ 'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
'app': config.get('application'),
'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
'page_url': url,
- 'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
'rtmp_live': config.get('live', False),
- 'ext': ext,
- 'vcodec': config.get('type') == 'audio' and 'none' or None,
'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
'rtmp_real_time': True,
}]
+ # Construct regular HTTP download URLs
+ replacements = {
+ 'audio': {
+ 'format_id': 'mp3',
+ 'pattern': r'^nas2\.share/wavrss/',
+ 'repl': 'http://rsspod.rtp.pt/podcasts/',
+ 'vcodec': 'none',
+ },
+ 'video': {
+ 'format_id': 'mp4_h264',
+ 'pattern': r'^nas2\.share/h264/',
+ 'repl': 'http://rsspod.rtp.pt/videocasts/',
+ 'vcodec': 'h264',
+ },
+ }
+ r = replacements[config['type']]
+ if re.match(r['pattern'], config['file']) is not None:
+ formats.append({
+ 'format_id': r['format_id'],
+ 'url': re.sub(r['pattern'], r['repl'], config['file']),
+ 'vcodec': r['vcodec'],
+ })
+
+ self._sort_formats(formats)
+
return {
'id': video_id,
'title': title,