X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/d4ff594119bc679aa175947eb59a97bee8f966f4..a5a28b1eabe0533f26d23c4157c97144215b22b7:/youtube_dl/extractor/rtp.py?ds=sidebyside diff --git a/youtube_dl/extractor/rtp.py b/youtube_dl/extractor/rtp.py index 4511cba..533ee27 100644 --- a/youtube_dl/extractor/rtp.py +++ b/youtube_dl/extractor/rtp.py @@ -1,25 +1,26 @@ # 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[0-9]+)/(?P[^/?#]+)/?' _TESTS = [{ 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas', + 'md5': 'e736ce0c665e459ddb818546220b4ef8', 'info_dict': { 'id': 'e174042', 'ext': 'mp3', 'title': 'Paixões Cruzadas', 'description': 'As paixões musicais de António Cartaxo e António Macedo', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', }, 'params': { - 'skip_download': True, # RTMP download + # rtmp download + 'skip_download': True, }, }, { 'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas', @@ -37,21 +38,48 @@ 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,