From 25fadd06d078d54e30e187063d8b45fae31bed81 Mon Sep 17 00:00:00 2001 From: dinesh Date: Fri, 24 Oct 2014 09:49:01 +0530 Subject: [PATCH] [Rte] New extractor added --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/rte.py | 53 ++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) create mode 100644 youtube_dl/extractor/rte.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0de0b4587..7918f9ab7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -297,6 +297,7 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rte import RteIE from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py new file mode 100644 index 000000000..ab12bb5fd --- /dev/null +++ b/youtube_dl/extractor/rte.py @@ -0,0 +1,53 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + float_or_none, +) + + +class RteIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/in/show/(?P[0-9]+)/' + _TEST = { + 'url': 'http://www.rte.ie/player/in/show/10336191/', + 'info_dict': { + 'id': '10336191', + 'ext': 'mp4', + 'title': 'Nine News', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'The One O\'Clock News followed by Weather.', + 'duration': 1622963.0, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + + description = self._search_regex(r'', webpage, 'description') + duration = float_or_none(self._html_search_meta('duration', webpage, 'duration')) + + thumbnail_id = self._search_regex(r'', webpage, 'thumbnail') + thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' + + feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id + json_string = self._download_json(feeds_url, video_id) + + # 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) + for f in f4m_formats: + del f['tbr'] + + return { + 'id': video_id, + 'title': title, + 'formats': f4m_formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + } \ No newline at end of file -- 2.22.2